pjandro/OmniRoute
1
0
Fork 0
mirror of https://github.com/diegosouzapw/OmniRoute.git synced 2026-08-26 17:12:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

feat(providers): add Nimble web search and fetch (#11620)

Browse Source 
Merged via /merge-batch (lote 2026-08-26 batch 2, v3.8.51). Boarded no worktree combinado junto com outras ~20 PRs; validação única: typecheck/complexity/cognitive-complexity/changelog-integrity verdes, file-size rebaseado onde necessário (crescimento legítimo), lint com os mesmos 228 achados pré-existentes confirmados via sonda contra o tip puro (não introduzidos por este lote), e 292 testes focados (unit) + 18 (vitest) passando. Obrigado pela contribuição.
This commit is contained in:
Kobi Kadosh
2026-08-26 05:22:03 -07:00
committed by GitHub
parent c11f661a8a
commit d1768de716
72 changed files with 1416 additions and 159 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
AGENTS.md
View File

@@ -46,7 +46,7 @@ Repository map and Reference Documentation sections below.
## Project at a Glance
**OmniRoute** — unified AI proxy/router. One endpoint, 353 LLM providers, auto-fallback.
**OmniRoute** — unified AI proxy/router. One endpoint, 354 LLM providers, auto-fallback.
| Layer | Location | Purpose |
| ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

1
changelog.d/features/nimble-search-and-fetch.md Normal file
View File

@@ -0,0 +1 @@
- **feat(providers):** add **Nimble** as a web-search and web-fetch provider (`nimble-search`) — `/v1/search` routes to Nimble's search API at `lite` depth (locale, freshness and include/exclude domain filters mapped onto the shared request contract), and `/v1/web/fetch` routes to Nimble Extract, which covers all four fetch formats (`markdown`, `html`, `links`, `screenshot`) from a single call. One API key serves both surfaces.

2
docs/diagrams/cli-terminal.svg
View File

@@ -1,4 +1,4 @@
<svg viewBox="0 0 1200 350" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (353 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over 85 top-level commands: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
<svg viewBox="0 0 1200 350" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (354 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over 85 top-level commands: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
<desc>Compact animated terminal cycling three real OmniRoute CLI commands with a typewriter effect and a scrolling subcommand ticker; the first frame shows the completed providers-list screen.</desc>
<defs><clipPath id="tickerClip"><rect x="12" y="304" width="1176" height="40"/></clipPath><clipPath id="tw0"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;31;61;92;122;153;184;214;245;245" keyTimes="0;0.012;0.018;0.024;0.030;0.036;0.042;0.048;0.054;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw1"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;26;51;76;102;128;153;178;204;204" keyTimes="0;0.348;0.351;0.357;0.363;0.369;0.375;0.381;0.387;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw2"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;20;41;61;82;102;122;143;163;163" keyTimes="0;0.678;0.684;0.690;0.696;0.702;0.708;0.714;0.720;1" dur="18s" repeatCount="indefinite"/></rect></clipPath></defs>
<rect width="1200" height="350" fill="#0d1117"/>
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 12 KiB

After

Width:  |  Height:  |  Size: 12 KiB

2
docs/diagrams/comparison-table.svg
View File

@@ -1,4 +1,4 @@
<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 353 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 110 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 354 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, a built-in MCP server with 110 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
<desc>Static-header comparison table where each capability row fades in top to bottom; the OmniRoute column is highlighted and shows a check or a leading value in every row, while competitors show a mix of checks, partials and crosses.</desc>
<defs>
<pattern id="gC" width="32" height="32" patternUnits="userSpaceOnUse"><path d="M 32 0 L 0 0 0 32" fill="none" stroke="#ffffff" stroke-opacity="0.05" stroke-width="1"/></pattern>
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 13 KiB

After

Width:  |  Height:  |  Size: 13 KiB

6
docs/diagrams/promise-pillars.svg
View File

@@ -1,4 +1,4 @@
<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint and 353 providers. Six pillars. Resilient fallback: automatic routing continues while another healthy target is available. Save up to 95 percent of eligible tokens: RTK plus Caveman stacked compression averages about 89 percent on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier and 56 recurring or keyless free-forever providers. Every tool works: 35 CLI and agent integration records, including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity, through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation at /v1. Production controls: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals, and 39,000+ static test declarations across 5,100+ tracked test files.">
<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint and 354 providers. Six pillars. Resilient fallback: automatic routing continues while another healthy target is available. Save up to 95 percent of eligible tokens: RTK plus Caveman stacked compression averages about 89 percent on tool-heavy sessions. Zero dollars to start: 90+ providers with a free tier and 56 recurring or keyless free-forever providers. Every tool works: 35 CLI and agent integration records, including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity, through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation at /v1. Production controls: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals, and 39,000+ static test declarations across 5,100+ tracked test files.">
<desc>Animated promise card: six pillar tiles fade in in reading order, then a soft colored border highlight sweeps from tile to tile in a continuous cycle.</desc>
<defs>
<pattern id="gridPaperP" width="32" height="32" patternUnits="userSpaceOnUse">
@@ -21,7 +21,7 @@
<line x1="150" y1="53" x2="1160" y2="53" stroke="#232b38" stroke-width="1.5"/>
</g>
<g>
<text x="40" y="100" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="23" font-weight="600" fill="#c9d1d9">One endpoint. <tspan fill="#a78bfa" font-weight="800">353 providers.</tspan> Never stop building — OmniRoute picks <tspan fill="#7ee787" font-weight="700">the cheapest one that works</tspan>.</text>
<text x="40" y="100" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="23" font-weight="600" fill="#c9d1d9">One endpoint. <tspan fill="#a78bfa" font-weight="800">354 providers.</tspan> Never stop building — OmniRoute picks <tspan fill="#7ee787" font-weight="700">the cheapest one that works</tspan>.</text>
</g>
<g font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif">
@@ -38,7 +38,7 @@
<line x1="3.9" y1="3.9" x2="18.1" y2="18.1"/>
</g>
<text x="102" y="170" font-size="18" font-weight="800" fill="#74b9ff">Never hit limits</text>
<text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 353 providers in</text>
<text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 354 providers in</text>
<text x="66" y="226" font-size="13.5" fill="#a1a1aa">milliseconds. Quota out? The next provider</text>
<text x="66" y="248" font-size="13.5" fill="#a1a1aa">takes over while a healthy target remains.</text>
</g>
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 10 KiB

After

Width:  |  Height:  |  Size: 10 KiB

4
docs/diagrams/readme-hero.svg
View File

@@ -1,4 +1,4 @@
<svg viewBox="0 0 1200 548" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute hero: Never stop coding. Every AI tool to 353 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot and Antigravity into free Claude, GPT and Gemini with auto-fallback. RTK + Caveman stacked compression saves 15 to 95 percent of tokens — about 89 percent average on tool-heavy sessions — so you never hit limits. Stats: 353 AI providers, 90+ free tiers, about 1.51B free tokens per month, 15 to 95 percent token savings, 19 routing strategies, zero dollars to start.">
<svg viewBox="0 0 1200 548" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute hero: Never stop coding. Every AI tool to 354 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot and Antigravity into free Claude, GPT and Gemini with auto-fallback. RTK + Caveman stacked compression saves 15 to 95 percent of tokens — about 89 percent average on tool-heavy sessions — so you never hit limits. Stats: 354 AI providers, 90+ free tiers, about 1.51B free tokens per month, 15 to 95 percent token savings, 19 routing strategies, zero dollars to start.">
<desc>Animated hero card: a pulse travels the divider line and a compression bar demo repeatedly shrinks a prompt by up to 95 percent; all headline content is static and readable on the first frame.</desc>
<defs>
<pattern id="gridPaperH" width="32" height="32" patternUnits="userSpaceOnUse">
@@ -28,7 +28,7 @@
<text x="48" y="138" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="60" font-weight="800" fill="#e9edf3">Never stop coding<tspan fill="#a855f7">.</tspan></text>
<!-- subheadline -->
<text x="48" y="184" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="25" font-weight="600" fill="#c9d1d9">Every AI tool → <tspan fill="#a78bfa" font-weight="800">353 providers</tspan> — <tspan fill="#7ee787" font-weight="800">90+ free</tspan> — through one endpoint.</text>
<text x="48" y="184" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="25" font-weight="600" fill="#c9d1d9">Every AI tool → <tspan fill="#a78bfa" font-weight="800">354 providers</tspan> — <tspan fill="#7ee787" font-weight="800">90+ free</tspan> — through one endpoint.</text>
<!-- plug line -->
<text x="48" y="222" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="16.5" fill="#a1a1aa">Claude Code · Codex · Cursor · Cline · Copilot · Antigravity&#160;&#160;→&#160;&#160;<tspan fill="#7ee787" font-weight="700">FREE</tspan> Claude / GPT / Gemini · auto-fallback</text>
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 7.3 KiB

