Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 12 of 41

router-core★ 10

Smart LLM router for AI agents — automatic model selection on every request: classify, hard-filter on capability, then rank on task fit, cost, speed and reliability. Deterministic and local, <1ms, no inference call. Powers ClawRouter, Franklin, Hermes and dsh-clawrouter.

gemini-webapi-proxy★ 10

OpenAI-compatible reverse-engineered gateway to Google Gemini Web (chat + image gen). Drop-in base_url for any OpenAI client — no API key needed, reuses your browser login.

backstage-chatgpt-backend★ 10

ChatGPT backend plugin for Backstage. Handles the interaction with OpenAI and exposes an API for the front end plugin

llmdispatch★ 10

Control which LLM handles each task in your app. Swap providers at runtime, fall back on failure, enforce per-user quotas. Framework-agnostic, no proxy.

octohub★ 10

High-performance LLM proxy: one OpenAI-style API over 20+ providers, with multi-tenant keys, full request logging, and usage analytics. Built in Rust.

Fleece-Radar★ 10

🐑 Fleece Radar — 薅羊毛雷达 - Automated radar & passive intelligence pipeline for 200+ Chinese AI gateways and free API relays. Zero-auth model probing, free tier telemetry, and instant OmniRoute upstream exports.

sub2api-state-guard★ 10

Sub2api State Guard:sub2api 插件,为 OpenAI OAuth 账号自建 x-codex-turn-state 算力票池,按模型铸票并在转发时注入,不依赖任何外部服务端

jevcache★ 10

MorrowCache — skip the chat call when the question is the same. OpenAI-compatible proxy. npm: @kushalicious/jevcache

llmrix-router★ 10

High-performance Java LLM router & proxy with intelligent multi-model routing, failover, quota management, and OpenAI-compatible API endpoints.

friendlilink★ 10

For FriendliLink, our integration convenience tool.

omd-dsh★ 10

Multi-mode agent presets for DeepSeek Harness — per-mode model routing + tiered subagent delegation.

SwayRouter★ 10

Open-source AI gateway for routing multiple providers through one unified API.

cortiq-gateway★ 10

Universal LLM gateway with intelligent routing. One OpenAI-compatible endpoint → automatic model selection from your pool (cheap local + expensive hosted) based on the task type and complexity.

codebuddy-cli2api★ 10

Universal cli2api gateway for Tencent CodeBuddy Code — OpenAI/Anthropic/Gemini/Codex formats, multi-key cache-aware rotation, vision, + Hermes Agent plugin. Python stdlib only, zero deps.

dvara★ 10

Open-source AI gateway for LLM calls: OpenAI-compatible, 14 providers, policy, PII redaction, guardrails and a tamper-evident audit log.

zeroroute★ 10

Never pay for LLMs again. ⚡ The $0/mo Multi-Cloud AI Gateway: pool free tiers across Groq, SambaNova, Mistral, Gemini, NVIDIA NIM, Cloudflare & Cohere into one unstoppable, zero-downtime OpenAI-compatible API. Ultra-fast, self-healing, streaming SSE, and RAM cache. Built for founders, startups & indie hackers.

freellmapi-extended★ 10

Free OpenAI-compatible LLM gateway & aggregator — 150+ free models, 15+ providers, health-aware routing + automatic fallback. Self-hosted, MIT.

ai-gateway★ 10

Backend for Brave's AI Services

opencode-jev-router★ 10

Superseded by robertn702/reasoning-router

Viktor2api★ 10

Viktor2api — OpenAI-compatible proxy to Viktor AI for OpenCode

gatewaycrate★ 10

GatewayCrate: self-hosted AI gateway powered by LiteLLM. Unified OpenAI-compatible API for 100+ cloud and local LLM providers. Auto-generated master key, first-start auto-configuration, and persistent data. PostgreSQL enables the admin UI, virtual key management, and spend tracking. Docker deployment on amd64/arm64.

zengate★ 10

Keyless OpenAI-compatible API gateway for OpenCode Zen free models: Chat Completions, Responses, tool calling, vision, key auth by default

webchat-to-api-harness★ 10

OpenAI/Anthropic-compatible API backed by a real webchat session — full file + bash tool calling, so Aider, LiteLLM and Claude Code can drive a session you own.

