Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 5 of 41
chatGpt Api SDK 封装,支持 GPT-3.5,GPT-4,账单查询,开箱即用,非常简单!
mimir is a drop-in proxy that caches LLM API responses using semantic similarity, reducing costs and latency for repeated or similar queries.
API proxy for calling endpoints using `agent` cli from Cursor
OpenAI API bindings for Lua
Local AI API gateway for OpenAI / Gemini / Anthropic. Runs on your machine, keeps tokens counted (SQLite), offers priority-based load balancing, optional OpenAI Chat↔Responses format conversion, and one-click setup for Claude Code / Codex.
Use your OpenCode Go subscription in the Codex app. Local Responses-to-Chat-Completions bridge for all 13 OpenCode Go models.
Production-ready Codex-compatible account-pool gateway with seamless failover, full-session recovery, native quota headers, WebSocket/HTTP bridge, and observability.
One control plane for every AI asset — MCP servers, skills, agents, AI apps. Self-hosted ledger with lifecycle state machine, 85 permission points, department × agent × skill cost attribution, and audit trail. MIT, zero runtime deps (Node 22 + node:sqlite). 企业 AI 资产治理。
An API for Chat Fine-Tuned Large Language Models (llm)
go 对接OpenAI ChatGPT接口,同时 azure openai接口已支持gpt-35-turbo和gpt-4模型
Route inference across providers.
Relay any model into any coding agent
self-hosted AI agent gateway written in Go, inspired by OpenClaw. Single binary, low memory, fast startup.
Reuse your Kimi Code (Moonshot) Coding plan inside pi-coding-agent
Anthropic-compatible HTTP facade over claude-agent-acp
Bifrost 是一个用 Rust 编写的高性能、AI 友好的代理服务器,它提供强大的请求拦截、修改和规则配置能力,支持 TLS 解密、脚本扩展等高级功能,支持强大的模糊搜索,支持导入导出分享,支持一键重放请求,支持Coding Agent 自主管理。提供类似 postman 的请求管理和验证能力,无缝和代理能力集成。
Drop-in OpenAI-compatible API gateway for Qwen AI models. Use your Qwen account (chat.qwen.ai) as a free AI API provider in any OpenAI-compatible client — Cursor, Continue.dev, Claude Code, VS Code Copilot, or any coding agent. Self-hosted, Chromium-based auth, streaming support, tool calling, dashboard.
将多个AI模型挂载为一个虚拟的本地Ollama服务,方便Vistual Studio Copilot Chat接入。
Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek models in Codex CLI or any OpenAI client. Cross-platform, single-file, no auth changes.
Claude Code / Codex 免费额度导航:收录 AI Coding 公益站 / 中转站,自动巡检可用性、签到额度、邀请返利,每 6 小时更新
Use Claude Agent SDK and Claude Code with other providers/models
OpenAI- and Anthropic-compatible HTTP API in front of the Cursor Agent CLI
Local OpenCode-backed LLM gateway for OpenAI, Anthropic, Gemini, and Responses API-compatible tools, with streaming and tool/function calling.
grok-build with the leash off — one binary, any OpenAI-compatible endpoint, zero phone-home. No x.ai account.
The AI runtime that turns your framework functions into OpenAI compatible endpoints
The GenAI API wrapper for Delphi seamlessly integrates OpenAI’s latest models (gpt-5 serie), delivering robust support for agent chats/responses, text generation, vision, audio analysis, JSON configuration, web search, and asynchronous operations. Image generation with gpt-image-2. Skills and agents
A lightweight AI gateway that exposes an OpenAI-compatible interface with full Tools support, using web AI sessions instead of API tokens.
⚡ Ultra-Reliable AI Inference Gateway & Verifiable Agent Control Plane. Dual-Dispatch, Zero-Token JSON Auto-Healer, VaaS On-Chain Attestation, FastMCP & Vercel AI SDK.
Agent-friendly GCP proxy deployment for fast, stable Claude access, with sing-box / Mihomo subscriptions and IP-based HTTPS.
