diff --git a/README.md b/README.md index 8715a6ca9a..fceab416f4 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@ # 🚀 OmniRoute — The Free AI Gateway -OmniRoute — Never stop coding. Every AI tool → 278 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 278 AI providers · 90+ free tiers · ~1.53B free tokens/mo · 18 routing strategies · $0 to start. +OmniRoute — Never stop coding. Every AI tool → 278 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 278 AI providers · 90+ free tiers · ~1.53B free tokens/mo · 19 routing strategies · $0 to start. @@ -137,7 +137,7 @@ curl http://localhost:20128/v1/chat/completions \ - ✅ **`auto` responds immediately** — OmniRoute builds a virtual combo from the built-in keyless free providers and routes to a healthy one, with no setup. - ➕ **Add more providers anytime** — drop in a Claude / GPT / Gemini key (or any of the 278 providers) from the dashboard and they join the `auto` pool automatically. -- 🎛️ **Build your own free combos** — chain your free tiers with any of the 18 routing strategies so you never run out of quota. +- 🎛️ **Build your own free combos** — chain your free tiers with any of the 19 routing strategies so you never run out of quota. Prefer a specific free backend? Call it directly, e.g. `oc/…` (OpenCode Free) or `felo/…` (Felo). Then graduate to `auto` and let OmniRoute pick. @@ -147,7 +147,7 @@ curl http://localhost:20128/v1/chat/completions \ -The Promise — One endpoint. 278 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 278 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 40+ free forever — no card needed) · Every tool works (26 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 104 tools, A2A, memory, guardrails, evals — 25,000+ tests). +The Promise — One endpoint. 278 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 278 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 40+ free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 104 tools, A2A, memory, guardrails, evals — 25,000+ tests).

@@ -162,7 +162,7 @@ curl http://localhost:20128/v1/chat/completions \
-OmniRoute request flow: your IDE or CLI (Claude Code, Cursor, Cline…) calls one local endpoint (http://localhost:20128/v1); the OmniRoute Smart Router (RTK + Caveman compression, 18 routing strategies, circuit breakers, TLS stealth, MCP, A2A, guardrails) auto-falls back across 4 provider tiers — Tier 1 Subscription (Claude Code, Codex, Copilot), quota out? Tier 2 API Key (DeepSeek, Groq, xAI), budget hit? Tier 3 Cheap (GLM $0.5, MiniMax $0.2), budget hit? Tier 4 Free (Kiro, Qoder, Pollinations) — always on. +OmniRoute request flow: your IDE or CLI (Claude Code, Cursor, Cline…) calls one local endpoint (http://localhost:20128/v1); the OmniRoute Smart Router (RTK + Caveman compression, 19 routing strategies, circuit breakers, TLS stealth, MCP, A2A, guardrails) auto-falls back across 4 provider tiers — Tier 1 Subscription (Claude Code, Codex, Copilot), quota out? Tier 2 API Key (DeepSeek, Groq, xAI), budget hit? Tier 3 Cheap (GLM $0.5, MiniMax $0.2), budget hit? Tier 4 Free (Kiro, Qoder, Pollinations) — always on.