After

Width:  |  Height:  |  Size: 7.3 KiB

6
docs/frameworks/SEARCH_TOOLS_STUDIO.md
View File

@@ -57,7 +57,7 @@ New tab for extracting content from a URL via `POST /v1/web/fetch` (created in p
- Submit → fetch → render `ScrapeResult.tsx`.
- `ScrapeResult` renders markdown preview + raw toggle.
- Cap: if response body > **256 KB**, UI shows `(truncated, view raw)` and opens raw in a Monaco modal (D21).
- Metadata panel: provider (firecrawl/jina-reader/tavily-search/tinyfish), latency, cost, response size, links count.
- Metadata panel: provider (firecrawl/jina-reader/tavily-search/tinyfish/nimble-search), latency, cost, response size, links count.
- Uses `useScrapeFetch.ts` hook.
### Compare Tab
@@ -108,7 +108,7 @@ Runs the same query/URL across up to **4 providers in parallel** (D22):
| Field | Source |
| ------------------------------ | ------------------------------------------------------------------------------------------ |
| `id`, `name` | `searchRegistry.ts` |
| `kind` | `"search"` (12 providers) or `"fetch"` (firecrawl, jina-reader, tavily-search, tinyfish) |
| `kind` | `"search"` or `"fetch"` (firecrawl, jina-reader, tavily-search, tinyfish, nimble-search) |
| `costPerQuery` | Registry data |
| `freeMonthlyQuota` | Registry data |
| `searchTypes` / `fetchFormats` | Registry data |
@@ -136,7 +136,7 @@ Only one backend change was needed for this feature:
`src/app/api/search/providers/route.ts` was extended to:
- Include all 4 fetch providers (`firecrawl`, `jina-reader`, `tavily-search`, `tinyfish`) in the array.
- Include every fetch provider (`firecrawl`, `jina-reader`, `tavily-search`, `tinyfish`, `nimble-search`) in the array.
- Add `kind: "search" | "fetch"` to every item.
- Add `status: "configured" | "missing" | "rate_limited"` derived from live credential state.
- Maintain backward compatibility — existing fields (`id`, `name`, etc.) unchanged.

6
docs/i18n/ar/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/az/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/bg/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/bn/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/cs/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/da/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/de/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/es/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/fa/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/fi/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/fr/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/gu/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/he/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/hi/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/hu/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/id/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/in/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/it/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/ja/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/ko/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/mr/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/ms/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/nl/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/no/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/phi/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/pl/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/pt-BR/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/pt/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/ro/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/ru/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/sk/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/sv/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/sw/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/ta/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/te/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/th/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/tr/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/uk-UA/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/ur/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/vi/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/zh-CN/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

6
docs/i18n/zh-TW/llm.txt
View File

@@ -4,7 +4,7 @@
---
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -479,7 +479,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

