OmniRoute

View on GitHub

Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors

★ 69K9,767 forksTypeScriptMITdiegosouzapw

OmniRoute is an MIT-licensed AI gateway that unifies 350+ LLM providers behind one OpenAI-compatible endpoint with quota-aware auto-fallback, token compression, and MCP/A2A support. It plugs into coding agents like Claude Code, Cursor, and Cline and self-hosts as CLI, Docker, desktop, or PWA.

Use Cases

Route LLM requests across 350+ providers through one OpenAI-compatible endpointConnect coding agents (Claude Code, Cursor, Cline, Codex, Copilot) to multiple model backendsAutomatically fail over when a provider hits quota or rate limitsCut token costs via RTK+Caveman prompt compressionAggregate free tiers of many providers into one poolExpose MCP and A2A interfaces for tools and agentsSelf-host a desktop or PWA AI gateway locallyTrack provider quota telemetry and usage on a dashboard

Built With

Language: TypeScript
Frameworks: Node.js · TypeScript · Electron · Next.js · Docker · pnpm

OmniRoute

Use Cases

Built With

Tags