Verified project record

diegosouzapw/OmniRoute

A self-hosted AI gateway that aggregates 250+ providers into a single endpoint with auto-fallback routing and token compression. It is suited for developers and AI engineers who need to consolidate multiple API keys, manage rate limits, and reduce token usage across coding agents.

Project overview

Project type: MCP · Infrastructure
Use cases: Coding & Development
Deployment: Refer to project documentation
License: MIT

Best for

Developers and AI engineers who need to unify multiple provider API keys into a single endpoint for their coding agents and tools.
Teams looking to aggregate free tiers from multiple providers to manage costs and distribute quotas fairly.

Key capabilities

Routes requests to over 250 AI providers using 18 different strategies, including priority, cost-optimized, and round-robin, to optimize for cost, latency, or headroom.
Automatically falls back across providers in milliseconds when quota limits are hit or providers fail.
Compresses tool outputs and context payloads by 15-95% to save tokens using stacked RTK and Caveman engines.
Includes a built-in MCP server with 94 tools, 3 transports, and 30 scopes.
Supports A2A (Agent-to-Agent) protocol with 6 skills using JSON-RPC 2.0.
Distributes a provider's time-based quota fairly across multiple keys in a pool, with options for weights, dimensions, policies, and caps.
Uses JA3/JA4 TLS fingerprint spoofing via wreq-js to access AI services from anywhere and bypass blocks.
Translates OpenAI, Claude, Gemini, and Responses API formats so any tool can be pointed at a single endpoint.

Limitations and risks

Reliance on free tiers introduces susceptibility to provider rate limits and quota exhaustion, requiring the configuration of fallback mechanisms.
The project depends entirely on the availability and terms of service of third-party AI providers, which can change without notice.

Getting started

Run a global npm installation with a single command. After executing the application, the dashboard automatically starts on localhost at http://localhost:20128.

Evidence and sources

GitHub project description: Never stop coding. Free AI gateway: one endpoint, 231+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline & Copilot to FREE Claude/GPT/Gemini.
README: Auto-fallback across 250 providers in milliseconds. Quota out? Next provider takes over — zero downtime.
README: 🖥️ Desktop (Electron) | npm run electron:build | Native window + system tray — Windows / macOS / Linux
README: 🌍 AI blocked in your country | 3-level proxy + TLS fingerprint stealth — use AI from anywhere
README: OpenAI ↔ Claude ↔ Gemini ↔ Responses API translation. Point any tool at <code>/v1</code> and it just works.

Reviewed at: 2026-07-17T12:51:28Z