23
docs/reference/API_REFERENCE.md
View File

@@ -529,7 +529,7 @@ Web/search provider abstraction (Tavily, Brave, Exa, Serper, etc.).
## Web Fetch API
Extract content from a URL via a configured web-fetch provider (Firecrawl, Jina
Reader, Tavily Extract, TinyFish Fetch).
Reader, Tavily Extract, TinyFish Fetch, Nimble Extract).
| Method | Path | Description |
| ------ | --------------- | --------------------------------------------------------- |
@@ -538,7 +538,8 @@ Reader, Tavily Extract, TinyFish Fetch).
**Auth:** Bearer API key (`extractApiKey` + `isValidApiKey`). Policy enforced via `enforceApiKeyPolicy`.
**Quota-aware fallback (#8297):** when no explicit `provider` is given, the pool
(`firecrawl` → `jina-reader` → `tavily-search` → `tinyfish`) is walked in fixed
(`firecrawl` → `jina-reader` → `tavily-search` → `tinyfish` → `nimble-search`) is
walked in fixed
priority order (fill-first) — a rate-limited-but-configured provider is skipped
instead of short-circuiting the request, and a retryable/quota upstream failure
(HTTP 429 always; 402/403 for Firecrawl/Tavily/TinyFish quota-style free tiers —
@@ -661,11 +662,21 @@ refusal. On success:
{
"allowed": true,
// present only when the key opted into per-key usage limits (daily/weekly USD):
"personal": { "dailySpentUsd": 1.25, "dailyLimitUsd": 5, "dailyResetAtIso": "…", "weeklySpentUsd": 8, "weeklyLimitUsd": 20, "weeklyResetAtIso": "…" /* … */ },
"personal": {
"dailySpentUsd": 1.25,
"dailyLimitUsd": 5,
"dailyResetAtIso": "…",
"weeklySpentUsd": 8,
"weeklyLimitUsd": 20,
"weeklyResetAtIso": "…" /* … */,
},
// the selected provider quota snapshot, or null when nothing is cached yet:
"provider": { "connectionId": "…", "provider": "claude", "plan": "…", "quotas": { /* … */ } },
"provider": { "connectionId": "…", "provider": "claude", "plan": "…", "quotas": {/* … */} },
// every connection's snapshot, so a UI can render several providers side by side:
"providers": [ { "connectionId": "…", "provider": "claude", /* … */ }, { "provider": "codex", /* … */ } ]
"providers": [
{ "connectionId": "…", "provider": "claude" /* … */ },
{ "provider": "codex" /* … */ },
],
}
```
@@ -674,7 +685,7 @@ On refusal (`401` bad key / `403` not allowed) the same route returns
(key allowed, nothing learned yet) is a different state from a refusal, and only the JSON form
distinguishes them.
**Auth:** the caller's own Bearer API key, validated with `isValidApiKey` — this is *not* the
**Auth:** the caller's own Bearer API key, validated with `isValidApiKey` — this is _not_ the
management surface (`/api/keys/…`), which stays behind `requireManagementAuth`.
---

5
docs/reference/PROVIDER_REFERENCE.md
View File

@@ -380,7 +380,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
| `vllm` | `vllm` | vLLM | Local, self-hosted | [link](https://github.com/vllm-project/vllm) | API key optional. Configure the local vLLM OpenAI-compatible base URL (default: http://localhost:8000/v1). |
| `xinference` | `xinference` | XInference | Local, self-hosted | [link](https://inference.readthedocs.io) | API key optional. Configure the local XInference OpenAI-compatible base URL (default: http://localhost:9997/v1). |
## Search Providers (15)
## Search Providers (16)
| ID | Alias | Name | Tags | Website | Notes |
|----|-------|------|------|---------|-------|
@@ -390,6 +390,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
| `firecrawl` | `fc` | Firecrawl | Search | [link](https://firecrawl.dev) | API key from firecrawl.dev/app/api-keys (or set your self-hosted Firecrawl base URL) |
| `google-pse-search` | `google-pse` | Google Programmable Search | Search | [link](https://developers.google.com/custom-search/v1/overview) | Requires a Google API key and your Programmable Search Engine ID (cx) |
| `linkup-search` | `linkup` | Linkup Search | Search | [link](https://docs.linkup.so) | Bearer API key from the Linkup dashboard |
| `nimble-search` | `nimble` | Nimble Search | Search | [link](https://docs.nimbleway.com/nimble-sdk/web-tools/search) | Bearer API key from the Nimble dashboard |
| `ollama-search` | `ollama-search` | Ollama Search | Search | [link](https://ollama.com/settings/keys) | Same API key as Ollama Cloud (from ollama.com/settings/keys) |
| `perplexity-search` | `pplx-search` | Perplexity Search | Search | [link](https://docs.perplexity.ai/guides/search-quickstart) | Same API key as Perplexity (pplx-...) |
| `searchapi-search` | `searchapi` | SearchAPI | Search | [link](https://www.searchapi.io/docs/google) | API key from SearchAPI (query param or Bearer auth) |
@@ -442,7 +443,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
- Catalog: [`src/shared/constants/providers.ts`](../../src/shared/constants/providers.ts)
- Registry (per-model details): [`open-sse/config/providerRegistry.ts`](../../open-sse/config/providerRegistry.ts)
- Executors: [`open-sse/executors/`](../../open-sse/executors/) (109 implementations)
- Executors: [`open-sse/executors/`](../../open-sse/executors/) (110 implementations)
- Translators: [`open-sse/translator/`](../../open-sse/translator/)
## See Also

6
llm.txt
View File

@@ -1,6 +1,6 @@
# OmniRoute
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 353 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 354 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
## Overview
@@ -277,7 +277,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
## Key Features (v3.8.50)
### Core Proxy
- **353 AI providers** with automatic format translation
- **354 AI providers** with automatic format translation
- **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
- **18 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline
- **4-tier fallback**: Subscription → API Key → Cheap → Free
@@ -475,7 +475,7 @@ diagnostics) plus **memory**, **skill**, **agentSkill**, **githubSkill**, **pool
## v3.8.x Highlights
- **353-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **354-provider catalog** with 90+ free tiers, one-click account imports, and bulk key add
- **19 routing strategies** — including `fusion` (parallel panel + judge synthesis), `pipeline`, `reset-aware`, `reset-window`, `headroom`, and `context-relay`
- **14-factor Auto-Combo scoring** with bandit exploration and progressive cooldown
- **MCP server expanded to 110 tools / 33 scopes** (canonical + memory/skill/agentSkill/githubSkill/pool/notion/obsidian/localCorpus/gamification/plugin modules)

17
open-sse/config/nimble.ts Normal file
View File

@@ -0,0 +1,17 @@
/**
* Nimble shared client constants.
*
* Nimble asks every integration to identify itself with a stable client-source
* header so calls can be attributed to the host product. Both Nimble surfaces
* in OmniRoute — search (`POST /v1/search`, wired in open-sse/handlers/search.ts)
* and fetch (`POST /v1/extract`, open-sse/executors/nimble-fetch.ts) — send it,
* and both read the value from here so the two can never drift apart.
*
* Docs: https://docs.nimbleway.com/api-reference/introduction
*/
/** Header Nimble uses to attribute a request to the calling product. */
export const NIMBLE_CLIENT_SOURCE_HEADER = "X-Client-Source";
/** The value OmniRoute sends. Do not vary it per surface or per request. */
export const NIMBLE_CLIENT_SOURCE = "omniroute";

21
open-sse/config/searchRegistry.ts
View File

@@ -116,6 +116,27 @@ export const SEARCH_PROVIDERS: Record<string, SearchProviderConfig> = {
cacheTTLMs: 5 * 60 * 1000,
},
// Nimble also serves POST /v1/web/fetch through the same credential — see
// open-sse/executors/nimble-fetch.ts.
"nimble-search": {
id: "nimble-search",
name: "Nimble Search",
baseUrl: "https://sdk.nimbleway.com/v1/search",
method: "POST",
authType: "apikey",
authHeader: "bearer",
costPerQuery: 0.005,
freeMonthlyQuota: 0,
searchTypes: ["web", "news"],
defaultMaxResults: 5,
maxMaxResults: 100,
// Kept below GLOBAL_TIMEOUT_MS (handlers/search.ts) so a stalled Nimble call
// still leaves budget for the failover provider instead of burning the whole
// request window.
timeoutMs: 10_000,
cacheTTLMs: 5 * 60 * 1000,
},
firecrawl: {
id: "firecrawl",
name: "Firecrawl",

222
open-sse/executors/nimble-fetch.ts Normal file
View File

@@ -0,0 +1,222 @@
/**
* Nimble Web Fetch Executor
*
* Fetches content from a URL using the Nimble Extract API.
* POST https://sdk.nimbleway.com/v1/extract
*
* Extract returns the requested formats side by side under `data`, so one call
* covers every OmniRoute fetch format: `markdown`, `html`, `links` and
* `screenshot` (base64 PNG, surfaced as a data URL).
*
* Docs: https://docs.nimbleway.com/nimble-sdk/web-tools/extract/quickstart
*/
import { sanitizeErrorMessage, buildErrorBody } from "../utils/error.ts";
import { NIMBLE_CLIENT_SOURCE, NIMBLE_CLIENT_SOURCE_HEADER } from "../config/nimble.ts";