codex-proxy★ 10

OpenAI-compatible proxy for the Codex (ChatGPT subscription) Responses API

claude-proxy★ 10

Self-hosted multi-account rotating proxy for Claude Code and the Anthropic API - priority-based account rotation, live rate-limit tracking, per-user limits and stats, plus OpenAI/Anthropic-compatible routing gateways.

claudemanager★ 10

Run Claude Code across several Claude Max accounts as if they were one: a local proxy that routes each session to the account with the most headroom and switches before a limit hits

SEAM★ 10

Self-documenting Endpoint Access Mediator - unified secret-injecting proxy gateway

proof★ 10

Claude Code plugin: quit babysitting Claude. Make it check its own work.

BargainProxy★ 10

个人自用的统一模型网关:聚合 Google Antigravity / WorkBuddy / Trae CN / ZCode / AutoClaw / Qoder / OpenCode 免费模型。纯 AI 制作,致敬 agentpoints、AIClient2API、magpie、sub2api、CLIProxyAPI。

dsh-zcode-cli-proxy★ 10

dsh-zcode cli反代 —— 把 ZCode CLI(客户端 agent)接入 DeepSeek Harness:app-server 常驻通道、Start Plan 额度直连、真流式、图片输入、工具委派

Jev-Auto-Router★ 10

Jev Auto Router: turn-pinned model and effort routing for Codex via TypeSafe Jev.

getcheapapi★ 10

Open-source price router for paid data and media APIs: pick the cheapest provider per call, with budget guards for AI agents.

litellm-config-generator★ 9

Fill up the `model_list` field in your LiteLLM proxy configuration file

n8n-g4f-proxy★ 9

LLM-proxy to expose one selected provider from Gpt4Free e.g. MetaAI or ChatGPT into n8n AI Agent as OpenAI compatible LLM

token-scavenger★ 9

A self-hosted LLM router to help you scavenge every free token on Earth

stratarouter★ 9

High-performance semantic router for AI systems with uncertainty-aware routing, model selection, and cognitive depth control.

llm-elasticsearch-cache★ 9

[IMPORTANT: This library is now part of LangChain, follow its official documentation] A caching layer for LLMs that exploits Elasticsearch, fully compatible with LangChain caching, both for chat and embeddings models.

chatgpt-lib★ 9

Simple javascript wrapper for ChatGPT's unofficial web API

chatgpt-secure★ 9

Secure proxy for Chatgpt requests.

nimbus-router★ 9

Nimbus is a zero-dependency local proxy that routes your IDE's AI requests to inference by providing a unified OpenAI-compatible endpoint. Supports multiple providers via the BYOK model.

laravel-openai-api★ 9

Add an OpenAI API and Artisan command easily into your Laravel application.

AnyFoundationModels★ 9

Unified Swift interface for Foundation Models — Ollama, Claude, OpenAI Responses API, and MLX backends via trait-based configuration

openai-billing★ 9

查询 openai 余额 fetch openai billing

kick★ 9

A local OpenAI-compatible proxy for Gemini CLI and Kiro in a native Flutter app

chatgpt-proxy-server★ 9

Enables you to query ChatGPT with a POST request.

gpt★ 9

a cli tool use to send GPT request

qt-openai★ 9

Qt Classes for OpenAI API

StableOpenAI★ 9

StableOpenai is an enhanced framework for OpenAI, providing stable and efficient API request management. It allows the use of multiple API keys to increase request limits and ensures thread safety. The library features multi-key management, thread-safe operations for reliable requests.

anthropic★ 9

Client for the Claude AI models via the Anthropic API

ccs★ 9

One command to switch between Claude API providers for Claude Code CLI

semantic-prompt-cache★ 9

This app leverages Semantic Caching to minimize inference latency and reduce API costs by reusing semantically similar prompt responses.

token-scout★ 9

For OpenClaw, Hermes and more. Find free and low-cost inference (LLM models). Use them directly. Provides both a CLI and MCP server that knows which free-tier LLM APIs exist, which ones you have keys for, and which one fits your task. Returns endpoints so can you call models directly. No proxy, no middleware, no latency tax.

Groq-Unofficial-API★ 9

Welcome to the Groq Unofficial API! This API provides an interface for interacting with Groq's services in a seamless and efficient manner. Whether you're a developer, researcher, or enthusiast, this API empowers you to integrate Groq's capabilities into your applications and projects with ease.

