diegosouzapw/OmniRoute

Health v2 · maintenance only

Adoption not part of the score

56223 stars · 7731 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

service · maturity active

api-gateway llm-inference proxy rate-limiting middleware mcp chat-interface developer-tools large-language-models developer-tools self-hosted apis backend cross-platform self-hosted cli 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

For agents

markdown · JSON · MCP: product_card(name="diegosouzapw/OmniRoute")