Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 4 of 41

GoRightLLM★ 142

A torch-free, lightweight LLM routing middleware. Lossless compression via fp32 ONNX embeddings + pure-numpy scorers (100% routing parity with the original), four routing modes (base / pro / ultra / agent), fully local inference with no data leaving your premises. Drop-in OpenAI-compatible proxy.

zen-proxy★ 141

Use OpenCode Zen's free models in any coding agent. OpenAI + Anthropic compatible, so Claude Code works too. No account, no API key.

OmniCopilot★ 140

1200+ AI models in your GitHub Copilot Chat — free & forever free. VS Code extension powered by OmniRoute: 340+ providers (90+ free) — Kimi, Claude, GPT, Gemini, GLM, DeepSeek, Qwen — with agent mode, tool calling, vision and quota-aware auto-fallback. MIT.

one-api-pro★ 139

One Api Pro 是一个基于开源项目one-api深度重构开发的企业级 AI API 网关。提供统一 OpenAI 兼容接口,聚合 30+ 主流模型平台,基于Vue 3 + Arco Design 开发了全新管理后台,支持可视化仪表盘、令牌精细管控、套餐订阅体系(按 Token / 按次计费 + 周期限频)、去中心化多活集群(节点独立 MySQL + Redis,通过应用层事件同步数据互信)、精确成本核算(Prompt / Completion / Cached 独立定价)、四级权限体系。面向需要统一管理多模型、关注成本监控与企业级高可用部署的开发者和团队。

pi-freeflow★ 139

🌊 33 verified free AI models (plus dynamically discovered Kilo models, up to 1M context) for Oh My Pi & Pi. Thin by design — model list, relay proxy, tool-call diagnostics — add your own relays to spread requests across more IPs.

gpt-5.5-api★ 139

GPT-5.5 API (gpt-5.5 / gpt-5.5-pro): model ids, per-million-token pricing, context limits, streaming, tool calling and OpenAI-compatible base URL examples.

llm-web-api★ 138

将ChatGPT网页转换成API接口。ChatGPT Web to API.

LoongPort★ 138

cc-switch 中转站的专用增强版(cc-switch for API relay providers),免去配置各种 密钥 endpoint 的烦恼。

sugt★ 138

SUGT - local AI gateway & skills console. Centralize LLM API keys, one OpenAI/Anthropic-compatible proxy for Claude Code, Codex & OpenCode. Homebrew & winget. Fully open source (Apache-2.0).

rllm★ 137

Use multiple LLM backends in a single crate, simple builder-based configuration, and built-in prompt chaining & templating.

dot-loom★ 136

Provider-pluggable orchestration runtime for multi-model AI inference. ( Sakana Fugu style )

cligate★ 135

Private AI assistant, AI agent, and unified model proxy for Claude Code, Codex CLI, Gemini CLI & OpenClaw. Skills, MCP, tools, channels, tasks,model routing, accounts, keys, logs, dashboard.

github-copilot-api-vscode★ 134

Unlock GitHub Copilot as a local API Gateway. Use Copilot with Cursor, LangChain, and any OpenAI-compatible tool.

lens★ 134

专为个人打造的轻量 LLM API 网关,统一管理多协议、多供应商,支持 Claude Code, Codex, OpenCode, OpenClaw, Grok Build, Hermes Agent、Pi 等 harness 调用,兼容 OpenAI(Chat、Responses、Embeddings、Images)、Anthropic、Gemini、Rerank 入口协议。

ccswitchmulti★ 133

CCswitch的全面升级,专门优化codex体验。支持官方订阅和第三方模型混用,自动路由,支持v2subagent使用第三方模型

n8n-openai-bridge★ 131

OpenAI-compatible API middleware for n8n workflows. Use your n8n agents and workflows as OpenAI models in any OpenAI-compatible client.

ai-relay★ 131

Open-source AI API Gateway | Serverless & VPS Self-hosted | Vercel, Cloudflare & Local | Multi-Provider, Smart Routing, Key Rotation & Failover

llm-router★ 130

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.

generate★ 129

A Python Package to Access World-Class Generative Models

TokenTamer★ 129

A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually needs to know.

droidproxy★ 129

macOS menu bar app that proxies Claude/Codex/Grok + More subscriptions for use with Factory Droid CLI. Actively maintained and updated with new model releases!

