Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 15 of 41

github-router★ 5

Power Claude Code, Codex CLI, and more with your Copilot subscription.

FreeHive★ 5

Free, local-first AI gateway — unified API access to Claude, ChatGPT, Gemini & 150+ Arena models. Zero API keys. Drop-in OpenAI/Anthropic compatibility.

skim★ 5

Runtime token proxy + intelligence dashboard for LLM tools. Intercepts API calls, strips waste, tracks costs — for individual developers and Fortune 500 teams.

claudberghini★ 5

Claude Code on Taalas's silicon-baked Llama 3.1 8B (~14,500 tok/s, ~1,000x faster than Opus). A tiny Anthropic-API proxy with tool translation, best-of-N reliability, and a safety guard. 🦞🏎️

solas-billing★ 5

An open-source, Zero-SDK LLM Billing Proxy & Credit Gating layer for AI startups. Intercepts completion requests, counts tokens, manages user credit wallets in SQLite, and provides self-healing model fallbacks

playground★ 5

streamlit region:us

info★ 5

ShuttleAI API Info - FREE GPT-5

crustoxy★ 5

Unlimited coding with Claude Code on ANY LLM. A Blazing-Fast Rust proxy featuring auto-routing and load balancing, API key pooling, and RTK optimization.

blockrun-llm★ 5

Python SDK for BlockRun — every frontier model, pay-per-call with USDC. OpenAI-compatible. Zero rate limits.

pi-llm-go★ 5

Minimal Go LLM client (v1.0, stable). Streaming, strict tool calling, adaptive extended thinking, prompt caching, token counting, cost helpers, retry middleware. Anthropic Claude, OpenAI (GPT-5 + Responses), Google Gemini, OpenAI-compatible hosts.

models-rahmanef-com★ 5

Portable multi-tenant BYOK model registry — auto-updating models.dev catalog plus per-tenant credential resolution behind one resolveModel() call, with host-gated keys. Zero runtime dependencies, ESM, Node ≥22.6. Distilled from openclaw + hermes-agent.

sorai★ 5

[WIP] Sorai is an open-source LLM proxy gateway built for resource efficiency and high performance.

proxiq★ 5

Self-hosted LLM gateway with DLP, SSO, policy enforcement, and full audit trail. Security teams get control. Developers notice nothing.

ai-proxy★ 5

国内直连ChatGPT/Claude/Gemini服务_一步API最全响应最快的大模型中转API

meta-openai★ 5

Yocto meta layer for OpenAI services including ChatGPT.

linguist★ 5

Unified AI model gateway built with Node.js + TypeScript. Accepts multiple API formats and routes to different LLM providers.

llm-proxy★ 5

A robust, transparent REST API proxy service for LLM APIs with profile-based configuration and comprehensive logging.

ghostpour★ 5

GhostPour — Open-source LLM API gateway with auth, multi-provider routing, and subscription-based access control. The invisible hand for your iOS app.

ai-router★ 5

Local-first AI protocol gateway and model router for OpenAI, Anthropic, and Gemini APIs

metis-orchestrator★ 5

Local-first AI orchestration studio. Route every task to the best-suited model, local or cloud. BYO keys or OpenRouter, free.

tokenomics★ 5

Spend model capability like a scarce budget: tiered routing, spec-based handoffs, and a living playbook that carry strategy across sessions. A Claude Code plugin plus a portable method for using context economically, in code and beyond.

grok-proxy★ 5

Expose OpenAI & Anthropic compatible APIs for Grok/xAI,

Open-WebUI-Pipe-OpenRouter★ 5

Access the full OpenRouter catalog (400+ models) — chat, TTS, audio (input + generation), image-generation, video-generation, and embedding models — directly inside Open WebUI, with provider routing, reasoning tokens, streaming, fallbacks, native media rendering, and cache control out of the box.

openvpn-configs-for-ai-services★ 5

Using OpenAI ChatGPT / Google Gemini / Anthropic Claude / Amazon Bedrock with OpenVPN include tunneling, from an unrestricted region.

model-switcher★ 5

Per-prompt model routing and offline cost tracking for Claude Code — keep simple prompts cheap, delegate complex work to a stronger model.

orichum★ 5

Project-aware multi-model harness for Claude Code with account routing, isolated sessions, LeanCTX, and MCP integrations.

codex-auth-broker★ 5

Codex app-server powered auth broker for Pi, Factory Droid, and OpenAI Responses API clients

Nemotron4Free★ 5

Using the API use Nemotron without even needing any account in python

mopass★ 5

🚀 High-performance Java AI Egress Gateway for unified LLM orchestration, quota control, and hybrid-cloud resilience.