MockAI is a mock server for OpenAI's API. It allows you to simulate Chat Completions API responses for development and testing purposes.
A native macOS menu bar app that proxies Claude/Codex/Gemini subscriptions for use with Factory Droid CLI. Always updated with new model releases!
Yosuri — LESS CHAT, MORE AUTOMATIC. A 24H self-evolving AI agent that aggregates free models into one OpenAI & Anthropic-compatible API, picks its own tasks, writes real code, and verifies results. Local-first, free forever. AGPL-3.0.
OpenAI, Azure OpenAI and OpenRouter Chat Completions (ChatGPT) .NET integration with DI, persistence and streaming support
Unified Python API for AI Batch Requests (50% discount on most providers)
One Endpoint, Every Model. Route, Monitor, and Failover — All From Your Terminal.
caching proxy for OpenAI API, deployable as a Cloudflare Worker
Pure Front-End LLM API Testing Tool
Free ChatGPT API reversed and simplified
1Panel AI 网关提供从统一接入、智能路由到合规审计的全链条管控,让企业 AI 落地更安全、更高效、更可控。
Providing Duckduckgo AI Chat API, which can use o3-mini for free.
A Java Lib for Google-Bard API (Reverse engineering of Google's Bard API)
Expose agent CLIs (Codex, Cursor Agent, Claude Code, Gemini) as an OpenAI-compatible /v1 API gateway.
AI-powered multi-model workspace and routing system for Claude, Codex and other LLM agents. Provides intelligent prompt routing, agent orchestration, evaluation workflows, CLI integrations, MCP tooling and developer productivity automation.
Use Duckduckgo AI Chat to provide an OpenAI-compatible API that can be used for free with o3-mini.
LangChain chat model abstractions for dynamic failover, load balancing, chaos engineering, and more!
Wrap OpenAI's Codex to an OpenAI compatible endpoint using Cloudflare Workers
Multi-tenant LLM API gateway for Claude and Codex — single Go binary, USD wallet, Alipay top-up, per-token caps, status-page health, fumadocs-style /docs.
别让支付卡死开源算力!Hugging Face / RunPod 专属买单通道
OpenAI Dive is an unofficial async Rust library that allows you to interact with the OpenAI API.
Raw line routing for large logs, source files, and agent-context references using GPT-6 Luna Light through Codex CLI.
Extension for the pi coding agent that intelligently routes each turn to the right LLM tier (high/medium/low) based on task intent, session budget, context size, and custom rules.
Multi-provider, multi-account AI proxy rotator with per-model routing, quota tracking, and provider compatibility. Non-technical setup: tell your AI agent to follow docs/agent-install-prompt.md.
Inference Hub for AI at Scale
A local proxy server that relays Anthropic Messages API-compatible requests to the Kiro (Amazon Q) backend using Kiro CLI credentials.
A tiny Rust gateway for running coding agents across model providers safely.
The official Rust library for the Edgee AI Gateway
Convert Cursor free API to OpenAI/Anthropic compatible format
A minimalistic OpenAI API client for the JVM, written in Java 🤖
OpenAI API -> Ollama API (original idea: https://github.com/microsoft/vscode-copilot-release/issues/7518#issuecomment-3043670968)
🚀 Free Unlimited OpenAI-compatible API for Google Gemini 4 Hydrogen & Neon. Supports Deep Thinking controls (High/Medium/Low), Agentic Task Mode, HTTP/3 QUIC, and multi-account pooling.
Interact with any LLM service
Rust client for t3.chat: use Claude, GPT, Gemini, Grok, DeepSeek, and 50+ other models from the terminal, with credit and usage tracking.
TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker/Worker/Verifier orchestration and policy loop for acceptance-driven completion.
A tiny, vendor-neutral LLM client library — one interface (LLMClient) with pluggable adapters for OpenAI, AWS Bedrock and Google Gemini, or bring your own backend.
∞ macOS menu bar app for switching Claude Code / OpenAI Codex / Claude Desktop accounts in one click — auto-fallback when you hit usage limits, auto-return on reset
Use DeepSeek, GLM, Kimi, OpenRouter and more in Codex CLI and Claude Code: one local endpoint, API translation, failover. Single Rust binary, CLIProxyAPI-compatible.