Gozar★ 129

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

llmix★ 128

Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, retries, circuit breakers, key rotation, singleflight, and Python/TypeScript/Rust parity.

claude-3★ 128

Free Proxy to access Claude-3 API. Anthropic key not required 🔐. It uses OpenAI format api to easily integrate on any Openai supported frontend.

OpenAI.Net★ 127

OpenAI library for .NET

go-openrouter★ 127

Unofficial API SDK for openrouter.ai in go

GPT-Models-Plus★ 126

别问我为什么大杂烩放在一块,懒得新建项目

TurboAgent★ 126
agent2api★ 125

多提供商本地网关:把 WorkBuddy、小浣熊、CatPaw、AutoClaw、Qoder、Cline 的登录态转成本地 OpenAI 兼容 API,含多账号管理、模型路由、出网代理与内容脱敏。

qoder2api★ 125

将 Qoder 的 AI 服务转化为兼容 OpenAI/Claude/Codex 格式的 API,支持每日签到领 Credits、多账号管理、模型上下文展示

model-message-stream-protocol★ 125

One interface for 1,000+ LLMs, with zero-code switching and built-in observability. (GPT 6 / Claude 5 / Gemini 4)

claude.asia★ 125

Claude中国镜像站上线!这一平台不仅提供了1:1还原官网的体验,而且实现了国内直连,为广大用户提供了更加便捷和流畅的使用体验。

litellm-rs★ 124

Self-hosted Rust LLM gateway with OpenAI-compatible APIs, load balancing, failover, and a reusable Rust kernel.

llm-interface★ 123

A simple NPM interface for seamlessly interacting with 36 Large Language Model (LLM) providers, including OpenAI, Anthropic, Google Gemini, Cohere, Hugging Face Inference, NVIDIA AI, Mistral AI, AI21 Studio, LLaMA.CPP, and Ollama, and hundreds of models.

llm-task-orchestrator★ 123

Top AI Router 2026: Split Codex for Quick Code & Claude for Complex Refactoring

openai★ 122

Implement OpenAI APIs and plugin-enabled ChatGPT with open source LLM and other models.

nexus-llm-router★ 122

Drop-in LLM router and AI gateway for OpenAI Chat Completions, Responses and Anthropic Messages APIs: 125 routing strategies (incl. feedback-aware Thompson sampling) across GPT-6, Claude Opus 5.5 / Fable 5.2, Gemini 4 and Kimi K3.1, a request feedback API, budgets, fallbacks, tenant rate limits, idempotency and audit logs.

opencode-free-bridge★ 122

OpenAI-compatible bridge for OpenCode free-tier models — no account required

workbuddy2api-panel★ 121

把腾讯 WorkBuddy 账号变成 OpenAI 兼容 API 的多账号网关。请求头照官方桌面端逐项对齐,主备入口 + HTTPDNS 自动切换,国内 / 国际双域合池,企业号可用 Claude,签到与成长任务全自动,React 管理面板支持一键更新。原版 workbuddy2api-panel 的持续同步增强版,Docker / 单文件部署。

Claude_api★ 120

Claude_api is a Python package that provides a convenient way to interact with Claude 2 from Anthropic.

Conduit★ 120

🦑 Unified Swift SDK for LLM inference across local and cloud providers

claude-gateway-manager★ 119

Best Tenbin AI Proxy for Anthropic Opus 4.8 & Sonnet 4.6 API Access 2026

AIephant-AI-Agent-Gateway★ 119

Alephant is an open-source AI Agent Gateway for routing, tracking, and controlling LLM usage across AI agents, members, and workflows, and for publishing agent capabilities as paid endpoints with x402 and MPP payment rails.

rgpt3★ 116

Making requests from R to the GPT models

groq-ruby★ 116

Groq Cloud runs LLM models fast and cheap. This is a convenience client library for Ruby.

hewn-forge★ 116

HEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code

subpool★ 116

A lightweight, self-hosted AI subscription pool for teams.

openai★ 115

golang的支持调用所有openai范式的ai的api的库

fabric-router-core★ 115

Smart Factory LLM Routing & OAuth Gateway Plugin 2026

agenthub★ 113

One interface for 1,000+ LLMs, with zero-code switching and built-in observability. (GPT-6 / Claude 5 / Gemini 3.8)

headroom★ 113

Track and rotate your Claude & Codex usage across accounts from one live dashboard — read live, never spending a token.

claude-proxy★ 113

Lightweight proxy that routes Anthropic API billing through Claude Code subscriptions. Zero dependencies, ~150 lines.

