Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 10 of 41
🐢⚡ KAME: Key-Aware Management Engine — API Rotation plugin for A0 — Rotating free LLM providers, saves you from 429 errors, rate limits cooldowns, exhausted keys and route around provider outages during long agent runs.
Drop-in OpenAI API proxy for Gonka decentralized inference. Cheap ai model access using gonka.ai inference network. Now supports devshards flow!
A local LLM router with OpenAI and Anthropic format translation, retry and fallback chains
High-performance async Python client for the private DeepSeek API
docker region:us
LLM plugin for Azure AI Foundry with Entra ID authentication
Cross-platform companion for Google Antigravity: Account Switcher, Custom Model Gateway, UI/UX Enhancement, Preview Browser, File Explorer, GitHub Workspace, Token Monitor, and many more features !
Провайдеры ChatGPT для бесплатного использования, преимущественно без регистрации
Google's Bard ChatBot Unofficial NodeJS API
☁️ 通过 Cloudflare Workers 代理 OpenAI API,实现内地正常访问。
🚧 Deprecated 🚧 HuggingChat PHP client (OpenAssistant's LLaMA)
OpenAI API wrapper for Swift
OpenAI-Compatible RESTful APIs for Amazon Bedrock, modified from the original "bedrock-access-gateway" project for not using ALB, so that one could deploy and use it under a pay as you go model WITH NO FIXED COSTS.
OpenAI proxy cloudflare worker
Транслятор запросов к LLM Yandex Cloud из SDK OpenAI
An openAI / LLM API wrapper that simplifies the batching API to reduce costs by 50%
A High-Availability, Transparent, and Smart Multi-Vendor Proxy for Claude Code. Support Claude Plans, GitHub Copilot, Google Antigravity, ZAI/GLM, MiniMax, Qwen, Xiaomi, Kimi, Doubao...
Automate x.ai registration with a web console, batch runner, WARP egress, and grok2api token sink in one project
sigma is a Go package for provider-neutral AI model calls.
Cloudflare Workers gateway for translating and routing OpenAI, Anthropic, Gemini, Bedrock, Azure, Ollama, and other chat APIs.
Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.
Self-hosted, OpenAI-compatible LLM gateway that turns any backend into an agent. Point an OpenAI SDK at it and the model runs tools mid-completion. From web search, code sandbox, document rendering, RAG, MCP connectors all behind a built-in chat UI. Multi-backend routing with health checks + failover, OIDC + RBAC, per-user tokens.
Task-aware reasoning-mode routing for opencode: spec/react/weak three-band agent routing, ported from yjh051108/dsh-routing-suite
Enhanced Sub2API distribution focused on OpenAI/Codex account operations, quota inventory, proxy routing, and upstream compatibility.
Model router for AI coding agents: routes routine work to cheaper models with routing rules, 8 subagents, hooks and a CLI runner
Self-hosted AI gateway in Rust: one OpenAI-, Anthropic-, Gemini- and ElevenLabs-compatible API for chat, images, video, speech and music on every provider, with SSO, roles, budgets, alias routes, request logs, a playground and an MCP portal.
React/Next.js visual dashboard for the OpenClaw AI gateway — every CLI command as a UI page, with speech-to-text everywhere
HTTP proxy for accessing Vertex AI with the REST API interface of ollama or OpenAI. Optionally forwarding requests for other models to ollama. Written in Go.
Delegate hard problems to a more capable advisor model while working with a cheaper, faster model day-to-day
Local proxy that lets Anthropic, Gemini and OpenAI API clients such as Claude Code use Google Cloud Vertex AI.
Local/self-hosted proxy that lets OpenAI-, Anthropic-, and Gemini-compatible clients use models from GitHub Copilot, OpenAI, Anthropic, and custom providers — with priority-based routing and automatic fallback.
OpenAI-compatible Go gateway for Vertex AI Gemini with explicit model routing, live catalog refresh, and Cloud Run setup.
Anthropic/OpenAI-compatible API layer over the Codex API with multi-account routing.
Kiro API Gateway · Anthropic-compatible proxy for Kiro/AWS Q · Multi-account pool · Admin UI · Claude Code compatible
Adaptive GPT-5.6 Sol, Terra, and Luna routing skill for Codex
Per-key smart routing for New API: automatic failover, shared health, self-healing recovery, actual-route billing, and explainable decisions.