SaasLiteLLM★ 9

Production-ready multi-tenant SaaS wrapper for LiteLLM with job-based cost tracking, credit management, and flexible pricing. Built on LiteLLM.

aigate★ 9

A self-hosted AI platform — inference, tool use, browser automation, image generation, speech synthesis, transcription, object storage, agentic code execution, and more — behind a single OpenAI-compatible endpoint. One docker-compose up.

copilot-proxy★ 9

OpenAI-compatible proxy server for GitHub Copilot

agy-tools-rust★ 9

CLI 版本的 Antigravity API 反代工具,将 Google Cloud Code (Antigravity) 反代为 OpenAI/Claude/Gemini 兼容 API。

kiro-proxy-anthropic★ 9

Anthropic Messages API compatible proxy for Kiro CLI (Amazon CodeWhisperer) — free Claude Opus 4.7, Sonnet 4.6 for Claude Code, Anthropic SDK

llm-env★ 9

Force any OpenAI-compatible or Anthropic API-compatible tool (Claude Code, Qwen Code, Aider, Fabric, Interpreter) to use Gemini, Groq, Cerebras, or Ollama. Pure Bash. Zero dependencies.

mozart-router★ 9

Local orchestration and routing for AI agents — gateway-first, agent-first, integration-first

doubao-free-api★ 9

🌐 Access a free API for AI functions, including chat, image generation, and web search, with easy setup and full OpenAI compatibility.

kiro-proxy★ 9

OpenAI-compatible local proxy for Kiro CLI (Amazon CodeWhisperer) — Claude Opus 4.7, Sonnet 4.6, Haiku, DeepSeek, Qwen, GLM as OpenAI API

go-ai★ 9

A mildly sane inference API library for go

CodexSwitch★ 9

Cross-platform desktop app for switching Codex accounts and OpenAI API profiles on Windows, macOS, and Linux.

codex-switch★ 9

Codex Switch manages AI providers, agents, chat, drawing, sessions, MCP, Skills, vision fallback, and web search on Windows.

Codexbar-win★ 9

A Windows-native tray utility for switching Codex OpenAI accounts and compatible providers without splitting the shared ~/.codex session history.

llm-classifier★ 9

Train and run classifiers that score how hard a prompt is for an LLM to answer.

claude-relay★ 9

Self-hosted, secured HTTP API around headless Claude Code — per-app keys, all tools locked off, zero deps. Use Claude from your own apps.

Warden★ 9

Self-hosted multi-tenant LLM gateway: adaptive routing, multi-agent prompt-injection defense, semantic caching, and a closed-loop cost optimizer. Java 25 · Spring Boot 4 · Spring AI · LangGraph · pgvector · Redis · ONNX · Prometheus · Grafana · Next.js · Docker. Ships a benchmark + a paper.

cursorpipe★ 9

OpenAI-compatible HTTP server wrapping the Cursor Python SDK. Point any OpenAI client at localhost and use Cursor’s frontier models — with streaming, stateful sessions, thinking/reasoning support, and Docker. Works with LangChain, LiteLLM, and Open WebUI out of the box.

LLM-Blender★ 9

gradio region:us

szr★ 9

Go-native cli proxy that reduces token usage

kotro-proxy-engine★ 9

Local coding-agent control plane — MCP action governance + LLM-path protection + cost control. One Rust binary, no SaaS.

llm-gateway★ 9

Inja LLM Gateway — stateless OpenAI/Anthropic API gateway with multi-provider routing and usage hooks.

g4f-bridge★ 9

Provides access to over 250+ models inside claude-code , opencode , codex and more. Free. Unlimited.