import type { WebFetchResult, WebFetchFormat, WebFetchCredentials } from "../handlers/webFetch.ts";
const NIMBLE_EXTRACT_URL = "https://sdk.nimbleway.com/v1/extract";
const NIMBLE_TIMEOUT_MS = 30_000;
/** Max characters kept from an HTML <title> / meta description. */
const META_MAX_CHARS = 500;
// These run over untrusted upstream HTML, so every quantifier is over a character
// class that cannot cross its own terminator — no backtracking (see AGENTS.md →
// "Regex Security"). Length is capped by META_MAX_CHARS after the match, not by the
// quantifier: bounding the capture instead would make an over-long title fail to
// match at all rather than truncate.
const TITLE_RE = /<title[^>]{0,200}>([^<]*)<\/title>/i;
// One pattern per quote style. A shared ["'] class for the closing delimiter would
// cut a double-quoted description at its first apostrophe ("Don't miss…" → "Don").
const META_DESCRIPTION_DOUBLE_RE =
/<meta[^>]{0,200}name=["']description["'][^>]{0,200}content="([^"]*)"/i;
const META_DESCRIPTION_SINGLE_RE =
/<meta[^>]{0,200}name=["']description["'][^>]{0,200}content='([^']*)'/i;
/** Map an OmniRoute fetch format onto the Nimble Extract format name. */
function mapFormat(format: WebFetchFormat): string {
switch (format) {
case "html":
return "html";
case "links":
return "links";
case "screenshot":
return "screenshot";
case "markdown":
default:
return "markdown";
}
}
function readString(source: Record<string, unknown>, key: string): string {
const value = source[key];
return value != null ? String(value) : "";
}
/**
* Pull a title / description out of raw HTML.
* Extract has no dedicated metadata format, so metadata is only available when
* the caller asked for it and we requested `html` alongside their format.
*/
function parseHtmlMetadata(html: string): { title: string | null; description: string | null } {
if (!html) return { title: null, description: null };
const title = TITLE_RE.exec(html)?.[1]?.trim().slice(0, META_MAX_CHARS);
const rawDescription =
META_DESCRIPTION_DOUBLE_RE.exec(html)?.[1] ?? META_DESCRIPTION_SINGLE_RE.exec(html)?.[1];
const description = rawDescription?.trim().slice(0, META_MAX_CHARS);
return {
title: title ? title : null,
description: description ? description : null,
};
}
interface NimbleFetchOptions {
url: string;
format: WebFetchFormat;
includeMetadata: boolean;
credentials: WebFetchCredentials;
}
/**
* Execute a Nimble Extract request.
*/
export async function nimbleFetch(opts: NimbleFetchOptions): Promise<WebFetchResult> {
const { url, format, includeMetadata, credentials } = opts;
if (!credentials.apiKey) {
const body = buildErrorBody(401, "Nimble API key required");
return { success: false, status: 401, error: body.error.message };
}
const requested = mapFormat(format);
// `links` always comes back so WebFetchResponse.links is populated; `html` is
// added only when the caller asked for metadata, since it is the sole source
// of a page title/description.
const formats = [...new Set([requested, "links", ...(includeMetadata ? ["html"] : [])])];
const requestBody: Record<string, unknown> = {
url,
formats,
// Extract types `render` as `boolean | "auto"`; "auto" lets Nimble select the
// driver per target domain rather than forcing a browser on every static page.
render: "auto",
};
const controller = new AbortController();
const timeoutId = setTimeout(() => {
const err = new Error(`nimble-fetch timeout after ${NIMBLE_TIMEOUT_MS}ms`);
err.name = "TimeoutError";
controller.abort(err);
}, NIMBLE_TIMEOUT_MS);
try {
const response = await fetch(NIMBLE_EXTRACT_URL, {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${credentials.apiKey}`,
[NIMBLE_CLIENT_SOURCE_HEADER]: NIMBLE_CLIENT_SOURCE,
},
body: JSON.stringify(requestBody),
signal: controller.signal,
});
if (!response.ok) {
// Nimble returns a plain-text body on auth failures, so this must be
// sanitized before it can reach a response.
const rawError = await response.text().catch(() => `HTTP ${response.status}`);
const msg = sanitizeErrorMessage(`Nimble error ${response.status}: ${rawError}`);
const body = buildErrorBody(response.status, msg);
return { success: false, status: response.status, error: body.error.message };
}
const payload = (await response.json()) as Record<string, unknown>;
// A 200 can still carry a failed extraction — Extract reports the target's own
// outcome in the envelope. Without this the caller would get an empty document
// marked successful, and the pool in /v1/web/fetch would never fall through to
// the next provider.
const taskStatus = typeof payload.status === "string" ? payload.status : "";
const taskStatusCode = typeof payload.status_code === "number" ? payload.status_code : null;
if (
(taskStatus && taskStatus !== "success") ||
(taskStatusCode !== null && taskStatusCode >= 400)
) {
const detail = taskStatus || `status ${taskStatusCode}`;
const msg = sanitizeErrorMessage(`Nimble extraction did not succeed: ${detail}`);
const body = buildErrorBody(502, msg);
return { success: false, status: 502, error: body.error.message };
}
const data = (payload.data as Record<string, unknown> | null) ?? {};
const rawLinks = data.links;
const links: string[] = Array.isArray(rawLinks) ? rawLinks.map((l) => String(l)) : [];
const screenshot = readString(data, "screenshot");
const screenshotUrl =
format === "screenshot" && screenshot
? screenshot.startsWith("data:")
? screenshot
: `data:image/png;base64,${screenshot}`
: null;
// The requested format must actually be present. An absent key means Extract
// succeeded but produced nothing for what the caller asked for; returning an
// empty document as a success would stop /v1/web/fetch from trying the next
// provider. An empty *value* is legitimate (a genuinely blank page) and passes.
if (!(requested in data)) {
const msg = sanitizeErrorMessage(`Nimble returned no ${requested} content for the request`);
const body = buildErrorBody(502, msg);
return { success: false, status: 502, error: body.error.message };
}
let content: string;
switch (format) {
case "html":
content = readString(data, "html");
break;
case "links":
content = JSON.stringify(links);
break;
case "screenshot":
content = "";
break;
case "markdown":
default:
content = readString(data, "markdown");
break;
}
const metadata = includeMetadata ? parseHtmlMetadata(readString(data, "html")) : null;
return {
success: true,
data: {
provider: "nimble-search",
url,
content,
links,
metadata,
screenshot_url: screenshotUrl,
},
};
} catch (err: unknown) {
// The abort reason above is named "TimeoutError"; an external abort surfaces as
// "AbortError". Both must reach the 504 branch.
if (err instanceof Error && (err.name === "TimeoutError" || err.name === "AbortError")) {
const body = buildErrorBody(504, "Nimble request timed out");
return { success: false, status: 504, error: body.error.message };
}
const msg =
err instanceof Error ? sanitizeErrorMessage(err.message) : sanitizeErrorMessage(String(err));
const body = buildErrorBody(502, msg);
return { success: false, status: 502, error: body.error.message };
} finally {
clearTimeout(timeoutId);
}
}

76
open-sse/handlers/search.ts
View File

@@ -24,6 +24,7 @@ import {
isUnconfiguredLoopbackSearchProvider,
type SearchProviderConfig,
} from "../config/searchRegistry.ts";
import { NIMBLE_CLIENT_SOURCE, NIMBLE_CLIENT_SOURCE_HEADER } from "../config/nimble.ts";
import { buildPerplexityRequest, parsePerplexitySearchOptions } from "./search/perplexitySearch.ts";
import * as fcSearch from "./search/firecrawlSearch.ts";
import { type FirecrawlSearchEnvelope } from "./search/firecrawlSearch.ts";
@@ -475,6 +476,38 @@ function buildTavilyRequest(
};
}
function buildNimbleRequest(
config: SearchProviderConfig,
params: SearchRequestParams
): { url: string; init: RequestInit } {
if (!params.token) throw new Error("Nimble Search requires an API key");
const { includes, excludes } = parseDomainFilter(params.domainFilter);
const body: Record<string, unknown> = {
query: params.query,
max_results: Math.min(params.maxResults, config.maxMaxResults),
search_depth: "lite",
output_format: "plain_text",
focus: params.searchType === "news" ? "news" : "general",
};
if (params.country) body.country = params.country.toUpperCase();
if (params.language) body.locale = params.language;
if (params.timeRange && params.timeRange !== "any") body.time_range = params.timeRange;
if (includes.length) body.include_domains = includes.slice(0, 50);
if (excludes.length) body.exclude_domains = excludes.slice(0, 50);
return {
url: resolveSearchBaseUrl(config, params),
init: {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${params.token}`,
[NIMBLE_CLIENT_SOURCE_HEADER]: NIMBLE_CLIENT_SOURCE,
},
body: JSON.stringify(body),
},
};
}
