Delivery infrastructure for agents. Arch is a models-native proxy and data plane for agents that handles plumbing work in AI - like agent routing and orchestration, guardrails, zero-code logs and traces, and unified access to LLMs (OpenAI, Anthropic, Ollama, etc.). Build agents faster and deliver them reliably to prod.

• UpdatedDec 17, 2025
• Rust

High-performance lightweight proxy and load balancer for LLM infrastructure. Intelligent routing, automatic failover and unified model discovery across local and remote inference backends.

• UpdatedDec 15, 2025
• Go

Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligent model routing using your logic or ours, and even use your Claude subscription as an API

• UpdatedDec 9, 2025
• Python

Open Source LLM proxy that transparently captures and logs all interactions with LLM API

• UpdatedJun 15, 2025
• HTML

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

• UpdatedNov 23, 2025
• Python

This is a robust and configurable LLM proxy server built with Node.js, Express, and PostgreSQL. It acts as an intermediary between your applications and various Large Language Model (LLM) providers

• UpdatedNov 13, 2025
• TypeScript

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.

• UpdatedAug 28, 2025
• Python

Allows any BYOK AI editor or extension, such as Cursor or Continue, to connect to any openai-compatible LLM by aliasing it as a different model

• UpdatedJul 4, 2025
• TypeScript

Local LLM proxy, DevOps friendly

• UpdatedDec 14, 2025
• Go

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

• UpdatedDec 15, 2025
• Go

Proxy for many LLM-provider with OpenAI like request

• UpdatedAug 13, 2025
• Go

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

• UpdatedDec 17, 2025
• Python

A self-hosted, open-source (Apache 2.0) proxy for LLM's with prometheus metrics

• UpdatedJul 30, 2025
• Go

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

• UpdatedDec 4, 2025
• Python

[WIP] Sorai is a lightweight, high-performance, and open-source LLM proxy gateway.

• UpdatedJun 24, 2025
• Rust

Nodejs OpenRouter proxy inference that provides all nessary endpoints for your LLM application.

• UpdatedOct 19, 2025
• TypeScript

Store your knowledge (privately), lead LLMs with it and cure hallucinations.

• UpdatedJun 17, 2025
• Shell

A proxy for claude code to use liteLLM

• UpdatedOct 6, 2025
• TypeScript

AI Proxy Server - A high-performance, secure unified API gateway for multiple LLM providers (OpenAI, Gemini, Groq, OpenRouter, Cloudflare) with intelligent routing, rate limiting, and streaming support. Features modular architecture, enhanced security, and optimized performance.

• UpdatedAug 26, 2025
• Go

OpenAI-compatible AI proxy: Anthropic Claude, Google Gemini, GPT-5, Cloudflare AI. Free hosting, automatic failover, token rotation. Deploy in 1 minute.

• UpdatedNov 22, 2025
• TypeScript