Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 9 of 41
Duckduckgo AI Chat to OpenAI API that can be used for free with gpt-4o-mini, llama-3.3, claude-3-haiku, o3-mini , mixtral-8x7b.
a simple web interface to check whether your OpenAI API key supports GPT-4
Make LLM as an API server
Gateway and load balancer to your LLM inference endpoints
chat.z.ai reverse-engineered OpenAI-compatible API proxy — supports streaming, thinking/reasoning, web search, and tool calling
A local mock LLM API server for development and testing: OpenAI, Claude and Gemini-compatible, with fixture replies, Claude tool calls, streaming, error simulation and a dashboard.
Session-scoped GPT-5.6 agent routing for Claude Code
Free Gemini web interface proxy for OpenCode - Use your free Gemini subscription as an OpenAI-compatible API with full tool calling support
Manage Pi providers and models from a TUI with native models.json persistence, header profiles, proxy routing, and protocol compatibility.
OpenAI-compatible gateway for todofor.ai with account pooling, tool calling, and streaming
把 OpenAI Prism 折射成标准 API 的 Go 网关:OpenAI Chat / Responses、Anthropic Messages、Codex CLI 开箱即用,多账号池调度与内置管理控制台
OpenAI & Anthropic-compatible gateway for Qoder IDE — account pool with failover, embedded dashboard · t.me/D3_vin
A straightforward method to reduce your LLM inference API costs and token usage.
AI gateway as a framework. For full control over models, routing & lifecycle. OpenAI /chat/completions, OpenResponses /responses & Anthropic /messages.
GigaChat API совместимый с OpenAI
A lightweight and intuitive Node.js client for the Paxsenix AI API.
OpenAI Router 轻量级、持久化、零配置的 OpenAI API 统一网关
LLM proxy with built-in DLP and regulatory compliance. Redacts secrets before they reach the API. EU AI Act, GDPR, HDS/PCI DSS ready. Multi-provider failover, live TUI, virtual keys, fan-out. 6 MB, zero deps. Rust.
Make every model a CodeX engine through an OpenAI-compatible Responses API gateway
Enterprise AI traffic gateway — unified compliance, routing across 20+ LLM providers, semantic cache, quotas, and audit. SDK / network / OS-layer intercept.
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.
Quality-per-token GPT-5.6 Sol, Terra, and Luna model router for Codex, Work, CLI, and subagents.
A self-hostable LLM router / gateway: OpenAI- and Anthropic-compatible, explicit-first routing with fallbacks, spend limits, and metadata-only cost tracking. No markup, no third-party proxy — your keys, your box.
Unofficial OpenAI-compatible bridge for Factory Droid
🚀 One API gateway for GPT, Claude, Gemini, DeepSeek and more. OpenAI-compatible API for developers.
DeepSeek Harness auth插件
OpenAI-Compatible API Proxy for ChatGPT Web with Sentinel PoW solver, tool-calling injection, and multi-account pool rotation.
Run Claude Code and Codex across multiple subscription accounts. A local Rust proxy that sends each request to the account with quota left, keeps each conversation on its warm prompt cache, and shows usage in a macOS menu bar app.
React Hooks for Keyless AI
bard-api-node is a Node.js library for interacting with Bard, an AI Chatbot developed by Google. Bard is based on Google's Large language model (LLM), LaMDA, which is designed to generate human-like text and images in response to prompts.
SwiftyGPT is an unofficial, lightweight and user-friendly Swift wrapper for accessing OpenAI API
The reliability layer between your code and LLM providers.
Use any LLM with the Cursor Agent SDK
Claw is a local-first AI control plane that runs powerful open models on your machine and connects to top LLM providers. It intelligently routes every prompt to the best model, giving you one secure workspace for chat, memory, context, connectors, routing, and full AI orchestration.
Multi-resource rate limiting for LLM APIs. Reserve tokens before you call, refund what you don't use, stay under the limit across workers.
使用TG Bot管理的AI模型中转工具,支持Anthropic、OpenAI Chat/Respones、Grok协议,支持OAuth登录,支持第三接口接入.
Unofficial Node.js client for gemini.google.com.
[ACL 2026] Official implementation of MTRouter, a cost-aware multi-turn LLM routing framework accepted to ACL 2026 Main Conference.
