Categories
Developer Tools Automation LLM Machine Learning API Gateway Artificial Intelligence ProxyStars
Forks
Watchers
Developer links
OmniRoute
OmniRoute is an AI gateway, aggregating 338 LLM providers including OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Kimi, MiniMax, and GLM into a single OpenAI-compatible endpoint at localhost:20128. The gateway catalogs over 1,200 models across 90 free-tier providers and 40 free-forever providers, automatically rotating through tier-1, tier-2, and tier-3 fallback chains when any provider exhausts its quota or returns errors. RTK plus Caveman stacked token compression reduces eligible context by 15 to 95 percent before forwarding requests, cutting API costs dramatically without degrading output quality. OmniRoute exposes its full routing engine through a built-in MCP server with 104 tools across 31 scopes over stdio, HTTP, and SSE transports, plus an A2A protocol server with six autonomous agent skills and JSON-RPC 2.0 streaming. The gateway integrates directly with Claude Code, Cursor, GitHub Copilot, Codex CLI, OpenCode, and Cline through standard base-URL configuration. Seventeen routing strategies include latency-optimized, cost-minimized, and auto-scoring modes that evaluate candidates on success rate, context fit, model fitness, quota state, and circuit-breaker health. The Next.js dashboard provides real-time provider status, usage analytics, combo chain configuration, and model catalog browsing via a responsive PWA. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Benefits
- 338 Providers in One Endpoint
- Aggregates OpenAI, Claude, Gemini, DeepSeek, Kimi, MiniMax, and 330 more providers into a single OpenAI-compatible API with automatic protocol translation between formats.
- Quota-Aware Automatic Failover
- Seventeen routing strategies with tier-1, tier-2, and tier-3 fallback chains switch providers in milliseconds when quotas exhaust or errors occur, ensuring zero downtime.
- Token Compression Saves Costs
- RTK plus Caveman stacked compression reduces eligible context tokens by 15 to 95 percent before forwarding, cutting API spend without degrading response quality.
- MCP and A2A Protocol Server
- Built-in MCP server exposes 104 tools across 31 scopes via stdio, HTTP, and SSE transports alongside A2A protocol server with six autonomous agent skills.
Features
- OpenAI-Compatible Gateway API
- Serves chat completions, embeddings, image generation, audio, and OCR endpoints on port 20128 with automatic Claude and Gemini protocol translation.
- Auto-Scoring Model Router
- Score-driven auto-router evaluates candidates on latency, cost, success rate, context fit, model fitness, and circuit-breaker state for zero-config operation.
- Next.js Dashboard and PWA
- Real-time provider status monitoring, usage analytics, combo chain builder, and model catalog browser accessible as Progressive Web App from any device.
- IDE Tool Integration
- Works directly with Claude Code, Cursor, GitHub Copilot, Codex CLI, OpenCode, and Cline via standard base-URL endpoint configuration.
- Webhook Event Pipeline
- Push events for usage metrics, quota warnings, errors, and routing decisions to external endpoints for integration with monitoring and alerting systems.