function buildGooglePseRequest(
config: SearchProviderConfig,
params: SearchRequestParams
@@ -707,6 +740,7 @@ const requestBuilders: Record<string, SearchRequestBuilder> = {
"perplexity-search": buildPerplexityRequest,
"exa-search": buildExaRequest,
"tavily-search": buildTavilyRequest,
"nimble-search": buildNimbleRequest,
firecrawl: fcSearch.buildFirecrawlSearchRequest,
"google-pse-search": buildGooglePseRequest,
"linkup-search": buildLinkupRequest,
@@ -828,6 +862,47 @@ function normalizeTavilyResponse(
return { results, totalResults: results.length };
}
interface NimbleSearchItem {
title?: string;
url?: string;
description?: string;
content?: string;
}
interface NimbleSearchEnvelope {
results?: NimbleSearchItem[];
total_results?: number;
}
function normalizeNimbleResponse(
data: unknown,
_query: string,
_searchType: string
): { results: SearchResult[]; totalResults: number | null } {
const now = new Date().toISOString();
const envelope = (data ?? {}) as NimbleSearchEnvelope;
if (!Array.isArray(envelope.results)) return { results: [], totalResults: null };
const results = envelope.results.map((item, idx) =>
makeResult(
"nimble-search",
{
title: item.title,
url: item.url,
snippet: item.description || item.content?.slice(0, 300) || "",
full_text: item.content || undefined,
text_format: "text",
},
idx,
now
)
);
return {
results,
totalResults:
typeof envelope.total_results === "number" ? envelope.total_results : results.length,
};
}
function normalizeGooglePseResponse(
data: any,
_query: string,
@@ -1283,6 +1358,7 @@ const responseNormalizers: Record<string, SearchResponseNormalizer> = {
"perplexity-search": normalizePerplexityResponse,
"exa-search": normalizeExaResponse,
"tavily-search": normalizeTavilyResponse,
"nimble-search": normalizeNimbleResponse,
firecrawl: (data: FirecrawlSearchEnvelope, _query: string, searchType: string) =>
fcSearch.normalizeFirecrawlSearchResponse(data, searchType, makeResult),
"google-pse-search": normalizeGooglePseResponse,

13
open-sse/handlers/webFetch.ts
View File

@@ -21,12 +21,14 @@ import { firecrawlFetch } from "../executors/firecrawl-fetch.ts";
import { jinaReaderFetch } from "../executors/jina-reader-fetch.ts";
import { tavilyFetch } from "../executors/tavily-fetch.ts";
import { tinyfishFetch } from "../executors/tinyfish-fetch.ts";
import { nimbleFetch } from "../executors/nimble-fetch.ts";
export type WebFetchFormat = "markdown" | "html" | "links" | "screenshot";
export interface WebFetchRequest {
url: string;
provider?: "firecrawl" | "jina-reader" | "tavily-search" | "tinyfish" | "context7";
provider?:
"firecrawl" | "jina-reader" | "tavily-search" | "tinyfish" | "context7" | "nimble-search";
format?: WebFetchFormat;
depth?: 0 | 1 | 2;
wait_for_selector?: string;
@@ -61,6 +63,7 @@ export const WEB_FETCH_PROVIDERS = Object.freeze([
"tavily-search",
"tinyfish",
"context7",
"nimble-search",
] as const);
// Derived from the array — adding a provider to WEB_FETCH_PROVIDERS
// automatically widens the union; they cannot drift apart.
@@ -139,6 +142,14 @@ export async function handleWebFetch(
credentials,
});
case "nimble-search":
return await nimbleFetch({
url: req.url,
format,
includeMetadata,
credentials,
});
case "context7":
// Context7 returns llms.txt text only: html/links/screenshot formats are
// unsupported, and the format field is validated/ignored below.

2
open-sse/mcp-server/schemas/tools.ts
View File

@@ -557,7 +557,7 @@ export const webFetchInput = z.object({
.min(1, "URL is required")
.describe("The URL to fetch content from"),
provider: z
.enum(["firecrawl", "jina-reader", "tavily-search", "tinyfish", "context7"])
.enum(["firecrawl", "jina-reader", "tavily-search", "tinyfish", "context7", "nimble-search"])
.optional()
.describe(
"Specific fetch provider to use (default: first available). " +

3
open-sse/mcp-server/server.ts
View File

@@ -694,7 +694,8 @@ async function handleXSearch(args: {
async function handleWebFetch(args: {
url: string;
provider?: "firecrawl" | "jina-reader" | "tavily-search" | "tinyfish" | "context7";
provider?:
"firecrawl" | "jina-reader" | "tavily-search" | "tinyfish" | "context7" | "nimble-search";
format?: "markdown" | "html" | "links" | "screenshot";
include_metadata?: boolean;
depth?: number;

2
package.json
View File

@@ -1,7 +1,7 @@
{
"name": "omniroute",
"version": "3.8.51",
"description": "Unified AI router with 353 providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.",
"description": "Unified AI router with 354 providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.",
"type": "module",
"bin": {
"omniroute": "bin/omniroute.mjs",

7
public/providers/nimble-search.svg Normal file
View File

@@ -0,0 +1,7 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" role="img" aria-label="Nimble">
<rect width="24" height="24" rx="5" fill="#6D28D9" />
<path
d="M7 17V7h2.1l5.8 6.6V7H17v10h-2.1L9.1 10.4V17H7z"
fill="#fff"
/>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 240 B

7
src/app/api/search/providers/route.ts
View File

@@ -54,6 +54,13 @@ const FETCH_PROVIDERS: FetchProviderDef[] = [
freeMonthlyQuota: 0,
fetchFormats: ["markdown", "html"],
},
{
id: "nimble-search",
name: "Nimble Extract",
costPerQuery: 0.005,
freeMonthlyQuota: 0,
fetchFormats: ["markdown", "html", "links", "screenshot"],
},
];
// ---------------------------------------------------------------------------

20
src/lib/providers/validation/searchProviders.ts
View File

@@ -5,6 +5,10 @@ import { SAFE_OUTBOUND_FETCH_PRESETS, safeOutboundFetch } from "@/shared/network
import { getProviderOutboundGuard } from "@/shared/network/outboundUrlGuardPolicy";
import { withCustomUserAgent } from "./headers";
import { toValidationErrorResult, validationWrite } from "./transport";
import {
NIMBLE_CLIENT_SOURCE,
NIMBLE_CLIENT_SOURCE_HEADER,
} from "@omniroute/open-sse/config/nimble.ts";
export async function validateSearchProvider(
url: string,
@@ -99,6 +103,22 @@ export const SEARCH_VALIDATOR_CONFIGS: Record<
},
};
},
"nimble-search": (apiKey) => ({
url: "https://sdk.nimbleway.com/v1/search",
init: {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${apiKey}`,
[NIMBLE_CLIENT_SOURCE_HEADER]: NIMBLE_CLIENT_SOURCE,
},
body: JSON.stringify({
query: "test",
max_results: 1,
search_depth: "lite",
}),
},
}),
"linkup-search": (apiKey) => ({
url: "https://api.linkup.so/v1/search",
init: {

1
src/shared/components/ProviderIcon.tsx
View File

@@ -160,6 +160,7 @@ const KNOWN_SVGS = new Set([
"moonshot",
"morph",
"nebius",
"nimble-search",
"nlpcloud",
"nomic",
"novita",

11
src/shared/constants/providers/search.ts
View File

@@ -87,6 +87,17 @@ export const SEARCH_PROVIDERS = {
website: "https://developers.google.com/custom-search/v1/overview",
authHint: "Requires a Google API key and your Programmable Search Engine ID (cx)",
},
"nimble-search": {
id: "nimble-search",
alias: "nimble",
name: "Nimble Search",
icon: "travel_explore",
color: "#6D28D9",
textIcon: "NB",
website: "https://docs.nimbleway.com/nimble-sdk/web-tools/search",
authHint: "Bearer API key from the Nimble dashboard",
serviceKinds: ["webSearch", "webFetch"],
},
"linkup-search": {
id: "linkup-search",
alias: "linkup",

4
src/shared/validation/schemas/apiV1.ts
View File

@@ -694,7 +694,9 @@ export const v1BatchCreateSchema = z.object({
export const v1WebFetchSchema = z.object({
url: z.string().url("url must be a valid URL (http/https)"),
provider: z.enum(["firecrawl", "jina-reader", "tavily-search", "tinyfish"]).optional(),
provider: z
.enum(["firecrawl", "jina-reader", "tavily-search", "tinyfish", "context7", "nimble-search"])
.optional(),
format: z.enum(["markdown", "html", "links", "screenshot"]).default("markdown"),
depth: z.union([z.literal(0), z.literal(1), z.literal(2)]).default(0),
wait_for_selector: z.string().max(256).optional(),

7
tests/integration/search-providers-catalog.test.ts
View File

@@ -48,11 +48,11 @@ const route = await import("../../src/app/api/search/providers/route.ts");
// Constants
// ---------------------------------------------------------------------------
// 18 search-kind providers: serper, brave, perplexity, exa, tavily, firecrawl,
// 19 search-kind providers: serper, brave, perplexity, exa, tavily, nimble-search, firecrawl,
// google-pse, linkup, searchapi, youcom, searxng, ollama, zai, jina-search,
// context7 (#11140), duckduckgo-free, x-search, xquik-search.
const EXPECTED_SEARCH_COUNT = 18;
const EXPECTED_FETCH_COUNT = 4;
const EXPECTED_SEARCH_COUNT = 19;
const EXPECTED_FETCH_COUNT = 5;
const EXPECTED_TOTAL = EXPECTED_SEARCH_COUNT + EXPECTED_FETCH_COUNT;
// ---------------------------------------------------------------------------
@@ -291,6 +291,7 @@ test("search-providers-catalog: fetch providers have correct metadata", async ()