@@ -191,9 +191,9 @@ No combo to create. Set your model to `auto` (or a variant) and OmniRoute builds ## -### 🔀 Or build your own — 18 routing strategies +### 🔀 Or build your own — 19 routing strategies -All **18** strategies — mix & match per combo step: +All **19** strategies — mix & match per combo step: | # | Strategy | What it does                                                                                                                                                             | | --- | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | @@ -211,12 +211,13 @@ All **18** strategies — mix & match per combo step: | 12 | `reset-aware` | Rank by quota reset time — short windows first 📊 | | 13 | `context-relay` | Hand off context across targets for long conversations 🧠 | | 14 | `context-optimized` | Pick the best fit for the current context size | -| 15 | `lkgp` | Last-Known-Good Path — sticky to the last successful target | -| 16 | `auto` | 12-factor live scoring across every connection 🤖 | -| 17 | `fusion` | Fan out to a panel of models + a judge synthesizes one answer 🧬 | -| 18 | `pipeline` | Chain steps — each target's output feeds the next one 🔗 | +| 15 | `cache-optimized` | Pin each reusable prompt prefix to the same account — maximize prompt-cache hits 🎯 | +| 16 | `lkgp` | Last-Known-Good Path — sticky to the last successful target | +| 17 | `auto` | 12-factor live scoring across every connection 🤖 | +| 18 | `fusion` | Fan out to a panel of models + a judge synthesizes one answer 🧬 | +| 19 | `pipeline` | Chain steps — each target's output feeds the next one 🔗 | -All 18 combo routing strategies animated, one tile per strategy showing the flow it executes: priority (drain the 1st, then the next), fill-first (fill a target's quota, then move on), weighted (weighted random), round-robin (cycle in order), p2c (pick 2, take the lighter), least-used (lowest load wins), random (uniform, deduped), strict-random (repeats allowed), cost-optimized (cheapest $ per request), headroom (most remaining quota), reset-window (resets soonest → use it), reset-aware (rank by reset, short first), context-relay (hand off long context), context-optimized (fit the context size), lkgp (sticky to last success), auto (live 12-factor scoring), fusion (panel + judge → one answer), pipeline (each output feeds the next). +All 19 combo routing strategies animated — one tile per strategy: priority, fill-first, weighted, round-robin, p2c, least-used, random, strict-random, cost-optimized, headroom, reset-window, reset-aware, context-relay, context-optimized, cache-optimized, lkgp, auto, fusion, pipeline. See the table above for what each one does. The Auto-Combo engine scores every candidate on **12 factors** (health, quota, cost, latency, success rate, freshness…) — see [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md). @@ -253,20 +254,20 @@ All **18** strategies — mix & match per combo step: -| Feature | OmniRoute | Other routers | -| -------------------------------------- | ------------------------------------------------------------------- | ------------- | -| 🌐 Providers | **278** | 20–100 | -| 🆓 Free providers | **90+ (40+ free forever)** | 1–5 | -| 🔀 Routing strategies | **18** (priority, weighted, cost-optimized, context-relay, fusion…) | 1–3 | -| 🗜️ Token compression | **RTK + Caveman stacked (15–95%)** | None / 20–40% | -| 🧰 Built-in MCP server | **104 tools, 3 transports, 31 scopes** | Rare | -| 🤝 A2A agent protocol | **6 skills, JSON-RPC 2.0** | None | -| 🧠 Memory (FTS5 + vector) | **Yes** | Rare | -| 🛡️ Guardrails (PII, injection, vision) | **Yes** | Rare | -| ☁️ Cloud agents | **Codex, Cursor, Devin, Jules** | None | -| 🥷 TLS fingerprint stealth | **JA3/JA4 via wreq-js** | None | -| 🖥️ Multi-platform | **Web · Desktop · Termux · PWA** | Web only | -| 🌍 i18n | **43 locales** | 0–4 | +| Feature | OmniRoute | Other routers | +| -------------------------------------- | -------------------------------------- | ------------- | +| 🌐 Providers | **278** | 20–100 | +| 🆓 Free providers | **90+ (40+ free forever)** | 1–5 | +| 🔀 Routing strategies | **19** strategies | 1–3 | +| 🗜️ Token compression | **RTK + Caveman stacked (15–95%)** | None / 20–40% | +| 🧰 Built-in MCP server | **104 tools, 3 transports, 31 scopes** | Rare | +| 🤝 A2A agent protocol | **6 skills, JSON-RPC 2.0** | None | +| 🧠 Memory (FTS5 + vector) | **Yes** | Rare | +| 🛡️ Guardrails (PII, injection, vision) | **Yes** | Rare | +| ☁️ Cloud agents | **Codex, Cursor, Devin, Jules** | None | +| 🥷 TLS fingerprint stealth | **JA3/JA4 via wreq-js** | None | +| 🖥️ Multi-platform | **Web · Desktop · Termux · PWA** | Web only | +| 🌍 i18n | **43 locales** | 0–4 | 📊 Detailed comparison vs LiteLLM, OpenRouter & Portkey → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md) @@ -282,7 +283,7 @@ All **18** strategies — mix & match per combo step: - **🗜️ Compression hardening** — default-on inflation guard, Caveman packs for DE / FR / JA + Chinese (wényán), RTK filters for Gradle & .NET. → [Compression](docs/compression/COMPRESSION_ENGINES.md) - **💸 Honest flat-rate cost** — subscription / coding-plan providers read **$0** in cost analytics; budget, quota & routing keep estimating. → [API Reference](docs/reference/API_REFERENCE.md) -- **⚖️ Quota-Share routing** — split load across accounts by _available quota_: DRR scheduling, per-connection concurrency, multi-window buckets, session stickiness. → [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md) +- **⚖️ Quota-Share routing** — split a shared account's quota fairly across pooled keys, work-conserving so idle slices are lent out. → [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md) - **🤖 One-command CLI/agent setup** — `setup-*` configures 12+ coding tools; `omniroute launch` / `launch-codex` are zero-config. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md) - **🛰️ Remote mode** — drive a remote OmniRoute with scoped tokens (`connect` / `contexts` / `tokens`) + an `antigravity` OAuth helper for VPS installs. → [Remote Mode](docs/guides/REMOTE-MODE.md) - **🧭 Smarter auto-routing** — `auto/:` combos, **Fusion** (model panel + judge), task-aware routing, per-request model / mode / USD-budget overrides. → [Auto-Combo](docs/routing/AUTO-COMBO.md) @@ -363,26 +364,26 @@ All **18** strategies — mix & match per combo step: - - - - - - - - - + + + + + + + + + - - - - - - - - - + + + + + + + + +
OpenAI
OpenAI
                           		Anthropic
Anthropic
                           		Gemini
Gemini
                           		xAI Grok
xAI Grok
                           		DeepSeek
DeepSeek
                           		Mistral
Mistral
                           		Qwen
Qwen
                           		Meta Llama
Meta Llama
                           		Groq
Groq
                           		OpenAI
OpenAI
                           		Anthropic
Anthropic
                           		Gemini
Gemini
                           		xAI Grok
xAI Grok
                           		DeepSeek
DeepSeek
                           		Mistral
Mistral
                           		Qwen
Qwen
                           		Meta Llama
Meta Llama
                           		Groq
Groq
                           
NVIDIA
NVIDIA
                           		MiniMax
MiniMax
                           		Cohere
Cohere
                           		Perplexity
Perplexity
                           		Hugging Face
HuggingFace
                           		Together
Together
                           		Fireworks
Fireworks
                           		Cloudflare
Cloudflare
                           		Baidu
Baidu
                           		NVIDIA
NVIDIA
                           		MiniMax
MiniMax
                           		Cohere
Cohere
                           		Perplexity
Perplexity
                           		Hugging Face
HuggingFace
                           		Together