Self-hosted AI gateway with a built-in dashboard. OpenAI-compatible API, multi-tenant, sandboxed code execution, MCP integrations, file storage, email, and support for any LLM — OpenAI, Gemini, OpenRouter, or custom.
Automatically loads the best free OpenRouter models into Hermes Agent. Ranks every :free model daily by privacy (optional) and rotates your default and fallback models before they expire so you can set and forget.
Safe local Codex model switching for OpenCode Go models with privacy-safe routing proof.
网页版登录态 → OpenAI 兼容本地反代:DeepSeek / Qwen / Doubao 免费额度驱动 ZCode。Web login → OpenAI-compatible local API.
Run Claude Code through FreeLLMAPI + LiteLLM with Anthropic compatibility, Windows setup guides, troubleshooting, validation tests, and community-driven fixes.
Free GPT/Claude/Mistral via duck.ai — Telegram bot + OpenAI-compatible API (no keys, no browser, pure JS)
Proxy for OpenAI api using python flask, supports SSE streaming.
Open Server is an OpenAI API Compatible Server for generating text, images, embeddings, and storing them in vector databases. It also includes a chat functionality.
Self-host your own API to use ChatGPT for free. Lovelace also provides you with an intuitive multilanguage web application, as well as detailed documentation for using the software. Interact with Ada and implement it in your applications!
A service that enables LLMs without native OpenAI tool calling support to simulate standard OpenAI tool calling, support claude code、roocode、kilocode,etc.
A zig OpenAI API client library
OpenAI 兼容的 API 中转代理平台,支持上游账号池负载均衡、用户管理、额度控制、套餐与兑换码系统
将Aliyun百炼大模型平台的App接口转成OpenAI API接口
OpenAI ChatGPT, GPT-3, GPT-4, DALL·E, Whisper API Client for Crystal
Seamless Integration with Amazon Bedrock for AI-Powered Text and Image Generation in Ruby.
Faster and cheaper! parallel processing of Anthropic API requests, optimizing for speed, cost-efficiency, and rate limit compliance.
Universal Elixir client for LLM APIs. Text generation, tool use, structured output, and decisions.
Open-source AI wallet — your keys never leave your device. 13 providers, 2 lines to integrate, cross-provider translation. Browser extension + iOS + Android.
Using OpenAI ChatGPT / Google Gemini / Anthropic Claude / Amazon Bedrock with WireGuard include tunneling, from an unrestricted region.
MITM proxy for Windsurf IDE — replace the LLM backend with your own Anthropic API key
A lightweight proxy that converts Anuneko services into a standard OpenAI API format. 将 Anuneko 服务转换为标准 OpenAI API 格式的代理服务。
Desktop provider switcher for Claude Code and Codex. Keep every endpoint, API key, and model in one place, switch the active provider in one click, and probe latency before you start. Atomic writes and rolling backups keep your configs safe. Python + Next.js in a native OS webview.
A local gateway that routes Claude Code sessions to OpenAI-compatible and Anthropic-compatible models, with same-session switching and visible compatibility behavior.
Qt/C++ OpenAI-compatible reasoning degradation guard proxy with GUI, CLI, deb and AppImage packaging
Enterprise-grade capability-driven AI routing engine, proxy gateway, MCP server, developer CLI, and agentic skills aggregator for 19+ free-tier AI providers.
Open-source AI gateway for LLM and agent traffic — multi-provider routing, guardrails, semantic caching and MCP support. Written in Go.
Use GPT (ChatGPT Plus/Pro), DeepSeek, Kimi, Grok and 400+ models in the Claude Desktop Code tab and Claude Code while staying signed in to your Claude subscription — no third-party gateway (3P) mode. Several ChatGPT accounts that take over when one runs out; Claude inside Codex too. Not affiliated with Anthropic or OpenAI.
docker region:us
The ops layer for running Claude Code and Codex all day on a Mac: subscription-first routing with overflow to GLM/OpenRouter/Bedrock, pauseless compaction, session coordination and handover across parallel sessions, lid-shut keep-awake with automatic hotspot join for Remote Control, and a dashboard for cost, health and guards.
把 CodeArts Agent(华为云码道)桌面端的上游模型服务复刻成 OpenAI / Anthropic 兼容的 Go 网关 · 复用本机已登录凭据 · 纯标准库零依赖
AI SDK Provider that makes All models (including Codex) from Github Copilot openai compatible
Langchain Gradient Integration
Universal LLM bridge for AI agents. Use Claude Code with MiniMax, Codex with GLM, or Gemini CLI with OpenRouter — one command, any provider. Works with coding agents, OpenClaw, Hermes, and others.