Free-LLM★ 5
codexctl★ 5

让第三方中转 API 也能用 Codex 手机 App 等官方原生全部功能:保留 ChatGPT 官方登录态,请求走中转省钱。单文件 exe,双击出界面。

codex-hidden-model-guide★ 5

Codex 隐藏路由模型无限调用指南:启用服务器下发的隐藏模型(如 gpt-5.6-sol-wm)不消耗额度,跨平台 macOS/Linux/Windows,含每小时自动同步脚本

pi-provider★ 5

Provider manager for Pi coding agent — add/edit/test providers with adaptive capability self-check

cache-assembler★ 5

Fixes broken prompt-caching for Claude Code and the Anthropic API - 8.2x cheaper

openrouter-cli★ 5

CLI tool for OpenRouter

claude-provider-manager★ 5

Desktop app to switch Claude Code between any Anthropic-compatible provider (OpenRouter, gateways, local models) in one click. Safe, auto-backup, macOS/Windows/Linux.

AgentRouter★ 5

Guide on integrating AgentRouter API Key in your projects

opencode-bridge★ 5

OpenAI-compatible API bridge for OpenCode — use GitHub Copilot, Anthropic, OpenRouter, Ollama and 75+ providers with any OpenAI-compatible AI client

cursorapi★ 5

CursorAPI: Cursor API key pool gateway - OpenAI/Anthropic dual protocol, tool relay, hot config, OTA updates

llmrix-router★ 5

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

gemini-business★ 5

💎 Automate Google Gemini Business registration, token refresh, and API integration into OpenAI, streamlining your workflow with robust multi-account management.

chutes-agent-toolkit★ 5

One toolkit, every agent — drop decentralized, all-TEE, OpenAI-compatible Chutes.ai inference into Claude, Hermes, OpenClaw, Codex, or any OpenAI-compatible client.

kompact★ 5

LLM context compression proxy — 40-70% token savings, zero code changes

lama-caravan★ 5

LAMA CARAVAN — Local And Multi-backend Adaptive Computation And Routing Across Various AI Nodes. Self-hosted control plane for llama.cpp fleets and AI agents: hybrid local/cloud token routing with queues & schedules, remote server cells, HF model browser, usage accounting. Stdlib Python.

session-warden★ 5

Credits-first router for agent fleets, plus a lifeguard for long Claude Code sessions. If it runs in bash, it can be orchestrated. OpenClaw, Hermes, Claude Code, Codex, Grok.

auto-model-switcher★ 5

Parallel model rotation across any CLI. Auto-discovers models, health-checks in <2s, scores by capability+cost, picks the best for every task.

skillstate-proxy★ 5

Local OpenAI/Anthropic-compatible proxy using structured conversation state to reduce repeated context. Savings and compatibility depend on the workload.

claude-api-hub★ 5

Multi-provider API gateway for routing requests to any LLM — manage providers, aliases, and monitor requests from a web dashboard.

AIFlowBridge★ 5

Multi-provider AI coding assistant with transparent vision proxy, usage metrics, and OpenAI-compatible local gateway.

SwitchAI-Account-Manager★ 5

Desktop account manager & switcher for ChatGPT, OpenAI Codex, and Antigravity / Gemini. Real-time quota tracking, multi-account switching, and encrypted local storage.

proxy-reseller-kit★ 5

Open-source reseller toolkit for the Proxies.sx Pool Gateway — SDK, drop-in React component, and Next.js storefront template

onegw★ 5

Single-binary LLM gateway in Go — OpenAI/Anthropic/Gemini any-to-any translation, fallback combos, token saver, usage tracking, ~100 MB RSS

cursor2api★ 5

Anthropic Messages and OpenAI Chat Completions API for Cursor models (reverse-engineered agent protocol)

