Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 8 of 41

claudex★ 36

Run Claude Code with GPT models through Raine's claude-code-proxy.

aiplane★ 36

croit AIplane — one plane for all your AI. Self-hosted AI infrastructure connecting applications and users with models, agents, tools and enterprise data: an OpenAI-compatible LLM gateway, server-side agent execution, MCP, RAG, memory, sandbox, identity, RBAC and quotas. Routes across vLLM, SGLang, Ollama and hosted APIs.

muse-bridge★ 36

Turn Muse (AI agent) into an OpenAI-compatible model (ms/muse) inside self-hosted 9Router for Hermes — file-queue bridge with native tool calls, unlimited batching & image understanding. Beginner tutorials in English & Indonesian

gpt-6-sol-agent-router★ 36

Argolink-focused agent gateway integration for GPT-6 Sol.

NanoProxy★ 35

A local proxy for OpenCode and similar OpenAI-compatible coding clients that works around NanoGPT’s often unreliable native tool calling. Instead of relying on NanoGPT to return proper tool calls directly, it sends a stricter text-based tool format upstream and converts that back into normal OpenAI-style tool calls for the client.

Local-LLM-Server★ 35

quick way to build a private large language model server and provide OpenAI-compatible interfaces | 快速搭建私有大语言模型(LLM)服务,提供OpenAI兼容接口

claude-proxy★ 35

Claude Code / Claude Agent SDK proxy for DeepSeek, Qwen, GLM, MiniMax, Kimi and MiMo via Anthropic Messages API with observability

codex-as-api★ 35

Local OpenAI & Anthropic compatible API server backed by ChatGPT/Codex OAuth credentials. Python, TypeScript, and Rust.

PaiSwitch★ 35

🔀 AI Coding Agent 模型切换器:为 Claude Code / Codex 一键切换 DeepSeek、Qwen、Kimi、OpenRouter 等模型,内置本地 LLM 代理、API Key 管理和 macOS 桌面版。

copilot-adapter★ 35

AI Models Adapter for Copilot Chat

linktokenview-docs★ 35

LinkTokenView(联视未来)国产大模型 Token API 聚合平台,提供 OpenAI 兼容接口,统一调用 DeepSeek v4.1、Kimi、GLM、通义千问 等模型,支持 Token Plan 与 Coding Plan。支持Codex、Claude、Harness、WorkBuddy等各类Agent工具。已上线deepseek-v4.1-flash。

multi-gpt★ 34

🤖 OpenAI. No account required.

fastapi-web★ 34

企业级 LLM API 快速集成系统,支持OpenAI、Azure、文心一言、讯飞星火、通义千问、智谱GLM、Gemini、DeepSeek、Anthropic Claude以及OpenAI格式的模型等,简洁的页面风格,轻量高效且稳定,支持Docker一键部署。

codex-fast-proxy★ 34

Paused Codex App auth-split proxy experiment; future work would need a Responses-to-Chat-Completions adapter.

amazon-bedrock-copilot-chat★ 34

A VSCode Language Model Chat Provider to use Amazon Bedrock in Copilot Chat

copilot-proxy★ 34

copilot proxy for glm coding plan, will support more in the future (maybe?)

kalibr-sdk-python★ 34

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

trooper★ 34

LLM reliability layer -keeps agents alive with smart routing, context compaction, and local fallback

khazad★ 34

Transparent, transport-layer semantic cache for LLM API calls, powered by Redis 8 Vector Sets.

Fable-agents★ 34

Portable model routing for Claude Code, specialized agents, ship gates, and Codex.

claudegpt★ 34

Use ChatGPT/Codex OAuth in Claude Code without an API key

Lupin★ 34

Run Claude Code on any LLM provider without losing your setup, local-first proxy with verified profiles, OAuth device-flow login, failover, content-aware routing and an honest per-model compatibility doctor

api-rank★ 34

AI API排行榜 - 实时139+中转站,自动排行,最高性价比中转站 Claude/GPT/Gemini/DeepSeek API中转站 | AI API Transit Station Ranking

krouter★ 34

Universal AI router — save 20-40% tokens with RTK and never stop coding. Connect Claude Code, Cursor, Antigravity, Kiro, Copilot, Codex, Cline & any OpenAI-compatible client to 40+ providers & 100+ models via one local endpoint. Zenith sub-1ms failover, MITM, multi-account.

omniroute-agent-extension★ 34

OmniRoute extension for Pi Coding Agent, OMP, and Prime Agent with model sync and OpenAI-compatible routing.

llm-proxy★ 33

Codex + Claude → DeepSeek or other llm 本地代理 | Agent Protocol Translation Proxy

api-proxy★ 33

OpenAI、Gemini Pro Proxy | 代理服务

chatgpt-free-api★ 33

Provide free GPT-3.5 API service by reverse engineering the login-free ChatGPT website.