assert.ok(ids.includes("jina-reader"), "jina-reader must be present");
assert.ok(ids.includes("tavily-search"), "tavily-search must be present");
assert.ok(ids.includes("tinyfish"), "tinyfish must be present");
assert.ok(ids.includes("nimble-search"), "nimble-search must be present");
const firecrawl = fetchProviders.find((p: { id: string }) => p.id === "firecrawl");
assert.equal(firecrawl.name, "Firecrawl");

5
tests/snapshots/executors/dispatch-rules.json
View File

@@ -52,6 +52,11 @@
"status": 400,
"throws": true
},
"nimble-search": {
"message": "Provider \"nimble-search\" is a search provider and does not support chat completions; use the /v1/search endpoint instead.",
"status": 400,
"throws": true
},
"ollama-search": {
"message": "Provider \"ollama-search\" is a search provider and does not support chat completions; use the /v1/search endpoint instead.",
"status": 400,

519
tests/unit/executor-nimble-fetch.test.ts Normal file
View File

@@ -0,0 +1,519 @@
import test from "node:test";
import assert from "node:assert/strict";
const { nimbleFetch } = await import("../../open-sse/executors/nimble-fetch.ts");
const { NIMBLE_CLIENT_SOURCE, NIMBLE_CLIENT_SOURCE_HEADER } =
await import("../../open-sse/config/nimble.ts");
const PAGE_HTML =
"<html><head><title>Example Domain</title>" +
'<meta name="description" content="An example page"></head><body>hi</body></html>';
function extractResponse(data: Record<string, unknown>) {
return new Response(
JSON.stringify({
url: "https://example.com/",
task_id: "00000000-0000-0000-0000-000000000000",
status: "success",
status_code: 200,
data,
metadata: { driver: "vx6", query_duration: 533 },
}),
{ status: 200, headers: { "content-type": "application/json" } }
);
}
test("nimbleFetch posts to /v1/extract with bearer auth and the omniroute client-source header", async () => {
const originalFetch = globalThis.fetch;
let captured: { url: string; init: RequestInit } = { url: "", init: {} };
globalThis.fetch = async (url, init = {}) => {
captured = { url: String(url), init: init as RequestInit };
return extractResponse({ markdown: "# Example Domain", links: [] });
};
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: false,
credentials: { apiKey: "nimble-key" },
});
assert.equal(result.success, true);
assert.equal(captured.url, "https://sdk.nimbleway.com/v1/extract");
assert.equal(captured.init.method, "POST");
const headers = captured.init.headers as Record<string, string>;
assert.equal(headers.Authorization, "Bearer nimble-key");
assert.equal(headers[NIMBLE_CLIENT_SOURCE_HEADER], NIMBLE_CLIENT_SOURCE);
assert.equal(headers[NIMBLE_CLIENT_SOURCE_HEADER], "omniroute");
const body = JSON.parse(String(captured.init.body));
assert.equal(body.url, "https://example.com");
assert.deepEqual(body.formats, ["markdown", "links"]);
assert.equal(body.render, "auto");
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch requests each OmniRoute format from Extract and returns the matching field", async () => {
const cases: Array<{
format: "markdown" | "html" | "links" | "screenshot";
data: Record<string, unknown>;
expectFormats: string[];
expectContent: string;
}> = [
{
format: "markdown",
data: { markdown: "# Title", links: ["https://a.example"] },
expectFormats: ["markdown", "links"],
expectContent: "# Title",
},
{
format: "html",
data: { html: "<p>hi</p>", links: [] },
expectFormats: ["html", "links"],
expectContent: "<p>hi</p>",
},
{
format: "links",
data: { links: ["https://a.example", "https://b.example"] },
expectFormats: ["links"],
expectContent: '["https://a.example","https://b.example"]',
},
{
format: "screenshot",
data: { screenshot: "iVBORw0KGgo=", links: [] },
expectFormats: ["screenshot", "links"],
expectContent: "",
},
];
for (const testCase of cases) {
const originalFetch = globalThis.fetch;
let formats: string[] = [];
globalThis.fetch = async (_url, init = {}) => {
formats = JSON.parse(String((init as RequestInit).body)).formats;
return extractResponse(testCase.data);
};
try {
const result = await nimbleFetch({
url: "https://example.com",
format: testCase.format,
includeMetadata: false,
credentials: { apiKey: "nimble-key" },
});
assert.equal(result.success, true, `${testCase.format} should succeed`);
assert.deepEqual(formats, testCase.expectFormats, `${testCase.format} request formats`);
assert.equal(result.data?.content, testCase.expectContent, `${testCase.format} content`);
} finally {
globalThis.fetch = originalFetch;
}
}
});
test("nimbleFetch surfaces a base64 screenshot as a data URL", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () => extractResponse({ screenshot: "iVBORw0KGgo=", links: [] });
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "screenshot",
includeMetadata: false,
credentials: { apiKey: "nimble-key" },
});
assert.equal(result.data?.screenshot_url, "data:image/png;base64,iVBORw0KGgo=");
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch always returns links and only requests html for metadata", async () => {
const originalFetch = globalThis.fetch;
let formats: string[] = [];
globalThis.fetch = async (_url, init = {}) => {
formats = JSON.parse(String((init as RequestInit).body)).formats;
return extractResponse({
markdown: "# Example Domain",
html: PAGE_HTML,
links: ["https://iana.org/domains/example"],
});
};
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: true,
credentials: { apiKey: "nimble-key" },
});
assert.deepEqual(formats, ["markdown", "links", "html"]);
assert.equal(result.data?.provider, "nimble-search");
assert.deepEqual(result.data?.links, ["https://iana.org/domains/example"]);
assert.equal(result.data?.metadata?.title, "Example Domain");
assert.equal(result.data?.metadata?.description, "An example page");
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch keeps an apostrophe inside a double-quoted meta description", async () => {
const originalFetch = globalThis.fetch;
const html =
"<html><head><title>Sale</title>" +
'<meta name="description" content="Don\'t miss our sale — it\'s on now"></head></html>';
globalThis.fetch = async () => extractResponse({ markdown: "body", html, links: [] });
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: true,
credentials: { apiKey: "nimble-key" },
});
// A shared ["'] closing class would cut this at "Don".
assert.equal(result.data?.metadata?.description, "Don't miss our sale — it's on now");
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch reads a single-quoted meta description", async () => {
const originalFetch = globalThis.fetch;
const html = "<html><head><meta name='description' content='Plain single quoted'></head></html>";
globalThis.fetch = async () => extractResponse({ markdown: "body", html, links: [] });
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: true,
credentials: { apiKey: "nimble-key" },
});
assert.equal(result.data?.metadata?.description, "Plain single quoted");
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch truncates an over-long title instead of dropping it", async () => {
const originalFetch = globalThis.fetch;
const longTitle = "T".repeat(600);
const html = `<html><head><title>${longTitle}</title></head></html>`;
globalThis.fetch = async () => extractResponse({ markdown: "body", html, links: [] });
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: true,
credentials: { apiKey: "nimble-key" },
});
// A capture bounded at 500 would fail to reach </title> and yield null.
assert.equal(result.data?.metadata?.title, "T".repeat(500));
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch fails a 200 whose envelope reports an unsuccessful extraction", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () =>
new Response(
JSON.stringify({
url: "https://example.com/",
task_id: "00000000-0000-0000-0000-000000000000",
status: "failed",
status_code: 404,
data: {},
metadata: {},
}),
{ status: 200, headers: { "content-type": "application/json" } }
);
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: false,
credentials: { apiKey: "nimble-key" },
});
// Must not be reported as an empty-but-successful document: the fetch pool only
// falls through to the next provider when the result is a failure.
assert.equal(result.success, false);
assert.equal(result.status, 502);
assert.ok(!result.error?.includes("at /"), "error must not contain a stack trace");
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch fails a 200 whose envelope carries only an error status_code", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () =>
new Response(JSON.stringify({ url: "https://example.com/", status_code: 403, data: {} }), {
status: 200,
headers: { "content-type": "application/json" },
});
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: false,
credentials: { apiKey: "nimble-key" },
});
