Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 7 of 41
通过代理访问openai api服务。
Hive Agents gateway localfirts
An OpenAI-compatible proxy server that lets Cursor IDE connect directly to GitHub Copilot's LLM services. Bypass Cursor's 500 premium requests/month limit by leveraging your existing GitHub Copilot subscription for unlimited AI-powered code completions, chat, and editing features within Cursor IDE.
Ollama Cloud plugin for Pi coding agent (API Key based)
NVIDIA NIM API provider extension for pi coding agent - access 100+ models from build.nvidia.com
Node.js SDK for interacting with OpenAI Chat API.
本项目基于 React + Spring Boot + Dubbo + AIGC,致力于为用户和开发者提供全面 API 接口调用和 AI 数据分析服务。
自建 ai api 反向代理服务,腾讯云函数,阿里云函数计算
Run any OpenAI-compatible model in Xcode Agent Mode. Use local models (Ollama and LM Studio) with no API key, or route to cloud providers with per-provider keys. Includes GUI, CLI, and over a dozen MCP tools.
Auto-delegation, status truth, and cost-aware model routing for OpenClaw agents
Self-hosted LLM router. Cost effective, deterministic, and fast. Secure and private by default.
Standalone Hermes Agent plugin: per-provider quota block in the footer + /usage, plus /quota command.
Multi-account rotating proxy for Claude Code — consume-first quota rotation, burst-aware 429 handling, hold-until-reset, per-device analytics. Herd-safe by test.
Claude Code plugin that picks the model and effort for each turn (micro, low, medium, or high tier), advised by Jev, Clef, OpenAI, or a local Ollama classifier.
OpenAI-compatible proxy for assistant-ui.com free LLM endpoint. Supports streaming, tool calling, vision, and 5 models.
Reduce Claude Desktop consumption by 10x - Integrate Google's Gemini or Z.ai's GLM-5 (744B params) with Claude via MCP for intelligent task delegation
F24 SALES free AI model directory, verified LiteLLM routes, import tools and agent-assisted model research.
Unlimited free GPT-3.5 turbo API service.
Agent that routes to different tools - LLM classifier SDK
🚀 cto.new 免费反代 | OpenAI & Anthropic 兼容 API | GPT-5.4 / GLM-5.1 账号池自动轮询 · JWT 刷新 · Dashboard UI · 批量注册 | Free OpenAI/Anthropic-compatible API proxy with account pool auto-rotation, JWT refresh, bulk registration & real-time dashboard. ⚠️ 不支持 agent 工具调用 / No function calling support.
把 CodeBuddy(国内站 + 国际版)、TRAE SOLO、OpenCode Zen、Kilo Gateway、Qoder、CodeArts、OfficeAce、小浣熊(SenseTime Raccoon)、WPS 灵犀(Lingxi)十个上游渠道封装为 OpenAI / Responses / Anthropic 兼容 API:公共凭证池、健康度调度与会话粘性、模型列表按渠道凭证加载、额度探测与每日签到、成长中心自动化、按人用量统计。逆向接口,仅供学习研究。
DSH 插件:把 WorkBuddy 桌面 App 里的模型接入 DeepSeek Harness,零配置直接用。(原生嵌入"插件-插件配置页")
Uncensored & abliterated AI models (GLM-5.3, DeepSeek V4, Qwen3) + Claude, GPT, Kimi, Gemini — one OpenAI/Anthropic-compatible API key. Docs, configs, tips.
Awesome AI gateways: open source and commercial LLM gateways, MCP gateways, agent (A2A) gateways, model routers, specs, and guides.
This is a Go client library for the OpenAI API
Community Plugin for Genkit to use Github Models
Round-robin proxy for multiple Claude Max subscriptions — multiply your Claude Code throughput with automatic OAuth token rotation and transparent request routing
Community-maintained registry of AI/LLM model configurations - pricing, features, and limits across 19 providers and 1000+ models
A unified OpenAI / Anthropic / Responses API gateway with built-in vision model injection — let any text-only model "see" images.
主要为 OpenCode Go 套餐打造的桌面客户端与本地代理:把 Claude Code 和 Codex 接到 OpenCode Go 并查看额度,也支持其他 OpenAI/Anthropic 兼容上游(Anthropic ↔ OpenAI Chat Completions / Responses 协议互转)。
AI Gateway
Unlimited FREE AI coding! Free AI API Gateway — 25+ models, no auth required, no api key, never hit limits.
在 Antigravity Manager 基础上接入 GitHub Copilot 上游提供商的 AI 网关(Rust + Tauri)
Local runtime for Claude Code and Codex — provider management, isolated sessions, routing and protocol translation.