Trae2api-cn★ 113

Trae CN model relay: OpenAI-compatible Chat/Responses API with tool calling, reasoning effort, multi-account polling and checkin

ChatGPT-PHP★ 112

Official and Reverse Engineered ChatGPT PHP SDK (Not GPT-3)

openai-multi-client★ 112

Making your requests to the OpenAI API go fast!

ai-welfare-hub★ 112

Claude Code 免费 | 公益站 | New API | AI API 中转站导航 —— 自动探活 15+ 站点(Claude/Codex/Cursor/Gemini 免费额度、每日签到),GitHub Actions 每 6 小时更新存活状态,纯静态零依赖可 fork

model-relay★ 112

Per-window model switcher, subagent router, and automatic 429 failover for Claude Code — switch any window with /provider, delegate subagents across models, and keep Remote Control & statuslines working.

Routerly★ 111

Self-hosted LLM gateway that routes requests across AI providers (OpenAI, Anthropic, Gemini, Mistral, Ollama) using intelligent multi-policy scoring — including an LLM-native routing policy. Drop-in compatible: just swap the base URL. No database required, built-in cost tracking, budget enforcement and multi-tenant isolation.

Hermes-router★ 111

OpenAI/Anthropic-compatible AI router that keeps apps online with provider failover, key rotation, caching, analytics, and local-model fallback.

302api-developer-kit★ 111

302API 开发者资料与接入示例:Python / Node.js / cURL、客户端配置、前端组件与本地账单验算器。Apache-2.0 开源,再分发请保留 NOTICE 署名。

UnionLLM★ 110

通过与OpenAI兼容的统一方式调用国内外各种大语言模型和Agent编排工具API的轻量级开源Python工具包。

Better-Codex-App-Custom-Provider-Support★ 110

Adds support for selecting a custom model provider to use for a thread/chat, without logging out of your ChatGPT account.

tokenbank★ 109

Token Bank — the local LLM gateway that sits between your AI agents and every provider. Know where tokens go · Spend less with smart routing to Ollama, Groq, GitHub Models · Earn by sharing idle quota on a community P2P network. One-click onboarding for Cursor, Claude Code, Codex CLI, Gemini CLI — no agent changes. Full trace, seamless model swap

DeepAA★ 109

Local-first AI Agent gateway & observability for Codex, Claude Code,Dsh and more. 统一模型管理、调用追踪与 Token 成本分析。

llm-gateway★ 108

Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load balancing across OpenAI, Anthropic, Ollama, vLLM, and any compatible backend. Identity-based access, virtual API keys, and end-to-end encryption via OpenZiti

openapis★ 108

Free Claude API + free OpenAI API in one unified proxy. Drop-in compatible with Anthropic SDK, OpenAI SDK, Claude Code CLI, OpenCode, LangChain. 100+ models (Claude Opus 4.7, Sonnet 4.6, Haiku 4.5, GPT-5.5, GPT-5.4-mini, GPT-5.3-codex). Open beta — totally free.

awesome-ai-api-proxy★ 106

One key. Every model. Anywhere. — A curated map of AI API relay stations & LLM gateways.

sageroute★ 106

Trajectory-aware model router. An OpenAI-compatible proxy that starts every task on a cheap model, watches what the agent actually does, and escalates on real execution evidence via the Levanto Sage API.

xcode-copilot-server★ 105

GitHub Copilot proxy for Xcode with support for Claude Agent and Codex Agent.

chatgpt-java★ 104

⌨ Lightweight Java library for OpenAI's ChatGPT using the reverse-engineered API.

psaisuite★ 104

Enterprise-grade PowerShell abstraction layer for 15+ GenAI providers. Standardized interface for model benchmarking, tool-calling, and high-performance LLM integration

datadog-api-client-typescript★ 103

Typescript client for the Datadog API

claude-to-chatgpt★ 102

Claude 聊天接口适配到 OpenAI API 标准接口。

cc-relay★ 102

Blazing fast LLMs API Gateway written in Go ⚡️

claude-code-provider-gateway★ 102

The easiest way to use Claude Code with any LLM. Install the app, pick your provider, done.