CLIProxyAPI-Plus★ 5

CLIProxyAPI Plus:轻量级 AI 编程代理网关,增强 Codex 配额展示、排序与自动停用 / Lightweight AI coding gateway with enhanced Codex quota management

QwenChat2Api★ 5

🚀 Transform your Qwen web chat into OpenAI-compatible API responses with features like token management and multi-modal support.

maxpool★ 5

Multi-account proxy for Claude Code with adaptive, rate-aware load balancing

free-gpt-api★ 5

⚡️ 零 API 账单!基于 OpenAI Prism 的无限 GPT Token 反代服务,直通满血 o1-astra-xhigh / o3 深度思考链,全兼容 OpenAI 接口。

cline-proxy★ 5

High-fidelity Rust gateway for aggregating multiple Cline API keys with Claude Code and OpenAI compatibility

Remote-Convert-Ollama★ 5

轻量级本地 API 网关:将 Ollama/Anthropic 转换为 OpenAI 兼容接口。完美适配 VS Code Copilot、VS2026 与 DeepSeek 思考追踪。 A lightweight local API gateway that converts Ollama/Anthropic API to OpenAI-compatible format. Optimized for VS Code Copilot, VS2026, and DeepSeek reasoning.

codex-connector★ 5

Browser SDK + localhost bridge: let users bring their ChatGPT Codex plan into your web app — no API keys, no server-side AI cost.

openai-register★ 5

自動化 OpenAI 帳號註冊與 AI API 代理管理工具 | Automated OpenAI account registration and AI API proxy management tool

FreeDeepseekAPI★ 5

DeepSeek for free — no subscriptions, no API bills, no middlemen. Private, powerful and ready for your favorite apps and coding agents.

claudehost★ 5

Turn a Claude Code subscription into an OpenAI-compatible API: Self-hosted LiteLLM gateway for chat completions and agentic coding sessions.

free-ai-providers★ 5

Curated analytical benchmark directory, latency scanner, and client config generator for free and trial AI API relays.

tokensaver-cli★ 5

Route Claude Code, Cursor & Codex through the TokenSaver control plane — Zero Trust governance, MCP, Flux IA. Free OSS CLI.

openAdapter★ 5

Self-hosted OpenAI API for Claude.ai via Playwright automation. No API key needed. Works with OpenClaw, Continue.dev, and any OpenAI-compatible tool. Free alternative to Claude API with streaming support.

kiwano★ 5

Local-first AI provider manager — one-click takeover routes Claude Code / Codex through a local gateway with failover, quotas and usage analytics

avo★ 5

Observable AI agent runtime uniting Claude, ChatGPT, and Gemini subscriptions with multi-tier failover down to local Ollama. Replayable SQLite ledger.

paseo-plugin-9router★ 5

Paseo plugin for 9router: accounts, quotas, models and token savers from one local router.

crossfeed-orchestrator★ 5

Route AI coding work across the AI subscriptions you already pay for, with a local console and quota-aware switches.

motty-sdk★ 5

The toolkit for building motties, models made of code, not weights. LLMs are layer 1. A motty is layer 2, below your agents, and to them it is one more model. Inside, it is your TypeScript. It fits the stack you have, as your gateway or beside it.

evolink-mcp★ 5

EvoLink.ai - AI API Gateway

kiro-acp-gateway★ 5

OpenAI- and Anthropic-compatible API gateway for Amazon Kiro's ACP agent, plus a Python ACP client library and CLI.

deep-sol★ 5

Amp plugin pairing GPT-5.6 Sol planning and review with DeepSeek V4 Flash implementation.

triproxy★ 5

A lightweight HTTP gateway written in Go that translates between OpenAI Chat Completions, OpenAI Responses (used by Codex), and Anthropic Messages (used by Claude Code), and forwards requests to any upstream provider.

sinapsai★ 5

Zero-dependency Universal AI Gateway & Smart Router for Node.js/Edge - Circuit Breakers, Semantic Cache, MCP Tool Loop, Reversible PII Vault & 9+ Providers (OpenAI, Claude, Gemini, DeepSeek, Groq, Ollama)

gliner25-decide-llm-routing★ 5

docker region:us

helios-llm-orchestrator★ 5

Local-first MCP multi-LLM orchestrator with task decomposition and benchmark-guided model routing through OpenRouter.