Enable interaction with distributed, decentralized LLMs on the Morpheus network through a desktop chat experience
🐢⚡ The best free API key rotation + automatic model fallback for Agent Zero. Many keys and models as one pool: every 429 / RESOURCE_EXHAUSTED read, each key rested exactly as long as needed, a late reply raced by your next model. Gemini, OpenAI, OpenRouter, any provider.
CodeBuddy / WorkBuddy 账号池管理工具 · Account pool manager —— 集中管理 CodeBuddy 中国站多账号,内置本地 OpenAI 兼容反代,多账号调度 / 配额监控 / 每日签到 / API Key 管理 / 模型同步与本地缓存 / 请求统计 / 系统托盘通知。Multi-account routing, quota monitoring, daily check-in, local reverse proxy & more.
zen-proxy is a local translation proxy that bridges Claude Code's Anthropic Messages API with OpenCode Zen's OpenAI‑compatible Chat Completions endpoint (https://opencode.ai/zen/v1). It forwards requests so you can use Zen's free model tier — hy3-free, deepseek-v4-flash-free, nemotron-3-ultra-free, and others — directly from Claude Code, with full
Never hit rate limits again. One OpenAI-compatible endpoint for 60+ providers & 1,200+ models — smart auto-fallback, prompt compression, 60-language dashboard. Plug into Claude Code, Cursor, Codex & more. Free, open-source, self-hosted.
Turn a pool of WorkBuddy / CodeBuddy accounts into one OpenAI-compatible API. Go + Vue 3, single binary, with users, quotas, billing, API keys, payments and an account-pool admin panel.
NLP Cloud serves high performance pre-trained or custom models for NER, sentiment-analysis, classification, summarization, paraphrasing, intent classification, product description and ad generation, chatbot, grammar and spelling correction, keywords and keyphrases extraction, text generation, image generation, code generation, and much more...
Node Js OpenAI Authentication Library for ChatGPT
IYKYK
Go client for interacting with OpenAI API endpoints.
Ruby wrapper for OpenAI's ChatGPT APIs.
让 GLM-4.5 完美适配 Agent TARS 系统的高性能适配器 - 解决 toolcall 兼容性,提供智能 fallback,极低成本享受顶级 AI Agent 体验
poe-chat-api is an open source Node.js library for Poe Chatbot AI.
Python client designed specifically for large-scale requests to the openai interface
Save 50% off GenAI costs in two lines of code
A local proxy to intercept and replace standard CLI or BYOK authentication with Kiro/AWS creds... basically letting Claude Code operate independently from Anthropic’s native billing backend
Open-source control plane for private, governed enterprise AI — one gateway for every model, composable governed pipelines, and apps your whole team builds in plain language, on infrastructure you own.
BrighTO LLM Router: free open-source, ultra-fast Rust LLM gateway/router and LiteLLM/Bifrost alternative with OpenAI + Anthropic APIs, Claude CLI bridge for OpenAI-compatible models, Qwen3.8 dual protocol, model load balancing, fallback routing, team API keys, token budgets, SystemOne decisions for Ollaya/Laya, JEV/DJEV and Quyết.
Self-hosted AI gateway for small teams: a key per person, budgets that fall back to local models, PII masking and free SSO.
Find out which model actually answers your Codex requests (detects silent model substitution, e.g. gpt-6-astra served by gpt-5.6-luna)
Self-hosted LLM gateway: vendor keys, rule-based routing, fallbacks, throttling and usage reporting over gRPC
The Hugging Face API wrapper for Delphi leverages cutting-edge models to deliver powerful features, including object detection, music generation, text classification, sentiment analysis, image segmentation, speech-to-text transcription, and text generation.
Scalable API gateway that aggregates calls to multiple LLMs (OpenAI, Hugging Face, Groq, Anthropic, Gemini, etc.), includes caching, rate limiting, logging, monitoring and production-ready deployment.
Connect to ChatGPT / OpenAI API using plain PHP
OpenAI ChatGPT, GPT-5, GPT-Image-1, Whisper API clients for Go
A powerful API proxy that seamlessly integrates ChatGPT unofficial browser API with OpenAI, bypassing CloudFlare's anti-bot detection for uninterrupted access.