llm-rosetta★ 102

Production-ready LLM API gateway and translation library — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Streaming & non-streaming. Zero core deps. Contributions welcome!

cnb2api★ 102

Bridge CNB cloud workspace models into OpenAI and Anthropic compatible APIs.

google-cloud-gcp-openai-api★ 101

🌴 Drop-in replacement REST API for Vertex AI (PaLM 2, Codey, Gemini) that is compatible with the OpenAI API specifications

thedistillery★ 101

The Distillery. A Token Optimization Proxy

Floway★ 101

Serverless LLM API gateway for you and your agents.

azure-functions-openai-extension★ 100

An extension (now retiring) that adds support for Azure OpenAI/ OpenAI bindings in Azure Functions for LLMs

signway★ 100

Bring the power of pre-signed URLs to your apps. Signway is a gateway for redirecting ephimeral signed URLs to the requested API

poe-code★ 100

Use Poe to power your favorite coding agents (Claude Code, Codex, OpenCode, etc). No need for multiple subscriptions.

ocgo★ 100

OCGO Provides an Ollama-style CLI for running Claude Code through an OpenCode Go subscription via a local Anthropic-compatible proxy.

litellm-skills★ 100

Agent Skills for managing live LiteLLM proxy deployments — users, teams, keys, orgs, models, MCP servers, agents

cline2api★ 100

cline to api,use in others agent etc.

opencode-deepseek★ 100

A local OpenAI-compatible bridge to the free DeepSeek web chat, which you can plug into opencode as a regular model provider and use as a full-fledged agent (reading/editing files, bash, code search, etc.) — with no API key and no payment.

semcache★ 99

Semantic caching layer for your LLM applications. Reuse responses and reduce token usage.

openai-api-rust★ 98

Rust client for OpenAI API

my_openai_api★ 98

部署你自己的OpenAI api🤩, 基于flask, transformers (使用 Baichuan2-13B-Chat-4bits 模型, 可以运行在单张Tesla T4显卡) ,实现了OpenAI中Chat, Models和Completions接口,包含流式响应

openclaw-java★ 97

OpenClaw 的 Java 全栈实现 — 基于 Spring Boot 的 AI Agent Gateway

anthropic-proxy-rs★ 97

A proxy server that intercepts Anthropic API requests and converts them to OpenAI-compatible format, enabling integration with dozens of inference providers such as OpenRouter, Together.ai, Novita AI, and other third-party API services. Primary use cases include Claude Code and other Claude Agent SDK-based tools.

antigravity-2.0-no-tun-login-proxy★ 97

Antigravity 2.0 不开启 TUN、无需使用 Proxifier 的登录代理修复方案。通过提供已配置好的 version.dll 和 config.json,让 Antigravity.exe 与 language_server.exe 走本地代理,解决 Sign In、Agent 初始化以及 daily-cloudcode-pa.googleapis.com 请求超时问题。

ChatGPT-Web2API★ 97

OpenAI-compatible API proxy for ChatGPT web — expose ChatGPT as an MCP server, REST API, and OpenAI SDK endpoint via CDP-driven browser automation

openai-api-server-via-codex★ 97

Get an OpenAI-compatible API from your ChatGPT subscription. Unofficial, lightweight Go server for OpenAI SDKs and existing tools, with no per-token charges within your Codex limits.

codearts2api★ 97

华为云 CodeArts Agent OpenAI 兼容代理 · 多账号轮转 + token 自动续期保活 + 并发控制 + WebUI

key0★ 96

key0 is the commercial gateway for your AI agents and APIs. Let AI agents discover, pay for, and access your APIs autonomously - no human in the loop.

fgpt★ 96

A free reverse proxy and CLI tool for OpenAI GPT-3.5-turbo.

control-layer★ 96

Open-source gateway for running agents on dedicated inference at scale. Offer an OpenAI-compatible API over your own model deployments, with per-team keys, usage metering, request logging and capacity pinning. 450x less overhead than LiteLLM

openclaw-deepseek-integration★ 95

DeepSeek API Platform integration for OpenClaw

More in Agent frameworks & infrastructure