codex-model-router★ 5

Local model router for Codex Desktop: native GPT + DeepSeek, Kimi, Qwen and more, with multi-key quota rotation and free OpenCode Zen models.

claude-code-adapter-fastapi★ 5

一个基于 FastAPI 的轻量代理/适配层:将 Anthropic/Claude 的消息与工具调用请求转换为 OpenAI Chat Completions 兼容格式;智能选择工具定义处理策略(系统提示词 vs 用户消息),根据配置自动优化性能和功能完整性;支持可选的自动工具选择、SSE 流式转发,以及将目标模型响应回转为 Anthropic 格式。仅提供服务端代理,不侵入客户端 SDK。

gpt_web_ui★ 5

Local Anthropic Messages to OpenAI Responses gateway with a web dashboard, per-key quotas, and Claude Code support.

AiRelayAPI★ 5

2026 中转站 高速、稳定、统一的中转站推荐

OmnisRouter★ 5

Open, self-hosted LLM routing proxy: routes each request to the cheapest capable model across Anthropic, OpenAI and Gemini formats, with a per-request receipt proving why. Reproducible routing, BYOK, Apache-2.0.

Freebuff-router★ 5

OpenAI-compatible API gateway for the Freebuff/Codebuff provider.

codex-no-tun★ 5

Use Codex on macOS through a local system proxy without TUN mode

toolcase-gateway★ 5

Zero-dependency Rust HTTP reverse proxy for LLM APIs: tool-name case repair and model failover for OpenAI-compatible endpoints

levogat-ai-api★ 5

Levogat - 国内 AI API 中转站:500+模型(GPT-6/Claude Opus 5/Gemini 3.8/DeepSeek V4/Grok 4.6/Qwen3.8/GLM-5.3/Kimi K3)免翻墙直连,OpenAI兼容,支持Claude Code/Cursor/Codex/Dify。33分组可选,价格表每6小时自动更新。

OpenSub★ 5

OpenAI-compatible proxy for Cursor backed by ChatGPT/Codex OAuth

risu-zai-proxy-archive★ 5

OpenAI-compatible proxy for RisuAI, Codex & Zed — many browser-session and API providers behind one /v1 endpoint (chat/responses).

pi-openai-api-models-sync★ 5

Pi extension that syncs OpenAI-compatible API models and enriches them with Sub2API metadata

gpt4batch★ 5

提供批量调用gpt-4,GPTs接口服务,日调用量支持百万。

ZenRouter★ 5

🌿 ZenRouter: Serene AI Gateway & Intelligent Routing Engine. Connect Claude Code, Codex, Cursor, Cline to 40+ AI providers with RTK token saving, combo fallback & zero-leak streaming.

claude-code-proxy★ 5

Self-hosted Claude Code proxy with usage policy controls.

cognition-claude-proxy★ 5

Use Devin CLI's model catalog (SWE-2, GLM-5.2, DeepSeek, 200+) with Claude Code as the backend

claude-anchor★ 5

Routes Claude Code to the right account per folder, shows rate limits and usage, and continues a conversation on another account. macOS menu bar app, Windows and Linux tray app, and an anchor CLI.

luxury-switchboard★ 5

Desktop-first local gateway for your AI providers: one OpenAI/Anthropic-compatible endpoint, routes, key pools, activity, cost estimates and an optional fail-closed tunnel.

millivolt★ 5

Self-hosted inference proxy for OpenAI-compatible and Anthropic clients. Live dashboard, SQLite history, per-request routing, and operator controls.

gatemux★ 5

Open-source LLM gateway in Go with teams, RBAC, OIDC and budgets built in — not an enterprise upsell. OpenAI-compatible API, virtual keys, rate limits, routing and fallback, and an admin console.

claude-desktop-gateway★ 5

Run Claude Desktop on OpenRouter, OpenCode/Zen, or ChatGPT Codex OAuth backends via a local third-party inference gateway.

ToRouter★ 5

Local-first AI model router & gateway for individuals. Single portable EXE, loss-free multi-protocol translation, smart transparent failover, tag-based policy firewall, dual-metric valuation ledger, native MCP hub & desktop pet.

More in Agent frameworks & infrastructure