High-performance OpenAI & Anthropic compatible API gateway for Qwen with multi-account rotation, interactive TUI dashboard, and resilient tool calling.
Share your claude/codex subscriptions ! multi-account router
Emulates Azure OpenAI API on your local machine using Ollama and open-source models.
Explore models form Vercel AI Gateway. Filter and compare by provider, context window, and pricing.
XAI
openai API 中转二次分发,docker一键部署,免费ChatGPT API,ChatGPT国内转发API,直连无需代理。一行Docker命令部署的 OpenAI/GPT API代理,支持SSE流式返回、腾讯云函数 。Simple proxy for OpenAi api via a one-line docker command
Drop-in caching proxy for OpenAI and Anthropic APIs - stop paying for the same answer twice!
An Anthropic-compatible /v1/messages proxy that lets Claude Code use the ChatGPT Codex backend.
Unofficial OpenAI & Anthropic-compatible bridge for chat.qwen.ai (Qwen3.8-Max) — single Go binary, multi-account pool, tool calling, Persian dashboard. Ported from GLM-Free-API.
ChatGPT API for https://github.com/yi-ge/chatgpt-web.
The Fastest enterprise AI gateway — route LLM traffic across OpenAI, Anthropic, Gemini, Groq & 30+ providers via a single API. Self-hosted, no vendor lock-in. ( 55x faster than litellm )
Turn a model gateway into a standard OpenAI-compatible API with a built-in web console. Zero deps (Node.js built-ins only). 把华为云果办 OfficeAce 模型网关反代成标准 OpenAI 兼容 API,自带中文控制台。
Claude Code CLI 代理服务器 - 多租户、自动故障切换、Web 管理界面
Production-ready Python library for multi-provider LLM orchestration
DuckDuckGo AI to OpenAI API
This is example of using Workers AI. This Cloudflare Worker provides a Base URL which allows you to make AI calls to the @cf/meta/llama-3-8b-instruct model using an OpenAI client.
OpenAI-compatible multi-account Codex and vibe coding proxy
A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and +1.9 pts completion on our tested dataset.
并发调用本机 Grok 4.5、Kimi K3 与 Claude Code,带实时心跳和独立日志 | Concurrent local model CLI orchestration with live progress and isolated logs.
ESP32 Arduino Framework Library to allow connection to OpenAI Chat Completions Endpoint
Merlin SDK Provides A Unified API To Interact With 20+ LLM Models.
Use frontier LLMs from nearly any orovider in VS Code with GitHub Copilot Chat - no Copilot subscription needed. Powered by any Vercel AI-SDK compatible provider including Claude Code, LiteLLM. z.ai, OpenAI, Anthropic and almost any other provider.
CopilotProxy — Ollama 兼容的多模型 AI 代理
A tiny, rate-limit-aware OpenAI-compatible proxy for the NVIDIA NIM API, built for agent harnesses like OpenCode, Codex, n8n, and anything else that speaks the OpenAI API.
Free Gemini web interface proxy for OpenCode - Use your free Gemini subscription as an OpenAI-compatible API with full tool calling support
A 3rd-Party Golang Client Library for Zhipu AI Platform
Reactive WebFlux OpenAI API Client in Java
A simple, modern, and reliable Go library for interacting with multiple LLM providers
🚀 AnyProxyAi - Universal AI API Gateway GUI | 通用 AI API 网关 GUI - Route, convert and manage multiple AI provider APIs (OpenAI, Claude, Gemini) through a single unified interface. 通过本地统一接口路由、转换和管理多个 AI 服务商 API相互转换。Built with Wails + Vue 3.
A Cloudflare Worker proxy that enables Claude Code to use NVIDIA NIM API models
Edge-native AI API gateway — cost-optimized routing across providers, multi-protocol support, built on Cloudflare Workers.
NPX/Docker package that creates Ollama API server and forward requests to Gemni/OpenAI/Deepseek/Kimi K2. Mainly purpose to use Free tier APIs in Jetbrains AI Assistant
Cost-optimised agent router for Claude Code: sends every sub-task to the cheapest model that can do it, and escalates only on verified failure.
Save your GPT-6 Astra tokens. Let Luna do the dirty work.
在 dsh 里装上这个插件即可,无需登录、注册或填 API Key,就能使用包括 Muse Spark 1.3、MiMo V2.6 在内的前沿模型——完全免费,不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, Muse Spark 1.3 and MiMo V2.6 among them. Completely free, with no usage cap.