ChatGPT Web API server based on Flask that can respond both via browser through Flask Forms and directly via POST/GET Requests
AI agent relay station
Zero-dependency Node.js LLM proxy that auto-rotates API keys for OpenAI, Gemini, Groq and OpenRouter on 429s
A lightweight dashboard and reporting tool powered by OmniRoute - The Free AI Gateway
DeepSeek Harness control center for balance, usage, peak/off-peak pricing, encrypted multi-account switching, health checks, reminders, recharge, and session controls. / 余额、用量、峰谷计费、加密多账户、健康检查、提醒、充值与会话控制
Node.js client for the chatgpt API. No third party dependencies.
Deploy free DuckDuckGO AI in Cloudflare Worker.
Transparent proxy for Claude Code that auto-routes image-bearing requests to a multimodal model — so a non-multimodal primary model never crashes your long-running sessions.
The Claude companion for Laravel: the Anthropic API behind a facade, with batches, token counting, files, refusal fallback, named connections, events and test fakes, beside laravel/ai.
OpenAI-compatible proxy server for CommandCode API. Exposes /v1/chat/completions and /v1/models endpoints so any OpenAI-compatible client can use CommandCode models through a local HTTP server.
A golang lib to help you to get openai access token and refresh the token(一个golang sdk,帮助你更容易的获取openai chatgpt的accessToken :)
Multi-instance Claude Code manager with intelligent translation proxy. Use Claude Code with Grok, ChatGPT, DeepSeek, Gemini, Kimi, GLM, Ollama and more.
Open-source bridge to use Kimi AI inside Cursor. Connect Kimi models to your AI coding workflow with fast setup, clean configuration, and reliable local tooling for code generation, refactoring, debugging, and agentic development.
Unofficial Deno wrapper for the Open Ai api
Vercel AI SDK community provider for Codex CLI - Use Plus/Pro Subscription via spawn of Codex CLI.
Radicalbit AI Gateway
A self-hosted AI gateway for enterprises. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
This is a project that converts the official poe.com API to the OpenAI API.
Unofficial Java API supporting Chat, Assistants, and more!
OpenAI PHP asynchronous client for workerman and webman.
Golang lib for LLM APIs, ChatGPT, Gemini and Anthropic
OpenAI Codex安装配置神马中转API超详细教程,AI编程工具Codex实战配置文件常见错误总结
Self-hosted gateway for Claude Code, Codex, Antigravity, Grok Build, OpenCode. Run AI coding agents on your own infra with a shared local-first memory layer. Drive from web, mobile, Telegram / Slack / Discord / Feishu / DingTalk / WeCom. Open REST + WebSocket API. Apache 2.0.
Reverse proxy that exposes AgentRouter's Claude/OpenAI models as a local OpenAI-compatible API with WAF bypass, header spoofing, and auto model health routing.
A self-hosted AI gateway for enterprises. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
A secure and efficient gateway for interacting with OpenAI's API, featuring load balancing, user request handling without individual API keys, and global access control.
OpenAI o1/o3-mini 深度推理 API 防断流:CoreGold 企业级虚拟卡解决动态预授权死锁与天价账单熔断。
LiteLLM for Go, the easiest way to write LLM-based programs in Go
A reverse proxy server to cache the slow expensive requests to the openai api. Built with nginx and docker.
Codex中转,可自部署的代理服务
Free-tier LLM API key pool with rotation, cooldown handling, and an OpenAI-compatible proxy. Use with Hermes Agent or any OpenAI-compatible tool - no paid API key required.
A reverse proxy server to cache the slow expensive requests to the openai api. Built with nginx and docker.
A flexible PHP library providing access to various AI models (OpenAI, Claude, Gemini, DeepSeek and Grok) via a consistent interface.
FREEGPT4 is a python server that allows you to have a self-hosted GPT-4 Unlimited and Free WEB API, via the latest Bing's AI.