SkillsMCP servers

cheaper-inference/OmniRoute

Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ 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 900+ contributors

Stars
89,425
+7 days
—
Forks
13,819
Language
TypeScript
License
MIT
Last push
22 Nov 2026

Summary

Summary written by AI from the README; it may be imprecise.

This open-source AI gateway provides a single local API endpoint to route requests across hundreds of model providers, including Claude, GPT, and Gemini. It features automatic multi-tier fallback across subscriptions, API keys, and free tiers, along with token compression and quota tracking. Developers can connect their existing credentials and integrate the gateway with tools like Claude Code, Cursor, and other coding CLIs.

Use it when

  • Route requests from Claude Code or Cursor through a single endpoint across multiple model providers
  • Fall back automatically between subscriptions, API keys, and free tiers when hitting rate limits
  • Reduce token consumption and monitor quotas across multiple AI accounts from a local dashboard

Install

mcp
claude mcp add --transport http omniroute http://localhost:20128/api/mcp/stream \
npm
npm install -g omniroute
npm
npm install -g --allow-scripts=omniroute,keytar,onnxruntime-node,@parcel/watcher,@swc/core,protobufjs,esbuild omniroute

Commands quoted from the repo's README. Read the README before running them.

Stars over 90 days

Collecting: 2 of 90 days so far. The chart appears after 7 days.

Type to search the reference, templates and lessons.