# diegosouzapw/OmniRoute

Never stop coding. Free MIT AI gateway: one endpoint, 350 providers (90+ 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 450+ contributors

Repository: https://github.com/diegosouzapw/OmniRoute
Canonical: https://ross.abutalabs.com/products/omniroute
Homepage: https://omniroute.online
Language: TypeScript
License: MIT
License Family: permissive
Topics: a2a, ai-agents, ai-gateway, anthropic, claude, claude-code, cline, codex, copilot, cursor, deepseek, free-ai, gemini, llm-gateway, mcp, openai, openai-proxy, qwen, token-saver, kimi
Last push: 2026-08-27T00:34:53+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 14
- inputs: {"age_days": 201, "days_push": 7, "days_rel": 7, "gap_med": 0.0, "n_releases_24m": 279}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 56223, forks 7731 (observed 2026-08-28T04:12:18.434628+00:00)

## What it is
OmniRoute is a free, MIT-licensed AI gateway that exposes a single OpenAI-compatible endpoint routing to 350+ LLM providers (90+ with free tiers) and 1200+ models, with quota-aware auto-fallback and RTK+Caveman token compression. It ships with a web dashboard, Desktop/PWA app, MCP/A2A support, and works with coding agents like Claude Code, Codex, Cursor, Cline, and Copilot.

## Use cases
- route claude code to free llm providers
- avoid hitting api rate limits with automatic provider fallback
- save tokens when using ai coding agents
- use one endpoint for openai anthropic and gemini models
- access free llm tiers without a credit card
- self-host an openai-compatible proxy for multiple providers
- connect cursor or cline to gemini and deepseek models

## When to choose
- you use AI coding agents and want quota-aware failover across many providers
- you want to stack free LLM tiers behind one OpenAI-compatible endpoint
- you need API translation between OpenAI, Claude, and Gemini formats
- you want token compression to cut costs on tool-heavy agent sessions

## When to avoid
- you need a single dedicated provider with guaranteed SLAs and enterprise support
- you require strict data residency or cannot route prompts through third-party free tiers
- you only use one local model and don't need routing or fallback

## Facets
- artifact type: service
- maturity: active
- function: api-gateway, llm-inference, proxy, rate-limiting, middleware, mcp, chat-interface, developer-tools
- domain: large-language-models, developer-tools, self-hosted, apis, backend
- platform: cross-platform, self-hosted, cli
- tags: llm-gateway, ai-gateway, openai-proxy, auto-fallback, token-compression, free-tier, claude-code, cursor, openai-compatible, multi-provider, a2a, pwa, ai-agents, nodejs, docker, web-server

## Member repositories
- diegosouzapw/OmniRoute (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:18.434628+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:18:48.341822+00:00, confidence not recorded.
  - readme: https://github.com/diegosouzapw/OmniRoute (fetched 2026-08-28T04:12:18.434628+00:00, sha 56cd7146bbe9)
  - homepage: https://omniroute.online (fetched 2026-08-28T18:04:10.435456+00:00, sha a9f15c13e687)
  - site_page: https://link.omniroute.online/gh-docs (fetched 2026-08-28T18:04:10.444197+00:00, sha ce259ab6ae37)
  - site_page: https://link.omniroute.online/gh-releases (fetched 2026-08-28T18:04:10.446143+00:00, sha 74d851c94d2e)
- Data as of 2026-08-30T08:39:29.467469+00:00.