Add AI capabilities to your app in seconds. The ultimate UI component for managing LLM providers and models. 快速为你的应用接入 AI 能力。通用 AI 模型配置组件。支持 React & Vue,内置 20+ 主流厂商,开箱即用。
🧑💼 AI gateway exposing Anthropic, Gemini, and OpenAI-compatible APIs, backed by GitHub Copilot, OpenAI Codex, Microsoft Foundry, and compatible model servers
统一AI网关基础库。多协议、多模型适配的 AI 基础设施库,支持 OpenAI/Anthropic/Gemini 等 46 个服务商,提供函数调用、图像生成、MCP 工具调用等能力
About Using OpenAI ChatGPT / Google Gemini / Anthropic Claude / Amazon Bedrock with Tailscale with an app connector, from an unrestricted region.
150+ free AI models across 20+ providers. Groq, Cerebras, NVIDIA and more with automatic fallback when rate limits hit.
Zero-dependency Go proxy for rotating free-tier AI API keys. No more 429s.
The fastest-growing AI community on Discord. Chat, earn, and build together. discord.gg/crow
A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-in proxy + one-line Python API for Claude Code, Codex, Cursor, OpenAI, Anthropic & Ollama. pip install foveance
Fugusashi — Federated Learning of LLM Routing with Human-Interpretable Decisions. Open-source alternative to Sakana AI Fugu.
Local multi-provider proxy for Claude Code — automatic failover, priority routing, auto-recovery, usage analytics, and a provider catalog
The control layer for agentic AI. A protocol-aware proxy that applies identity, policy, trust and payment controls to A2A, MCP and DIDComm traffic between callers and agents.
Unofficial Node.js client for gemini.google.com.
Python command-line tool for interacting with AI models through the OpenRouter API/Cloudflare AI Gateway, or local self-hosted Ollama. Optionally support Microsoft LLMLingua prompt token compression
This sample shows how to take a ChatGPT prompt as HTTP Get or Post input, calculates the completions using OpenAI ChatGPT service, all hosted in an Azure Function.
Unimpeded: Convert Poe.com to OpenAI Interface-Compatible Format! 🔑 畅通无阻: 将 Poe.com 转换为 OpenAI 接口兼容格式!
Stop runaway LLM agent costs
Self-hosted AI gateway in one Rust binary: OpenAI- and Anthropic-compatible API, routing with fallbacks, budgets, rate limits, logs and a built-in console for teams.
An AI chat proxy with universal tool access, protocol conversion, load balancing, key isolation, prompt enhancement, centralized MCP hub, and built-in WebSearch & WebFetch — more than an AI assistant for chat, translation, mind maps, flowcharts, and search.
Self-hosted API gateway for Claude Code on Amazon Bedrock — unlock extended thinking, web search & tool use with team budgets, OIDC SSO, and an admin portal
Transparent Codex wrapper and account-rotation proxy
Lightweight signal-driven LLM router for Claude Code, Cursor, Codex, Gemini CLI, and Codex CLI
A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run. Plus vision and BlockRun's full model catalog from one wallet, paid per request over x402.
Loopback-first universal API gateway for local AI Agents.
基于 Sub2API 的非官方可扩展衍生版。
Self-hosted LLM gateway with SSO, audit logs, client access controls, routing, and usage tracking. OpenAI-compatible and MIT licensed.
Local, self-hosted agent infrastructure — one endpoint for every AI client (Claude Code, Codex CLI, Gemini CLI, OpenCode). Unified model access, platform-run tools, request history, and usage.
dsh-model-master(模型选择大师)— model selector for DeepSeek Harness: search across providers, probe any model with a real streaming request to measure TTFT and TPS, and jump from a leaderboard row to a local search for channels of that name.
Multi-API Proxy Gateway Based on Vercel Routes, Cloudflare Workers, and Netlify Redirects
Adapter / facade for language models (OpenAI, Anthropic, Cohere, local transformers, etc)
A managed proxy gateway and compiler for AI agents. It takes noisy OpenAPI/MCP directories, compresses them in flat mode, saves tokens, and adds Governance.
Budget-Aware Agentic Routing (BAAR) — Intelligent LLM model selection with a zero-call financial kill-switch. Save 90% on costs without losing accuracy.
Prism — a one-click desktop LLM gateway. Embeds 37 providers (OpenAI / Anthropic / Gemini / Bedrock / …) behind one OpenAI-compatible endpoint, with Cloudflare Tunnel built in. AGPL-3.0.
Anthropic Claude models on Google Cloud Vertex AI for pi coding agent.
Local-first Codex quota tracker and multi-account switcher for macOS and Windows
OpenAI-compatible HTTP API that acts as a gateway to the Agent Client Protocol (ACP)