Together
                           		Fireworks
Fireworks
                           		Cloudflare
Cloudflare
                           		Baidu
Baidu
                           
@@ -394,13 +395,13 @@ All **18** strategies — mix & match per combo step: - - - - - - - + + + + + + +
AgentRouter
AgentRouter
GPT-5, Claude, Gemini
$100 free credits
                                     		Qoder AI
Qoder AI
Kimi-K2, DeepSeek-R1
Unlimited FREE
                                     		Pollinations
Pollinations
GPT-5, Claude, Llama 4
No key needed
                                     		LongCat
LongCat
LongCat-2.0
10M tokens one-time (KYC) 🔑
                                     		Cloudflare AI
Cloudflare AI
50+ models
10K neurons/day
                                     		NVIDIA NIM
NVIDIA NIM
129 models
~40 RPM free
                                     		Cerebras
Cerebras
Qwen3 235B
1M tokens/day
                                     		AgentRouter
AgentRouter
GPT-5, Claude, Gemini
$100 free credits
                                     		Qoder AI
Qoder AI
Kimi-K2, DeepSeek-R1
Unlimited FREE
                                     		Pollinations
Pollinations
GPT-5, Claude, Llama 4
No key needed
                                     		LongCat
LongCat
LongCat-2.0
10M tokens one-time (KYC) 🔑
                                     		Cloudflare AI
Cloudflare AI
50+ models
10K neurons/day
                                     		NVIDIA NIM
NVIDIA NIM
129 models
~40 RPM free
                                     		Cerebras
Cerebras
Qwen3 235B
1M tokens/day
                                     
@@ -450,7 +451,7 @@ All **18** strategies — mix & match per combo step: -> OmniRoute isn't just a server — it's a **full command-line cockpit** with **80+ commands**, plus open agent protocols so an AI agent can drive OmniRoute **by itself**. +> Beyond the server, OmniRoute is a **full command-line cockpit** with **80+ commands**, plus open agent protocols so an AI agent can drive it **on its own**. ### ⌨️ A real CLI (not just `start`) @@ -485,14 +486,14 @@ Tokens are scoped `read` / `write` / `admin`; process-spawning routes stay loopb ### 🤝 Connect an agent — and it controls OmniRoute itself -Expose OmniRoute over **MCP** or **A2A** and any capable agent gets the keys to the whole gateway — routing, providers, combos, cache, compression, memory — autonomously. +Expose OmniRoute over **MCP** or **A2A** and any capable agent gets the keys to the whole gateway — routing, providers, combos, cache, compression, memory — autonomously. HTTP endpoints below are served under `http://localhost:20128`. -| Protocol | Endpoint | Use it for | -| ------------------ | ----------------------------------------------- | ------------------------------------------------------- | -| 🧰 **MCP (stdio)** | `omniroute --mcp` | Plug into Claude Desktop, Cursor, any MCP client | -| 🌊 **MCP (HTTP)** | `http://localhost:20128/api/mcp/stream` | Remote MCP — **104 tools**, 31 scopes, full audit trail | -| 📡 **MCP (SSE)** | `http://localhost:20128/api/mcp/sse` | Streaming MCP transport | -| 🤝 **A2A** | `http://localhost:20128/.well-known/agent.json` | Agent-to-agent, **JSON-RPC 2.0** + SSE, 6 skills | +| Protocol | Endpoint | Use it for | +| ------------------ | ------------------------- | ------------------------------------------------------- | +| 🧰 **MCP (stdio)** | `omniroute --mcp` | Plug into Claude Desktop, Cursor, any MCP client | +| 🌊 **MCP (HTTP)** | `/api/mcp/stream` | Remote MCP — **104 tools**, 31 scopes, full audit trail | +| 📡 **MCP (SSE)** | `/api/mcp/sse` | Streaming MCP transport | +| 🤝 **A2A** | `/.well-known/agent.json` | Agent-to-agent, **JSON-RPC 2.0** + SSE, 6 skills | ```bash # Give Claude Code the full OmniRoute toolset over MCP: @@ -515,20 +516,20 @@ claude mcp add-server omniroute --type http --url http://localhost:20128/api/mcp Engines run in pipeline order; each is independently toggleable and configurable per combo: -| # | Engine | What it does | -| --- | ------------------------- | ----------------------------------------------------------------------------------------------------------------------- | -| 1 | **Session-Dedup** | Drops content repeated across turns (content-addressed, cross-turn) | -| 2 | **CCR** | Archives large blocks behind retrieve markers, fetched on demand | -| 3 | **Lite** | Whitespace + image-URL trimming (latency-light baseline) | -| 4 | **RTK** | Smart tool-result filtering, dedup & truncation (command-aware) | -| 5 | **Responses Tool Output** | Lossless-first JSON + bounded diagnostic compression for shell/patch/search/build outputs (Responses API) | -| 6 | **Headroom** | Lossless tabular compaction of homogeneous JSON arrays, flat or nested (~30%), via a vendored **GCF** codec (spec v3.2) | -| 7 | **Relevance** | Extractive sentence scoring against the last user query | -| 8 | **Caveman** | Rule-based prose compression (~65–75% on output) | -| 9 | **Aggressive** | Summarization + progressive aging of old turns | -| 10 | **LLMLingua-2** | ML semantic pruning via MobileBERT ONNX — code-safe, async | -| 11 | **Ultra** | Heuristic token pruning with an optional small-model (SLM) tier | -| 12 | **OmniGlyph** | Experimental context-as-image encoding routed to Claude Fable 5 (most aggressive; opt-in) | +| # | Engine | What it does | +| --- | ------------------------- | --------------------------------------------------------------------------------------------------------- | +| 1 | **Session-Dedup** | Drops content repeated across turns (content-addressed, cross-turn) | +| 2 | **CCR** | Archives large blocks behind retrieve markers, fetched on demand | +| 3 | **Lite** | Whitespace + image-URL trimming (latency-light baseline) | +| 4 | **RTK** | Smart tool-result filtering, dedup & truncation (command-aware) | +| 5 | **Responses Tool Output** | Lossless-first JSON + bounded diagnostic compression for shell/patch/search/build outputs (Responses API) | +| 6 | **Headroom** | Lossless tabular compaction of JSON arrays (~30%) via a vendored **GCF** codec | +| 7 | **Relevance** | Extractive sentence scoring against the last user query | +| 8 | **Caveman** | Rule-based prose compression (~65–75% on output) | +| 9 | **Aggressive** | Summarization + progressive aging of old turns | +| 10 | **LLMLingua-2** | ML semantic pruning via MobileBERT ONNX — code-safe, async | +| 11 | **Ultra** | Heuristic token pruning with an optional small-model (SLM) tier | +| 12 | **OmniGlyph** | Experimental context-as-image encoding routed to Claude Fable 5 (most aggressive; opt-in) | Code blocks, URLs and structured data are **always preserved** byte-perfect. **One-click presets** combine the engines: @@ -575,7 +576,7 @@ Code blocks, URLs, JSON and structured data are **always protected** by the pres ### 🎚️ Beyond the engines — output styles, the adaptive dial & per-request control -The 10 engines above shrink what goes **in**. Three more layers shape **how**, **when**, and what comes **out**: +The 12 engines above shrink what goes **in**. Three more layers shape **how**, **when**, and what comes **out**: - **🪄 Output Styles** _(output-axis steering)_ — inject deterministic, cache-safe response-shaping instructions; combinable, each at `lite` / `full` / `ultra` intensity. Adding a style is a one-line registry entry: - **Terse prose** — drop filler / articles / hedging; keep technical substance exact. @@ -728,15 +729,15 @@ same process on one port, so there is no separate CLI-only package today.
- - - @@ -757,12 +758,26 @@ same process on one port, so there is no separate CLI-only package today. -| Page | Screenshot | Page | Screenshot | -| ---------- | ------------------------------------------------- | ---------- | --------------------------------------------- | -| Providers | ![Providers](docs/screenshots/01-providers.png) | Combos | ![Combos](docs/screenshots/02-combos.png) | -| Analytics | ![Analytics](docs/screenshots/03-analytics.png) | Health | ![Health](docs/screenshots/04-health.png) | -| Translator | ![Translator](docs/screenshots/05-translator.png) | Settings | ![Settings](docs/screenshots/06-settings.png) | -| CLI Tools | ![CLI Tools](docs/screenshots/07-cli-tools.png) | Usage Logs | ![Usage](docs/screenshots/08-usage.png) | +