Tiny HTTP proxy that lets OpenClaw (and other third-party agents) route Anthropic /v1/messages through your claude login OAuth session. Avoids the third-party-app rejection, preserves tool-use bridging.
OpenAI APIs in FastAPI application
Self-hosted, OpenAI-compatible AI gateway for organizations — multi-provider (Azure/OpenAI/Anthropic/Gemini), revocable per-allocation credentials, usage & cost tracking, and an OpenAI Codex–ready /v1/responses endpoint.
[ICML2026] The official code of "Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale"
🧠 Intelligent LLM router with ML-based query classification. Route prompts to the right model automatically. OpenAI-compatible, multi-provider, self-hosted.
Local and cloud GPU interference model orchestrator exposing OpenAI-compatible API from different engines
Local multi-provider LLM proxy, model router and control plane for Claude Code, Codex, OpenCode and Gemini CLI: 60 providers, fallback routing, credential health, web search and cost provenance.
把 OpenCode 的免费模型(big-pickle、LongCat、MiMo、Nemotron、Space Bunny 等)接进 DSH 的模型选择器,作为 opencode-xdbridge 分组使用,并在设置 → OpenCode-XD 里提供一个可视化的交互入口。
Interact with Anthropic and Anthropic-compatible chat completion APIs in a simple and elegant way. Supports vision, prompt caching, and more.
Reduce your LLM costs by 40-70% automatically. Routes prompts locally, compacts context, tracks real savings.
A simple framework for using Claude Code or Codex CLI as the frontend to any cloud or local LLM on Apple Silicon. Connect locally via LiteLLM + MLX or LM Studio, or remotely via Z.AI, Gemini/Google AI Studio, DeepSeek, or OpenRouter.
Framework to talk to AI models and intelligently route
Know what your AI agents cost. API gateway with budget enforcement, session tracking, and MCP tools.
Self-hosted LLM gateway that turns flat-rate AI subscriptions (Claude Code Max, ChatGPT Plus, Codex, Copilot, M365, Gemini) into one OpenAI/Anthropic-compatible API. Unified subscription wallet, OAuth passthrough on /v1/responses, prompt-injection + PII defense, MCP server, semantic cache, time-travel replay.
MITM proxy for Claude Code with real-time TUI, web UI & MCP server — intercept, inspect, and send messages to the Anthropic API. Headless mode for automation.
Chrome extension wallet for user-owned AI API access
Self-hosted Rust LLM API gateway with OpenAI-compatible and Anthropic-compatible APIs, model routing, multi-tenant keys, usage tracking, billing, and admin console.
CLI & async Python library for free AI chat, image & video generation.
Local ChatGPT/Codex session adapter for Claude Code, OpenAI-compatible APIs and GPT Image, with a browser admin console.
Wrap the official Antigravity CLI (agy) with OpenAI, Anthropic, Ollama, OpenRouter and any OpenAI ompatible provider support.
Per-turn model routing for the Pi coding agent: a small judge picks the cheap or the strong tier for each message, with multi-model failover, task-level orchestration, and an optional decision-model judge (Jev) that answers with a calibrated probability instead of prose.
MiniMax 反代网关:有头浏览器过滑块批量注册养号 + 账号池自动调度,一键转换为 OpenAI / Anthropic 兼容 API
Claude API国内接入:8个Claude API中转站横评,价格、汇率、缓存、Claude Code兼容性实测对比(2026-11更新)
Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor (GPT or Claude).
Chrome extension wallet for user-owned AI API access
Vendor parameter translation and deterministic JSON repair for DeepSeek Harness: /translate maps temperature/top_p/max_tokens/stop/system across 11 vendors, and the post-execute repair layer (plus fix_json) fixes broken JSON tool output without ever fabricating data
Vercel AI community package for using anthropic through vertex ai.
This example shows how a multitenant service can distribute requests evenly among multiple Azure OpenAI Service instances and manage tokens per minute (TPM) for multiple tenants.
Production-grade LLM client - Rust, Python, TypeScript. 100+ providers, 11,000+ models.
OpenRouter skill for AI agents: model discovery, multimodal chat, tool calling, routing, and starter templates.