CLIProxyAPI-Quota-Inspector★ 33

CLIProxyAPI 的统一配额与用量查询工具. A unified quota and usage inspector for CLIProxyAPI.

openai-oxide★ 33

Idiomatic Rust client for OpenAI API — 1:1 parity with openai-python

model-router★ 33

Automatic cost-aware model routing plugin for Hermes Agent

pi-antigravity-rotator★ 33

Intelligent multi-account rotation proxy for Google Antigravity with per-model routing, real-time quota tracking, automatic token management, and infringement detection.

haxsd-byok★ 33

Windows x64 本机模型网关:让 Cursor、Devin、Codex 与 Claude Desktop 使用你自配的模型 API,含模型库、调用记录与 Token 统计。

muse-bridge★ 33

Expose any AI agent worker as an OpenAI-compatible API — plug it into 9Router (or any OpenAI client) as a custom provider.

falProxy★ 32

A high-performance, self-hosted Deno proxy that makes Fal.ai's powerful models (Flux, SDXL, etc.) compatible with the standard OpenAI image generation API. Use any OpenAI client seamlessly.

autogen-oaiapi★ 32

An OpenAI-compatible API server for AutoGen

openai-unofficial★ 32

An completely Free & Unlimited unofficial Python SDK for the OpenAI API, providing seamless integration and easy-to-use methods for interacting with OpenAI's latest powerful AI models, including GPT-4o (Including gpt-4o-audio-preview & gpt-4o-realtime-preview Models), GPT-4, GPT-3.5 Turbo, DALL·E 3, Whisper & Text-to-Speech (TTS) models

aqueduct★ 32

Aqueduct is a simple yet fully-featured AI gateway built on top of the LiteLLM Router SDK using Django.

webllm-gateway★ 32

WebLLM Gateway:让 Qwen/DeepSeek 网页模型接入 OpenAI/Anthropic 兼容 Agent 工具链,支持 OpenClaw、Hermes、Claude Code、Codex 工具调用

Claude-Code-NVIDIA-Free-AI-Coding-Agent★ 32
ferrogate★ 32

Open-source AI gateway on Cloudflare Workers, in TypeScript: OpenAI/Anthropic-compatible chat with SSE streaming, Files + Batch APIs, provider routing with circuit breaking and failover, virtual API keys, per-tenant Durable Object storage, quotas/wallets/budgets, guardrails, response cache, MCP server, durable metering, contract-driven Admin API.

mmcp★ 31

Multi-Model Collaboration Pipeline — orchestrate AI models as a DAG. RL routing, multi-verifier voting, agent mesh, self-improving. Works with OpenAI, Anthropic, Gemini, DeepSeek. npm install mmcp-core | pip install mmcp-core

parallel_process_gpt★ 31

Process 1000 calls to ChatGPT API in 2m

openrouter_client★ 31

A comprehensive OpenRouter API client library for ESP32 (ESP-IDF), enabling seamless integration with OpenRouter’s AI models. Supports text generation, streaming responses, function calling, and multimodal capabilities including image and audio processing.

streamed-chatgpt-api★ 31

A node module for streaming API responses from the ChatGPT APi.

llmprice.cn★ 31

LLM price comparison 大模型价格对比

relay★ 31

High-throughput, self-hostable LLM router in Go. BYO provider keys, k8s-native, key pooling + batch + usage observability.

helm-api★ 31

Self-hosted LLM gateway — route OpenAI/Anthropic/Gemini traffic by config, not code. Fallback, protocol translation, telemetry.

free-astra★ 31

Use GPT-6-Astra from local Codex for free - no paid plan, no API key, just a signed-in prism.openai.com session

whalegate★ 31

🐳 whalegate — OpenAI-compatible gateway into DeepSeek web sessions (Rust): account pool, failover, SSE, native-style tool calling (tool_choice, schema validation, repair retries), vision, PoW solver. Prefer the official paid API.