+
+ Guia em Português
🇧🇷 Português
Guia completo 		+ English Guide
🇺🇸 English
Complete walkthrough 		+ Руководство
🇷🇺 Русский
Полное руководство
+ + + + + + + + + + + + + + + + +
Providers
Providers		Combos
Combos
Analytics
Analytics		Health
Health
Translator
Translator		Settings
Settings
CLI Tools
CLI Tools		Usage Logs
Usage Logs
+

@@ -866,15 +881,15 @@ same process on one port, so there is no separate CLI-only package today. ### 📋 Project & Quality -| Document | Description                                                                                                                                                                              | -| -------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| [Contributing](CONTRIBUTING.md) | Development setup and guidelines | -| [Branching & Release Model](docs/ops/BRANCHING_MODEL.md) | Where PRs target (`release/*`), what `main` and tags mean | -| [Changelog](CHANGELOG.md) | Full per-version release history | -| [Security Policy](SECURITY.md) | Vulnerability reporting and security practices | -| [i18n Guide](docs/guides/I18N.md) | 40+ language support, translation workflow, RTL | -| [Release Checklist](docs/ops/RELEASE_CHECKLIST.md) | Pre-release validation steps | -| [Coverage Plan](docs/ops/COVERAGE_PLAN.md) | Test coverage strategy and 25,000+ test suite | +| Document | Description                                                                                                                                                                              | +| -------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| [Contributing](CONTRIBUTING.md) | Development setup and guidelines | +| [Branching & Release Model](docs/ops/BRANCHING_MODEL.md) | Where PRs target (`release/*`), what `main` and tags mean | +| [Changelog](CHANGELOG.md) | Full per-version release history | +| [Security Policy](SECURITY.md) | Vulnerability reporting and security practices | +| [i18n Guide](docs/guides/I18N.md) | 40+ language support, translation workflow, RTL | +| [Release Checklist](docs/ops/RELEASE_CHECKLIST.md) | Pre-release validation steps | +| [Coverage Plan](docs/ops/COVERAGE_PLAN.md) | Test coverage strategy and 25,000+ test suite |
@@ -891,7 +906,7 @@ same process on one port, so there is no separate CLI-only package today. oyi77
oyi77
- 🥇 207 commits • +114K lines
+ 🥇 213 commits • +114K lines
Analytics engine, SQL aggregations,
proxy marketplace, test coverage @@ -923,11 +938,19 @@ same process on one port, so there is no separate CLI-only package today. Jan Leon
Jan Leon
- 🏅 52 commits • +22K lines
+ 🏅 58 commits • +22K lines
Reasoning-effort routing, proxy controls,
quota visibility, Live Zone compression + + + backryun
+ backryun +
+ 🏅 53 commits • +70K lines
+ Provider catalog curation — Perplexity, Kimi,
Cerebras, Copilot, LMArena refreshes + Chirag Singhal
@@ -936,14 +959,6 @@ same process on one port, so there is no separate CLI-only package today. 🏅 46 commits • +4.8K lines
Error sanitization, MITM prefill fix,
fusion judge, breaker/429 correctness - - - backryun
- backryun -
- 🏅 43 commits • +70K lines
- Provider catalog curation — Perplexity, Kimi,
Cerebras, Copilot, LMArena refreshes - kfiramar
@@ -965,7 +980,7 @@ same process on one port, so there is no separate CLI-only package today. Hernan J. Ardila
Hernan J. Ardila
- 🏅 22 commits • +174K lines
+ 🏅 25 commits • +174K lines
Zero-latency combos, vision-bridge auto-routing,
catalog context-length, resilience 429 hints @@ -981,7 +996,7 @@ same process on one port, so there is no separate CLI-only package today.
