Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.

Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligent model routing using your logic or ours

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

SmarterRouter: An intelligent LLM gateway and VRAM-aware router for Ollama, llama.cpp, and OpenAI. Features semantic caching, model profiling, and automatic failover for local AI labs.

A personal LLM gateway with fault-tolerant capabilities for calls to LLM models from any provider with OpenAI-compatible APIs. Advanced features like retry, model sequencing, and body parameter injection are also available. Especially useful to work with AI coders like Cline and RooCode and providers like OpenRouter.

Connect any LLM-powered client app, such as a coding agent, to any supported inference backend/model.

Use any LLM with Claude Code — proxy that translates Anthropic API to OpenAI, Gemini, DeepSeek, Ollama, and more. Full tool calling, streaming, ReAct XML fallback, hot-reload config.

Small reliability layer for HTTP APIs and LLM calls. Idempotent HTTP/LLM proxy with retries, cache, circuit breaker and predictable AI costs.

Local desktop relay for Trae and Cursor, routing OpenAI and Anthropic models through switchable proxy config groups.

Route, manage, and analyze your LLM requests across multiple providers with a unified API interface

Multi-provider LLM gateway with automatic fallback and cost tracking. Single API across DeepSeek, Gemini, OpenAI, and Anthropic.

Python proxy for Gemini API. Overcomes the tight free-tier rate limits of Gemini Pro by key pooling and provides full OpenAI compatibility for OpenWebUI.

Use your Cursor subscription to power Claude Code — smart proxy with lazy tool loading, auto-continuation & model fallback

AI development environment with 90% cost savings. Routes between 8 LLM providers while defaulting to FREE local models. Production-ready with automated testing.

Astrai inference router skill for OpenClaw — 40-60% savings on agent LLM costs with intelligent routing and privacy controls

Turn any LLM API into an OpenAI-compatible endpoint in minutes.

Ready to go local AI gateway: LiteLLM proxy + Langfuse observability + Caddy reverse proxy. Per-tool tracing, session evaluation, and zero-config trace enrichment.

Simultaneous multi-provider proxy for Claude Code - Do the splits with your Claude requests.

LLM cost-optimization proxy which routes requests across 11 models from 4 providers using complexity classification, two-level semantic caching, and automatic provider failover

Open-source AI Agent Control Plane. Transparent HTTP proxy for security, cost optimization, and reliability between AI agents and LLM APIs.