OmniRoute
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
- stars
- 67,206
- 30-day movement
- +2,583861/day
- Related entries
- 106
- Connections
- 4
OmniRoute is a self-hostable AI gateway that exposes a single endpoint routing to 352 providers and 1200+ models, with quota-aware auto-fallback and token compression (RTK+Caveman). It integrates with coding agents like Claude Code, Codex, Cursor, Cline, and Copilot, and supports MCP/A2A protocols.
Reach for it when you want one gateway endpoint to route coding agents across many LLM providers with automatic failover and token savings.
Use it to
- Route coding agents through one unified endpoint
- Fall back automatically when provider quotas run out
- Compress prompts to reduce token spend
- Expose models via MCP or A2A for agent tooling
- Self-host the gateway with Docker or Nix
For Developers running AI coding agents across multiple providers
- Role
- agent-app
- Language
- TypeScript
- Licence
- MIT
- Forks
- 9,459
- Open issues
- 268
- Last push
- 2026-09-17
- Latest release
- v1.0.0 · 2026-02-18
- Skills shipped
- 46