ChatGPTSharp★ 30

This project implements ChatGPT continuous dialogue based on ConversationId, which can be quickly integrated with just a few lines of code. It supports models such as gpt-4, gpt-3.5-turbo, and text-davinci-003.

claude-code-openrouter★ 30

Claude Code agent that routes to external LLMs (Grok, Gemini, GPT-5, etc.) via OpenRouter - just mention the model name

flyllm★ 30

A Rust library for unifying LLM backends as an abstraction layer with load balancing and parallel generation.

openai-authenticator★ 30
LLMProxy★ 30

LLMProxy is an intelligent large language model backend routing proxy service.

any-api★ 30

AI 多模型 API 聚合与协议转换网关:统一调用并互转 OpenAI Chat/Responses、Claude、Gemini 等格式,Provider 仅需实现原生协议。Multi-LLM gateway & protocol transformer: unify and convert OpenAI Chat/Responses, Claude, Gemini, etc.; providers implement native only.

agent-command-center-sdk★ 30

SDK Client for Agent Command Center

openai-c★ 30

C bindings for the OpenAI API

Antigravity2Api★ 30

🚀 Transform Antigravity into standard Claude and Gemini APIs, enabling seamless tool use, structured outputs, and workaround support for MCP issues.

ccrelay★ 30

Switch Claude Code, Claude Desktop and ChatGPT/Codex to third-party models from one desktop app. Local proxy converts Anthropic/OpenAI formats automatically.

tokdiet★ 30

Local streaming reverse proxy between AI coding agents (Claude Code, Cursor, Codex) and model APIs (Anthropic, OpenAI, Gemini, MiniMax). Meters every token + USD cost, compacts bloated context to cut pay-per-token API spend, and runs shadow-eval to prove quality held. ccusage-style metering + live local dashboard.

openproxy★ 30

Smart AI proxy router that connects Claude Code, Cursor, Codex, Copilot, and 50+ coding tools to 40+ AI providers with 100+ models. Saves 20-40% tokens via RTK compression, auto-fallback from subscription to cheap to free providers, multi-account round-robin, and a local dashboard.

hub-cc★ 30

Local control plane for Claude Code on Windows and macOS: switch LLM gateways in one click behind a fixed endpoint, SSE keepalive proxies, key pools with live balances, GitHub accounts with TOTP, statusline, Telegram remote.

Free-Gemini-pro-API★ 30

Free, unlimited Google Gemini Pro API proxy completely compatible with OpenAI and Anthropic standards. Features auto cookie refresh, account pooling, and a beautiful admin dashboard.

sub2api-excel2api-plugin★ 30

Sub2API 0.2.7 OpenAI OAuth 插件:Excel2API BPS 隧道、Codex CLI 工具目录、请求时区与并行降智检测。

pi-vlm-proxy★ 30

让非多模态模型(DeepSeek 等)把图片识别委托给任意 OpenAI 兼容的多模态模型。零厂商硬编码,主模型支持视觉时自动隐藏自己。

one-api★ 30

⚡ One API for 20+ LLM providers. OpenAI-compatible, single binary edge gateway, streaming & rate-limiting.

cfbase64★ 29

🔧 Base64 Proxy Tool - Cloudflare Workers代理工具,支持递归Base64解码、自定义UA和多层编码处理 A Cloudflare Workers-based proxy tool with recursive Base64 decoding, custom User-Agent, and multi-layer encoding support.

swift-openai-responses★ 29

Hand-crafted Swift SDK for the OpenAI Responses API.

cli-agent★ 29

一个极简的 Go HTTP 网关服务,将 HTTP 请求桥接到 Claude CLI。通过 HTTP 接口调用 Claude CLI 的无头模式,让任何支持 HTTP 的应用都能使用 Claude CLI 的能力。

CLASP★ 29

Run Claude Code with any LLM provider — drop-in proxy for OpenAI, Gemini, and more. Go.