Google Antigravity / Cloud Code Assist inference provider plugin for Hermes Agent
Claude Code / Codex / Grok 桌面供应商一键切换器:API 中转站与官方账号一键切换、本地代理热切换、测速与真实流式体检。One-click provider switcher for Claude Code, OpenAI Codex CLI & Grok CLI. cc-switch alternative · Tauri + Rust · Windows/macOS/Linux · No ads.
decentralising the Ai Industry, free gpt-4/3.5 scripts through several reverse engineered api's ( poe.com, phind.com, chat.openai.com, phind.com, writesonic.com, sqlchat.ai, t3nsor.com, you.com etc...)
Lightweight HTTP proxy enabling Claude Code to work with OpenRouter (200+ models), OpenAI Direct (GPT-5), and Ollama (local inference). Full tool support, streaming, thinking blocks.
lm15 for Python: one request and response model for every AI model provider. The reference implementation; standard library only. pip install lm15
Node.js backend that unifies multiple AI models into one API featuring rate limiting, caching, input validation, streaming, and monitoring.
Universal API client for common AI models
With AI Core as a proxy for Azure OpenAI Services, we are able to perform prompt engineering, e.g. to add more context in the form of (SAP) documents or to perform input validation. This repo serves as a starting point for such a raw proxy and shows how SAP BTP, AI Core can be consumed and exposed via a CAP API.
Unofficial PowerShell Module for OpenAI, Azure OpenAI and almost all the GPT services or even local LLMs
Delphi implementation of ChatGPT - an event based component
A powerful, unofficial OpenAI-compatible API service offering free access to GPT-4o, GPT-4-turbo, and audio preview models like gpt-4o-audio-preview & Realtime Models like gpt-4o-realtime. Features streaming responses, voice synthesis, TTS with no authentication requirements. Hosted on Hugging Face & Railway (Free tier)
Fake API Server for AI-Bypass
Free JSON API for Claude peak hours: is it peak right now, and when does it change? Used by status lines, shell prompts and menu bar apps.
对网页deepseek的封装,实现免费API调用。支持 OpenAI completions / responses socket。可工具调用,可接入codex、copilot。轻量自用
A lightweight, highly secure AI API Gateway/Proxy written in Go. Acts as transparent middleware between local AI coding clients (OpenCode/Pi/Cursor) and upstream LLM providers (Gemini, DeepSeek, Zhipu z.ai).
With AI Core as a proxy for Azure OpenAI Services, we are able to perform prompt engineering, e.g. to add more context in the form of (SAP) documents or to perform input validation. This repo serves as a starting point for such a raw proxy and shows how SAP BTP, AI Core can be consumed and exposed via a CAP API.
Self-hosted AI workbench for a company LAN. One command on a Windows server sets up login, roster, model gateway, company disk and knowledge base; each employee's agent works on their own PC while model keys stay on the server. 一键安装的局域网 AI 工作台。
🤖 Hermes Agent + 9Router + OmniRouter on a free Hugging Face Space — one-click deploy with a beautiful web wizard (Telegram bot, web dashboard, OpenAI-compatible API, hourly backups)
Use your OAuth subscriptions or API keys in any coding agent, Factory Droid, Cursor, and more. Tunnel Agent handles provider authentication and routes requests through CLIProxyAPI or 9Router.
Your Claude, ChatGPT and Gemini subscriptions as one fast API. A single Rust binary with OpenAI, Anthropic and Gemini compatible endpoints, WebSockets and a built-in dashboard.
DeepSeek Harness bundle: the AgentRouter relay as one pi-ai route with a domestic/international endpoint switch, plus the outbound request compatibility the relay requires.
Automatic multi-account failover & rotation for Pi Agent across Anthropic (Claude), OpenAI/ChatGPT Codex, and Qwen/Alibaba.
OpenAI API client library for .NET. I was developed it for for public use and it is free.
One API, any AI
神马中转API教程文档_Claude中转教程_AI中转站配置使用教程_支持Claude、Midjourney、Suno、OpenAI等650+模型教程
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
Cross platform GLM proxy for AutoClaw's Zhipu AI models. Provides OpenAI-compatible Chat Completions and Anthropic Messages APIs for Claude Code, Cursor, Continue, OpenCode, and SDKs
OpenCode 免费模型的 OpenAI 兼容代理,纯 Go 实现,支持 SSE 流式,可部署到 Vercel、Docker 或本地。
Ask, compare, and synthesize across 10 LLM providers. Python SDK, CLI, local Arena, MCP, and privacy-aware
Use Claude Code's UI with OpenAI GPT-5.6 (Sol/Terra/Luna) as the engine — powered by your ChatGPT Plus/Pro subscription via a local Codex proxy. One-line install; plain claude stays untouched.