-## 👥 350+ Contributors +## 👥 500+ Contributors
diff --git a/docs/diagrams/cli-terminal.svg b/docs/diagrams/cli-terminal.svg index 832ac12fd8..bb015e3a12 100644 --- a/docs/diagrams/cli-terminal.svg +++ b/docs/diagrams/cli-terminal.svg @@ -1,4 +1,4 @@ - + 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. @@ -32,7 +32,7 @@ -OmniRoute Health  Status: healthy   Uptime: 4d 12h 33m  Requests (24h): 18,412   p95: 412ms  Breakers: ● 24 closed  ◒ 1 half-open  ○ 0 open  Providers: 268 registered   90+ free tiers… live: /dashboard · omniroute status +OmniRoute Health  Status: healthy   Uptime: 4d 12h 33m  Requests (24h): 18,412   p95: 412ms  Breakers: ● 24 closed  ◒ 1 half-open  ○ 0 open  Providers: 278 registered   90+ free tiers… live: /dashboard · omniroute status diff --git a/docs/diagrams/compression-pipeline.svg b/docs/diagrams/compression-pipeline.svg index 72a12994e4..3b3c311972 100644 --- a/docs/diagrams/compression-pipeline.svg +++ b/docs/diagrams/compression-pipeline.svg @@ -1,4 +1,4 @@ - + @@ -30,7 +30,7 @@ - OMNIROUTE COMPRESSION — 11 ENGINES + OMNIROUTE COMPRESSION — 12 ENGINES @@ -77,114 +77,124 @@ - + - - - + + + - 1 - Session - Dedup + 1 + Session + Dedup - - + + - 2 - CCR + 2 + CCR - - - - - + + + + + - 3 - RTK + 3 + Lite - - - - - + + + + + - 4 - Headroom + 4 + RTK - - - - - + + + + + - 5 - Relevance + 5 + Responses + Tool Out - - - - - + + + + + - 6 - Caveman + 6 + Headroom - - - - - + + + + + - 7 - LLM - Lingua-2 + 7 + Relevance - - - - - + + + + + - 8 - Omniglyph + 8 + Caveman - - - - + + + + - 9 - Lite + 9 + Aggressive - - - - + + + + - 10 - Aggressive + 10 + LLM + Lingua-2 - - - + + + - 11 - Ultra + 11 + Ultra + + + + + + + + 12 + OmniGlyph - - default stack: RTK → Caveman + + default stack: RTK → Caveman { } code · URLs · JSON — always preserved byte-perfect diff --git a/docs/diagrams/free-tier-budget.svg b/docs/diagrams/free-tier-budget.svg index fece1c76f6..6ae541be74 100644 --- a/docs/diagrams/free-tier-budget.svg +++ b/docs/diagrams/free-tier-budget.svg @@ -1,4 +1,4 @@ - + @@ -60,10 +60,10 @@ - ~1.4B + ~1.53B FREE TOKENS / MONTH · STEADY - up to ~2.0B in your first month — signup credits - documented free tiers · 39 provider pools · 460+ models · one endpoint + up to ~2.15B in your first month — signup credits + documented free tiers · 43 provider pools · 460+ models · one endpoint @@ -74,7 +74,7 @@ every rate limit · 24/7 we don't publish that - ~1.4B + ~1.53B each shared free pool counted once ✓ 15 providers ToS-flagged — we flag it · you decide diff --git a/docs/diagrams/promise-pillars.svg b/docs/diagrams/promise-pillars.svg index e687bfb652..7585eb08a0 100644 --- a/docs/diagrams/promise-pillars.svg +++ b/docs/diagrams/promise-pillars.svg @@ -1,4 +1,4 @@ - + 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. @@ -21,7 +21,7 @@ - One endpoint. 268 providers. Never stop building — OmniRoute picks the cheapest one that works. + One endpoint. 278 providers. Never stop building — OmniRoute picks the cheapest one that works. @@ -38,7 +38,7 @@ Never hit limits - Auto-fallback across 268 providers in + Auto-fallback across 278 providers in milliseconds. Quota out? The next provider takes over — zero downtime. diff --git a/docs/diagrams/readme-hero.svg b/docs/diagrams/readme-hero.svg index 71f0949ab8..d9760f725f 100644 --- a/docs/diagrams/readme-hero.svg +++ b/docs/diagrams/readme-hero.svg @@ -1,4 +1,4 @@ - + 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. @@ -28,7 +28,7 @@ Never stop coding. - Every AI tool → 268 providers — 90+ free — through one endpoint. + Every AI tool → 278 providers — 90+ free — through one endpoint. Claude Code · Codex · Cursor · Cline · Copilot · Antigravity  →  FREE Claude / GPT / Gemini · auto-fallback @@ -66,19 +66,19 @@ - 268 + 278 AI PROVIDERS 90+ FREE TIERS - ~1.4B + ~1.53B FREE TOKENS / MO 15–95% TOKEN SAVINGS - 18 + 19 ROUTING STRATEGIES $0