assert.equal(result.success, false);
assert.equal(result.status, 502);
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch omits metadata when includeMetadata is false", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () => extractResponse({ markdown: "body", html: PAGE_HTML, links: [] });
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: false,
credentials: { apiKey: "nimble-key" },
});
assert.equal(result.data?.metadata, null);
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch returns null metadata fields when the page has no title or description", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () =>
extractResponse({ markdown: "body", html: "<html><body>hi</body></html>", links: [] });
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: true,
credentials: { apiKey: "nimble-key" },
});
assert.deepEqual(result.data?.metadata, { title: null, description: null });
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch accepts a genuinely blank page (format present, value empty)", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () => extractResponse({ markdown: "" });
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: false,
credentials: { apiKey: "nimble-key" },
});
assert.equal(result.success, true);
assert.equal(result.data?.content, "");
assert.deepEqual(result.data?.links, []);
assert.equal(result.data?.screenshot_url, null);
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch fails when the requested format is absent from the response", async () => {
for (const format of ["markdown", "html", "links", "screenshot"] as const) {
const originalFetch = globalThis.fetch;
// Envelope says success, but nothing backing the requested format came back.
globalThis.fetch = async () => extractResponse({});
try {
const result = await nimbleFetch({
url: "https://example.com",
format,
includeMetadata: false,
credentials: { apiKey: "nimble-key" },
});
// Must be a failure so the /v1/web/fetch pool falls through to the next
// provider instead of returning an empty document as a success.
assert.equal(result.success, false, `${format} should fail`);
assert.equal(result.status, 502, `${format} status`);
assert.ok(!result.error?.includes("at /"), "error must not contain a stack trace");
} finally {
globalThis.fetch = originalFetch;
}
}
});
test("nimbleFetch returns 401 when no API key is configured", async () => {
const originalFetch = globalThis.fetch;
let called = false;
globalThis.fetch = async () => {
called = true;
return extractResponse({});
};
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: false,
credentials: {},
});
assert.equal(result.success, false);
assert.equal(result.status, 401);
assert.equal(called, false, "must not call Nimble without a key");
assert.ok(!result.error?.includes("at /"), "error must not contain a stack trace");
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch sanitizes an invalid-credential response", async () => {
const originalFetch = globalThis.fetch;
// Nimble answers auth failures with a plain-text body, not JSON.
globalThis.fetch = async () =>
new Response("unauthorized: bearer token validation failed", {
status: 401,
headers: { "content-type": "text/plain" },
});
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: false,
credentials: { apiKey: "bad-key" },
});
assert.equal(result.success, false);
assert.equal(result.status, 401);
assert.ok(result.error, "should carry an error message");
assert.ok(!result.error!.includes("at /"), "error must not contain a stack trace");
assert.ok(!result.error!.includes("bad-key"), "error must not echo the API key");
} finally {
globalThis.fetch = originalFetch;
}
});
test("nimbleFetch propagates a rate-limit response as 429", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () =>
new Response(JSON.stringify({ message: "Too Many Requests" }), {
status: 429,
headers: { "content-type": "application/json" },
});
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: false,
credentials: { apiKey: "nimble-key" },
});
assert.equal(result.success, false);
assert.equal(result.status, 429);
assert.ok(!result.error?.includes("at /"), "error must not contain a stack trace");
} finally {
globalThis.fetch = originalFetch;
}
});
// The executor aborts with a reason named "TimeoutError"; an external abort surfaces
// as "AbortError". Both must produce a 504, not the generic 502 transport branch.
for (const name of ["TimeoutError", "AbortError"]) {
test(`nimbleFetch maps ${name} to a 504 timeout`, async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () => {
const err = new Error("aborted");
err.name = name;
throw err;
};
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: false,
credentials: { apiKey: "nimble-key" },
});
assert.equal(result.success, false);
assert.equal(result.status, 504);
} finally {
globalThis.fetch = originalFetch;
}
});
}
test("nimbleFetch rejects with its own abort reason, which is a TimeoutError", async () => {
// Pins the contract the two tests above rely on: the reason the executor passes to
// controller.abort() is what fetch rejects with, so the 504 branch must match its name.
const controller = new AbortController();
const reason = new Error("nimble-fetch timeout after 30000ms");
reason.name = "TimeoutError";
controller.abort(reason);
assert.equal((controller.signal.reason as Error).name, "TimeoutError");
});
test("nimbleFetch maps an unexpected transport failure to a sanitized 502", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () => {
throw new Error("socket hang up");
};
try {
const result = await nimbleFetch({
url: "https://example.com",
format: "markdown",
includeMetadata: false,
credentials: { apiKey: "nimble-key" },
});
assert.equal(result.success, false);
assert.equal(result.status, 502);
assert.ok(!result.error?.includes("at /"), "error must not contain a stack trace");
} finally {
globalThis.fetch = originalFetch;
}
});

320
tests/unit/search-nimble-provider.test.ts Normal file
View File

@@ -0,0 +1,320 @@
import test from "node:test";
import assert from "node:assert/strict";
import { mkdtempSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
process.env.DATA_DIR = mkdtempSync(join(tmpdir(), "omniroute-search-nimble-"));
const { handleSearch } = await import("../../open-sse/handlers/search.ts");
const { SEARCH_PROVIDERS } = await import("../../open-sse/config/searchRegistry.ts");
const { NIMBLE_CLIENT_SOURCE, NIMBLE_CLIENT_SOURCE_HEADER } =
await import("../../open-sse/config/nimble.ts");
/** A `lite`-depth /v1/search payload: `description` carries the snippet, `content` is empty. */
function nimbleSearchPayload() {
return {
total_results: 2,
request_id: "00000000-0000-0000-0000-000000000000",
results: [
{
title: "Nimble — real-time web data",
url: "https://www.nimbleway.com/product?ref=1",
description: "Structured web data for AI applications.",
content: "",
metadata: { position: 1, entity_type: "SearchResult", country: "US", locale: "en" },
},
{
title: "Nimble docs",
url: "https://docs.nimbleway.com/",
description: "",
content: "Full page body captured at a deeper search depth.",
metadata: { position: 2, entity_type: "SearchResult", country: "US", locale: "en" },
},
],
};
}
test("nimble-search is registered with the /v1/search endpoint and bearer auth", () => {
const provider = SEARCH_PROVIDERS["nimble-search"];
assert.ok(provider, "nimble-search must be in the search registry");
assert.equal(provider.baseUrl, "https://sdk.nimbleway.com/v1/search");
assert.equal(provider.method, "POST");
assert.equal(provider.authType, "apikey");
assert.equal(provider.authHeader, "bearer");
assert.deepEqual(provider.searchTypes, ["web", "news"]);
});
test("handleSearch builds a Nimble request with the omniroute client-source header", async () => {
const originalFetch = globalThis.fetch;
let captured: { url: string; headers: Record<string, string>; body: Record<string, unknown> } = {
url: "",
headers: {},
body: {},
};
globalThis.fetch = async (url, init = {}) => {
const request = init as RequestInit;
captured = {
url: String(url),
headers: request.headers as Record<string, string>,
body: JSON.parse(String(request.body || "{}")),
};
return new Response(JSON.stringify(nimbleSearchPayload()), {
status: 200,
headers: { "content-type": "application/json" },
});
};
try {
const result = await handleSearch({
query: " nimble web data ",
provider: "nimble-search",
maxResults: 2,
searchType: "web",
country: "us",
language: "en",
timeRange: "month",
domainFilter: ["nimbleway.com", "-spam.example"],
credentials: { apiKey: "nimble-key" },
log: null,
});
assert.equal(result.success, true);
assert.equal(captured.url, "https://sdk.nimbleway.com/v1/search");
assert.equal(captured.headers.Authorization, "Bearer nimble-key");