pllm★ 29

High-performance LLM Gateway built in Go - OpenAI compatible proxy with multi-provider support, adaptive routing, and enterprise features

PiPiMink★ 29

Route every prompt to the best LLM — for you specifically.

arbr-control-plane★ 29

Open-source LLM control plane: observe every call, recommend savings, then apply only human-approved, reversible routing.

humanasllm★ 29

Human as Agent(人即智能体)· Human-as-LLM 人工代理网关:把工程师变成模型,OpenAI 兼容 /v1 接入 Agent 调度池,涉密/需人工任务路由给真实工程师。为 AI Agent 提效、为平台/运维收集工单。Human-as-LLM Gateway, human-in-the-loop, OpenAI compatible /v1, human-llm model.

GLM_proxy★ 29

we love free stuff. ox alpha . glm-5.3-flash is here!.

infinite-claude-code★ 29

Infinite, 100% Free, Zero-latency Multi-provider AI Router for Claude Code CLI & Desktop with real-time SSE streaming, auto-failover across 51 providers, and Cyber HUD telemetry.

UniLLM★ 28

🦄 Consume any LLM from any provider, using the OpenAI API

OpenAI-GPT-3-API-Wrapper-for-PHP-8★ 28

PHP 8 Wrapper for OpenAI GPT-3 API.

uniai★ 28

AI models all in one!

deerflow-oauth-bridge★ 28

OAuth bridge enabling DeerFlow 2.0 to use ChatGPT Plus/Pro subscriptions via OpenAI Codex OAuth — no API key required

open-next-router★ 28

A lightweight, DSL-driven LLM gateway for routing, patching provider quirks, and normalizing APIs across channels

api-proxy-server★ 28

Self-hosted AI API gateway 鈥?proxy OpenAI / Claude / DeepSeek behind one endpoint; works with Codex CLI / OpenCode / Cherry Studio.

gpt4free★ 28

gradio region:us

codex-reset★ 28

Redeem your Codex banked rate-limit reset from the command line — no UI required.

pi-grok-cli★ 28

Use your X Premium or SuperGrok subscription in pi.

console★ 28

Open-source, self-hosted AI gateway and control plane: OpenAI-compatible LLM routing, RAG, an MCP hub, guardrails and agent tracing for multi-tenant teams.

metapi-go★ 28

MetAPI Go rewrite — meta-layer management and unified proxy for AI API aggregation platforms

SRouter★ 28

Self-hosted LLM gateway in Rust: one OpenAI- and Anthropic-compatible endpoint for Claude, Codex, Qoder, Cline, Grok, Antigravity, CodeBuddy and OpenCode Zen. OAuth token refresh, quota pooling, failover, request logs, React dashboard.

aweswitch★ 28

CLI proxy for switching AI model profiles (Claude Code, Codex, etc.)

gpt-billing-template★ 27

A starter template to write Fastify APIs for OpenAI GPTs with auth, billing and OpenAPI spec generation.

grok2api-pro★ 27

Grok2API(OpenAI 兼容接口):将 Grok Web 调用适配为 OpenAI 风格 API,支持流式对话、图片/视频生成与缓存、代理池与 SSO 绑定、号池并发与自动负载均衡。

stdapi.ai★ 27

Self-hosted AI gateway for Amazon Bedrock. OpenAI, Anthropic, Cohere and Ollama compatible APIs, plus Amazon Polly, Transcribe and Comprehend.

claudex★ 27

Use ChatGPT/Codex OAuth in Claude Code without an API key

tokenrouter★ 27

One OpenAI-compatible endpoint for all your AI providers

llm_proxy★ 27

Self-hosted, Elixir-native alternative to LiteLLM: one API for multi-provider routing, fallbacks, budgets, keys, and observability.

aweswitch★ 27

CLI proxy for switching AI model profiles (Claude Code, Codex, etc.)

bbd2api★ 26

Backboard.io → Claude/OpenAI API proxy with tool calling and thread pooling

ai-function-helper★ 26

Simplify OpenAI API usage with precise response formats, seamlessly integrating AI-generated content into your applications. Make any functions in a second

tokenfirewall★ 26

Scalable LLM cost enforcement middleware for Node.js with budget protection and multi-provider support

More in Agent frameworks & infrastructure