AI gateway written in Go. Lightweight unified OpenAI-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI & Ollama. LiteLLM alternative with observability, guardrails, streaming, costs and usage tracking.

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

Go LLM gateway — one interface for Claude Code, Codex, Gemini CLI, Anthropic, OpenAI, Qwen, and vLLM.

A local OpenAI-compatible proxy for Gemini CLI and Kiro in a native Flutter app

Open-source AI gateway — pool your provider keys behind one OpenAI-compatible endpoint with load balancing, failover, circuit breaking, rate limits, and cost analytics. Self-host in minutes. To follow on X: https://x.com/alayranexus

Bridge your local AI tools to the web. Exposes Claude Code CLI, Gemini CLI, and Antigravity sessions as a standard API, allowing you to use these accounts with any OpenAI/Claude/Gemini-compatible API client.

A proxy that allows you to add Straico as a Provider in Opencode

Ultra-lightweight (<5MB RAM) proxy for Claude Code. Flexible routing for Opus, Sonnet, and Haiku across different API providers with on-the-fly request format conversion.

🤖 Streamline AI access with a unified API proxy, connecting multiple LLM providers for seamless integration and enhanced functionality.

OpenAI-Compatible API Gateway — 48 models, unlimited tokens, fixed price

Pluggable OpenAI-compatible proxy server for custom LLM providers.

Dockerized LiteLLM gateway for Cursor IDE. Exposes /v1 with chat, coder, and vision; routes OpenRouter models with latency-based routing, Redis caching, Postgres, and Cloudflare tunnel ingress.

Production-grade AI Gateway with reversible Content Shield (DLP) — mask, redact, block PII/PHI/secrets in LLM traffic.

Transparent proxy that auto-injects DeepSeek thinking / reasoning_effort into API requests — no client-side changes needed.