Kleros★ 9

An Agentic System that finds free LLM APIs and tokens from the website

claude_api_free★ 9

免费 AI API 服务 | Claude Sonnet 4.5 免费用 | 国内直连无需代理 | 0.39元/刀超低价 | 支持 Cursor/Claude Code 等所有主流工具

WebAItoAPI★ 9

Web AI to API基于 DrissionPage 的 Gemini 网页转 API 接口工具。支持 OpenAI 格式、流式输出、图片上传及 JSON 自动修复。仅供学术研究,严禁商用。

claude-router★ 9

Cut your Claude API bill: local proxy that auto-routes every request to right model. Zero code changes.

aegis★ 9

Turn your Claude subscription into a multi-tenant agent API with rate limits, cost tracking, autonomous objectives, and an admin dashboard. Self-hostable, no API key.

dshelm★ 9

Evidence-backed, explainable multi-model routing for DeepSeek Harness — policy resolution, provenance, and compatibility boundaries.

codex-deepseek-vision★ 9

Codex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Codex. Local proxy turns pasted images and view_image into text via free GLM-4V-Flash or any OpenAI-compatible vision API. No GPU, no Ollama.

cc-swap★ 9

Multi-account and usage manager for Claude Code and OpenAI Codex — switch logins, track quota, auto-rotate before rate limits

cursor-openai-api★ 9

The missing OpenAI-compatible API for calling Cursor models. Point OpenAI clients at Composer models via your Cursor API key

openvidia★ 9

Multi-key proxy for NVIDIA NIM with a native desktop dashboard — auto-rotation, cooldown, RPM limiting, Claude Code + Codex CLI + opencode support. Free-tier keys pooled behind one endpoint.

kiro_proxy_gateway★ 9

🚀 Multi-model AI proxy gateway that converts private APIs (Kiro/AWS Claude) into standard OpenAI & Anthropic compatible interfaces. Async, multi-account, auto-registration. 中文版: 🚀 多模型 AI 代理网关,将 Kiro/AWS Claude 等私有接口统一转换为 OpenAI 和 Anthropic 标准 API。异步架构,多账号管理,元类自动注册。

MiclawApiBridge★ 9

Xposed module: expose Xiaomi Super AI (com.aios.osbot) as local OpenAI-compatible HTTP API

pxpipe-go★ 9

Go port of pxpipe core - cut Claude Code token usage by rendering text context as images

Qwen-Reverse★ 9

Reverse-engineered async Python client for chat.qwen.ai — text chat, streaming with real-time reasoning, tool calling, image and video generation. No official API key required (works anonymously).

codex-router★ 9

本地多模型路由器:让 Codex 桌面端 / Claude Code / 任意 OpenAI 客户端在一个菜单里共用 GPT、DeepSeek、Kimi、GLM、Gemini、Claude、ChatGPT 订阅额度 | Local multi-model router: one menu for GPT + any OpenAI-compatible model, with Claude/Gemini/ChatGPT subscription pools,纯文本模型视觉中继借眼看图

openai-relay-for-cursor★ 9

Use GPT-6 Astra and other Responses-API-only OpenAI models in Cursor's Agent with your own API key. Local relay with embedded ngrok tunnel that translates Cursor's BYOK Chat Completions requests to the OpenAI Responses API and back.

aweshare★ 9

Share local Ollama/vLLM or authorized OpenAI/Anthropic backends through a self-hosted hub — a sharing economy for tokens.

dsh-opencode-free★ 9

Use OpenCode Zen free models in DeepSeek Harness with anonymous access or an optional API key

langertha-knarr★ 9

LLM Proxy with Langfuse Tracing - OpenAI, Anthropic, Ollama format support

ClassifyAI★ 9

AI Service that classifies data with given or passed model structure response to use in code

from-safari-to-api★ 9

Turn Safari web chats (DeepSeek, etc.) into a local OpenAI/Anthropic-compatible API — no API key, no cost. Drop-in for Claude Code / ccswitch.(把 Safari 网页对话(DeepSeek 等)包装成本地 OpenAI/Anthropic 兼容 API —— 不要 API key、不花钱,可直接接入 Claude Code / ccswitch)

codex-provider-switcher★ 9

Keep Codex Desktop conversation history visible when switching subscription and OpenAI-compatible API profiles. Local metadata repair, backups, and private credentials.

Agent2API★ 9

可扩展的多平台 AI Agent 协议网关 · 标准 LLM API、模型路由与统一控制台 · 当前支持 WorkBuddy 国内版与国际版

llmbridge★ 9

A sub-millisecond, drop-in OpenAI-compatible LLM gateway in C++

marvis2api★ 9

将腾讯 Marvis 桌面助手逆向为 OpenAI 兼容网关,离线脱壳设备指纹 uskey,无需启动客户端

More in Agent frameworks & infrastructure