assert.equal(captured.headers[NIMBLE_CLIENT_SOURCE_HEADER], NIMBLE_CLIENT_SOURCE);
assert.equal(captured.headers[NIMBLE_CLIENT_SOURCE_HEADER], "omniroute");
assert.deepEqual(captured.body, {
query: "nimble web data",
max_results: 2,
search_depth: "lite",
output_format: "plain_text",
focus: "general",
country: "US",
locale: "en",
time_range: "month",
include_domains: ["nimbleway.com"],
exclude_domains: ["spam.example"],
});
} finally {
globalThis.fetch = originalFetch;
}
});
test("handleSearch maps search_type=news onto the Nimble news focus", async () => {
const originalFetch = globalThis.fetch;
let body: Record<string, unknown> = {};
globalThis.fetch = async (_url, init = {}) => {
body = JSON.parse(String((init as RequestInit).body || "{}"));
return new Response(JSON.stringify(nimbleSearchPayload()), { status: 200 });
};
try {
await handleSearch({
query: "nimble",
provider: "nimble-search",
maxResults: 5,
searchType: "news",
credentials: { apiKey: "nimble-key" },
log: null,
});
assert.equal(body.focus, "news");
// Regression guard: `focus` must stay a scalar. Sending an array makes Nimble
// read it as a list of Web Search Agent subagents and reject the call with 422.
assert.equal(Array.isArray(body.focus), false, "focus must not be an array");
// Optional locale/date filters stay off the wire when the caller omits them.
assert.equal("country" in body, false);
assert.equal("time_range" in body, false);
} finally {
globalThis.fetch = originalFetch;
}
});
test("handleSearch normalizes Nimble results into the shared SearchResult shape", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () =>
new Response(JSON.stringify(nimbleSearchPayload()), {
status: 200,
headers: { "content-type": "application/json" },
});
try {
const result = await handleSearch({
query: "nimble",
provider: "nimble-search",
maxResults: 5,
searchType: "web",
credentials: { apiKey: "nimble-key" },
log: null,
});
assert.equal(result.success, true);
const data = result.data!;
assert.equal(data.provider, "nimble-search");
assert.equal(data.metrics.total_results_available, 2);
const [first, second] = data.results;
assert.equal(first.title, "Nimble — real-time web data");
assert.equal(first.url, "https://www.nimbleway.com/product?ref=1");
assert.equal(first.display_url, "nimbleway.com/product");
assert.equal(first.position, 1);
assert.equal(first.citation.provider, "nimble-search");
assert.equal(first.citation.rank, 1);
// `lite` depth: the snippet comes from `description`, and there is no full text.
assert.equal(first.snippet, "Structured web data for AI applications.");
assert.equal(first.content, null);
// Deeper depths populate `content`; it becomes both the snippet fallback and full text.
assert.equal(second.snippet, "Full page body captured at a deeper search depth.");
assert.equal(second.content?.format, "text");
assert.equal(second.content?.text, "Full page body captured at a deeper search depth.");
assert.equal(
second.content?.length,
"Full page body captured at a deeper search depth.".length
);
} finally {
globalThis.fetch = originalFetch;
}
});
test("handleSearch returns an empty result set when Nimble finds nothing", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () =>
new Response(JSON.stringify({ total_results: 0, results: [], request_id: "x" }), {
status: 200,
headers: { "content-type": "application/json" },
});
try {
const result = await handleSearch({
query: "a query with no hits",
provider: "nimble-search",
maxResults: 5,
searchType: "web",
credentials: { apiKey: "nimble-key" },
log: null,
});
assert.equal(result.success, true);
assert.deepEqual(result.data?.results, []);
assert.equal(result.data?.metrics.total_results_available, 0);
} finally {
globalThis.fetch = originalFetch;
}
});
test("handleSearch rejects a Nimble request with no credentials before calling out", async () => {
const originalFetch = globalThis.fetch;
let called = false;
globalThis.fetch = async () => {
called = true;
return new Response("{}", { status: 200 });
};
try {
const result = await handleSearch({
query: "nimble",
provider: "nimble-search",
maxResults: 5,
searchType: "web",
credentials: {},
log: null,
});
assert.equal(result.success, false);
assert.equal(result.status, 401);
assert.equal(called, false, "must not call Nimble without a key");
} finally {
globalThis.fetch = originalFetch;
}
});
test("handleSearch surfaces an invalid Nimble key without leaking a stack trace", async () => {
const originalFetch = globalThis.fetch;
// Nimble answers an auth failure with a plain-text body, not JSON.
globalThis.fetch = async () =>
new Response("unauthorized: bearer token validation failed", {
status: 401,
headers: { "content-type": "text/plain" },
});
try {
const result = await handleSearch({
query: "nimble",
provider: "nimble-search",
maxResults: 5,
searchType: "web",
credentials: { apiKey: "bad-key" },
log: null,
});
assert.equal(result.success, false);
assert.equal(result.status, 401);
assert.ok(result.error, "should carry an error message");
assert.ok(!result.error!.includes("at /"), "error must not contain a stack trace");
assert.ok(!result.error!.includes("bad-key"), "error must not echo the API key");
} finally {
globalThis.fetch = originalFetch;
}
});
test("handleSearch propagates a Nimble rate-limit response as 429", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () =>
new Response(JSON.stringify({ message: "Too Many Requests" }), {
status: 429,
headers: { "content-type": "application/json", "retry-after": "30" },
});
try {
const result = await handleSearch({
query: "nimble",
provider: "nimble-search",
maxResults: 5,
searchType: "web",
credentials: { apiKey: "nimble-key" },
log: null,
});
assert.equal(result.success, false);
assert.equal(result.status, 429);
assert.ok(!result.error?.includes("at /"), "error must not contain a stack trace");
} finally {
globalThis.fetch = originalFetch;
}
});
test("handleSearch maps a Nimble timeout to 504", async () => {
const originalFetch = globalThis.fetch;
globalThis.fetch = async () => {
const err = new Error("aborted");
err.name = "AbortError";
throw err;
};
try {
const result = await handleSearch({
query: "nimble",
provider: "nimble-search",
maxResults: 5,
searchType: "web",
credentials: { apiKey: "nimble-key" },
log: null,
});
assert.equal(result.success, false);
assert.equal(result.status, 504);
} finally {
globalThis.fetch = originalFetch;
}
});

6
tests/unit/search-registry.test.ts
View File

@@ -25,6 +25,7 @@ test("SEARCH_PROVIDERS has all registered providers", () => {
assert.ok(SEARCH_PROVIDERS["perplexity-search"], "perplexity-search should exist");
assert.ok(SEARCH_PROVIDERS["exa-search"], "exa should exist");
assert.ok(SEARCH_PROVIDERS["tavily-search"], "tavily should exist");
assert.ok(SEARCH_PROVIDERS["nimble-search"], "nimble should exist");
assert.ok(SEARCH_PROVIDERS["firecrawl"], "firecrawl should exist");
assert.ok(SEARCH_PROVIDERS["google-pse-search"], "google-pse should exist");
assert.ok(SEARCH_PROVIDERS["linkup-search"], "linkup should exist");
@@ -39,7 +40,7 @@ test("SEARCH_PROVIDERS has all registered providers", () => {
assert.ok(SEARCH_PROVIDERS["xquik-search"], "xquik-search should exist");
// #11140: context7 provides library-docs search
assert.ok(SEARCH_PROVIDERS["context7"], "context7 should exist");
assert.equal(Object.keys(SEARCH_PROVIDERS).length, 18);
assert.equal(Object.keys(SEARCH_PROVIDERS).length, 19);
});
test("duckduckgo-free config is a no-key, fallback-only provider", () => {
@@ -173,7 +174,7 @@ test("zai-search config is correct", () => {
test("getAllSearchProviders returns flat list", () => {
const all = getAllSearchProviders();
assert.equal(all.length, 18);
assert.equal(all.length, 19);
assert.ok(all.some((p) => p.id === "duckduckgo-free"));
assert.ok(all.some((p) => p.id === "jina-search"));
assert.ok(all.some((p) => p.id === "x-search"));
@@ -183,6 +184,7 @@ test("getAllSearchProviders returns flat list", () => {
assert.ok(all.some((p) => p.id === "perplexity-search"));
assert.ok(all.some((p) => p.id === "exa-search"));
assert.ok(all.some((p) => p.id === "tavily-search"));
assert.ok(all.some((p) => p.id === "nimble-search"));
assert.ok(all.some((p) => p.id === "google-pse-search"));
assert.ok(all.some((p) => p.id === "linkup-search"));
assert.ok(all.some((p) => p.id === "searchapi-search"));

3
tests/unit/search-route.test.ts
View File

@@ -52,13 +52,14 @@ test("v1 search GET lists all search providers", async () => {
assert.equal(response.status, 200);
assert.equal(body.object, "list");
assert.equal(body.data.length, 18);
assert.equal(body.data.length, 19);
assert.deepEqual(ids, [
"serper-search",
"brave-search",
"perplexity-search",
"exa-search",
"tavily-search",
"nimble-search",
"firecrawl",
"google-pse-search",
"linkup-search",