diff --git a/README.md b/README.md index a2447a82f6..3ab7eb1bee 100644 --- a/README.md +++ b/README.md @@ -160,7 +160,7 @@ πŸ”Œ Every tool works
24+ coding agents β€” Claude Code, Codex, Cursor, Cline, Copilot, Antigravity β€” through one config. 🧩 One endpoint
OpenAI ↔ Claude ↔ Gemini ↔ Responses API translation. Point any tool at /v1 and it just works. - πŸ›‘οΈ Production-grade
Circuit breakers, TLS stealth, MCP (95 tools), A2A, memory, guardrails, evals. 21,000+ tests. + πŸ›‘οΈ Production-grade
Circuit breakers, TLS stealth, MCP (94 tools), A2A, memory, guardrails, evals. 21,000+ tests. @@ -194,7 +194,7 @@ β–Ό β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚ OmniRoute β€” Smart Router β”‚ -β”‚ RTK + Caveman compression Β· 17 routing strategies β”‚ +β”‚ RTK + Caveman compression Β· 18 routing strategies β”‚ β”‚ Circuit breakers Β· TLS stealth Β· MCP Β· A2A Β· Guardrails β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” @@ -232,9 +232,9 @@ No combo to create. Set your model to `auto` (or a variant) and OmniRoute builds ## -### πŸ”€ Or build your own β€” 17 routing strategies +### πŸ”€ Or build your own β€” 18 routing strategies -All **17** strategies β€” mix & match per combo step: +All **18** strategies β€” mix & match per combo step: | # | Strategy | What it does | | --- | ------------------- | ---------------------------------------------------------------- | @@ -253,10 +253,11 @@ All **17** strategies β€” mix & match per combo step: | 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 β€” sticky to the last successful target | -| 16 | `auto` | 9-factor live scoring across every connection πŸ€– | +| 16 | `auto` | 12-factor live scoring across every connection πŸ€– | | 17 | `fusion` | Fan out to a panel of models + a judge synthesizes one answer 🧬 | +| 18 | `pipeline` | Chain steps β€” each target's output feeds the next one πŸ”— | -The Auto-Combo engine scores every candidate on **9 factors** (health, quota, cost, latency, success rate, freshness…) β€” see [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md). +The Auto-Combo engine scores every candidate on **12 factors** (health, quota, cost, latency, success rate, freshness…) β€” see [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md). ## @@ -315,9 +316,9 @@ Result: 4 layers of fallback = zero downtime | -------------------------------------- | ------------------------------------------------------------------- | ------------- | | 🌐 Providers | **248** | 20–100 | | πŸ†“ Free providers | **90+ (11 free forever)** | 1–5 | -| πŸ”€ Routing strategies | **17** (priority, weighted, cost-optimized, context-relay, fusion…) | 1–3 | +| πŸ”€ Routing strategies | **18** (priority, weighted, cost-optimized, context-relay, fusion…) | 1–3 | | πŸ—œοΈ Token compression | **RTK + Caveman stacked (15–95%)** | None / 20–40% | -| 🧰 Built-in MCP server | **95 tools, 3 transports, 30 scopes** | Rare | +| 🧰 Built-in MCP server | **94 tools, 3 transports, 30 scopes** | Rare | | 🀝 A2A agent protocol | **6 skills, JSON-RPC 2.0** | None | | 🧠 Memory (FTS5 + vector) | **Yes** | Rare | | πŸ›‘οΈ Guardrails (PII, injection, vision) | **Yes** | Rare | @@ -543,7 +544,7 @@ Expose OmniRoute over **MCP** or **A2A** and any capable agent gets the keys to | 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 β€” **95 tools**, 30 scopes, full audit trail | +| 🌊 **MCP (HTTP)** | `http://localhost:20128/api/mcp/stream` | Remote MCP β€” **94 tools**, 30 scopes, full audit trail | | πŸ“‘ **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 | @@ -882,7 +883,7 @@ Compression: aggressive (~50%) β†’ double your free quota Β· Cost: $0/mo **Routing:** 18 strategies Β· task-aware smart routing Β· thinking budget controls Β· wildcard routing Β· system prompt injection. **Compatibility:** OpenAI ↔ Claude ↔ Gemini ↔ Responses API Β· auto OAuth refresh (PKCE, 8 providers) Β· multi-account round-robin Β· Batch + Files API Β· live OpenAPI 3.0. -**Protocols:** MCP (95 tools, 3 transports, 30 scopes) Β· A2A (JSON-RPC 2.0, SSE, 6 skills) Β· ACP Β· cloud agents (Codex, Cursor, Devin, Jules). +**Protocols:** MCP (94 tools, 3 transports, 30 scopes) Β· A2A (JSON-RPC 2.0, SSE, 6 skills) Β· ACP Β· cloud agents (Codex, Cursor, Devin, Jules). **Plugins:** custom plugin marketplace (system-configured registry URL with SSRF-guarded fetch) Β· install / enable / disable Β· Notion + Obsidian knowledge-base integrations (WebDAV file server, vault search, note CRUD). **Embedded services:** one-click install & lifecycle management of local sidecar services (CLIProxy, NineRouter). **Quality & Ops:** built-in **Evals** (golden-set: exact/contains/regex/custom) Β· guardrails (PII, injection, vision) Β· health dashboard Β· p50/p95/p99 telemetry Β· webhooks Β· compliance audit. @@ -1027,7 +1028,7 @@ Compression: aggressive (~50%) β†’ double your free quota Β· Cost: $0/mo | [Compression Rules Format](docs/compression/COMPRESSION_RULES_FORMAT.md) | JSON rule-pack schemas for Caveman and RTK filters | | [Compression Language Packs](docs/compression/COMPRESSION_LANGUAGE_PACKS.md) | Language detection and Caveman rule-pack authoring | | [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md) | Circuit breakers, cooldowns, queue, anti-thundering herd, TLS spoofing | -| [Auto-Combo Engine](docs/routing/AUTO-COMBO.md) | 9-factor scoring, mode packs, self-healing | +| [Auto-Combo Engine](docs/routing/AUTO-COMBO.md) | 12-factor scoring, mode packs, self-healing | | [Proxy Guide](docs/ops/PROXY_GUIDE.md) | 3-level proxy system, 1proxy marketplace, registry CRUD | | [Free Tiers](docs/reference/FREE_TIERS.md) | 25+ free API providers consolidated directory | | [Features Gallery](docs/guides/FEATURES.md) | Visual dashboard tour with screenshots | diff --git a/changelog.d/maintenance/readme-strategy-tool-counts.md b/changelog.d/maintenance/readme-strategy-tool-counts.md new file mode 100644 index 0000000000..6e82bd00c1 --- /dev/null +++ b/changelog.d/maintenance/readme-strategy-tool-counts.md @@ -0,0 +1 @@ +- **docs(readme):** fix stale counts β€” 18 routing strategies (adds the missing `pipeline` row), 94 MCP tools, 12-factor Auto-Combo scoring.