Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 16 of 41

limitbreak★ 5

Use several Claude accounts from one Claude Code install; switches automatically when a usage limit is hit, no restart. MIT.

EdgeRelay★ 5

部署在 Cloudflare 边缘的AI API 网关,用统一 OpenAI 兼容接口接入、路由和派发多家大模型服务。

flarum-ai★ 5

Connect Flarum to OpenAI, Anthropic, Gemini or any OpenAI-compatible API, for other extensions to generate text with.

vertex-openai-proxy★ 5

A blazing-fast local proxy that bridges OpenAI coding agents to Google Vertex AI. Claim your $300 free setup credits and code with Gemini 3.1 Pro inside VS Code (Cline, Cursor, Kilo) for free.

dsh-set-model★ 5

Through Jev or through its own tool calls, the agent switches model presets and thinking depth on its own. A DeepSeek Harness plugin: set_model/list_models and switch_preset/list_presets behind independent switches, Jev auto-switching, Plan Mode staging, and a Web settings page.

switchyard★ 5

Switchya: a local coding workspace (desktop app + CLI) for the model providers you choose, powered by Switchyard Gateway, a self-hosted Rust LLM API gateway for OpenAI, Anthropic and Gemini protocols

cc-model-router★ 5

Route Claude Code tasks to Haiku, Sonnet or Opus by task type, with a 48-run cost/quality benchmark, verification and escalation. MIT, no proxy, no telemetry.

claude-router★ 5

Route each Claude Code task to the cheapest Claude model tier that can do it well — via model-pinned subagents.

Neko-Router★ 5

High-performance, ultra-low overhead headless AI Gateway & Router designed for OpenAI and Anthropic compatible endpoints.

tsm-hub★ 5

AI Capability Hub & LLM Gateway - unify models, tools, skills, MCPs, sandbox, memory with discovery and promotion across 13+ providers

portunus★ 5

One endpoint for every LLM — multi-channel routing, protocol translation, and usage logging.

modelwharf★ 5

模型码头 modelwharf — 把 workbuddy/trae/qwen/qoder 与 24 家官方 API 停泊到同一处,统一成 OpenAI / Anthropic / MCP 协议的本地网关,自带管理面板

workbuddy-claude-bridge★ 5

把 WorkBuddy(腾讯 CodeBuddy)账号额度接入 Claude Code / Claude 桌面端:零依赖本地反代网关 + 含 16 条真机排障记录的安装向导

kingjboy-claude-code★ 5

Personal fork of free-claude-code: a Chrome side panel for the proxy, credential pooling, measured context windows, and a curated model list

claude-pool★ 5

Transparent rate-limit failover for Claude Code teams. Pool API keys across your team — when one teammate hits a 429, the next request silently borrows an idle key and the session keeps going.

qoder-to-dsh★ 5

把 Qoder 的模型额度原生接进 DeepSeek Harness 的纯 dsh 插件

aigate★ 5
new-api★ 5

Backend powering unorouter.com. Unified AI gateway aggregating 12+ providers with billing, channel routing, and OpenAI/Claude/Gemini compatible relay.

awesome-ai-api-hub★ 5

🔌 精选 AI API 中转站 / 聚合网关 / 导航比价站合集 —— 一个 Key 打通 GPT、Claude、Gemini、DeepSeek 与国产大模型

dots-bridge★ 5

Use OpenAI dots from your own apps: a bridge with a Python client and an OpenAI-compatible API.

agent-cockpit★ 5

国内 AI Agent 多开 / 换号 / 额度过期提醒 / API Key 台账 / 本地反代 一体化桌面工具(Tauri 2 + Rust)

AgentCompass★ 5

Deterministic multi-agent task router & subscription quota scheduler for Claude Code, Codex, Agy CLI (Antigravity), Grok, and Paseo. Routes sub-agents by model DNA, ability floor, and 5h/7d rate-limit windows with a PreToolUse spawn gate.

kronaxis-router★ 4

OpenAI-compatible LLM proxy in Go: cost-optimised routing, response caching, batch API, RAG pre-stage (pgvector + sentence-transformers), agent-gateway sub-service for CLI agents (Claude Code/Anthropic SDK/Gemini CLI)

deepcode-v4★ 4

Unlock Claude Code with DeepSeek V4. Get Anthropic's agent tools with 95% lower costs and local vision.

GetFreeChat★ 4

Automatic collection of free instances of AI text models (ChatGPT, Claude, llama and others)

httpxr★ 4

⚡ A 1:1 Rust port of httpx — same API, faster. Zero dependencies.

Claude-Agent★ 4

An AI model interface service, support for large language models includes Claude, Gemini, Mistral, PaML, Llama, CodeBison, etc.

Smart-Routing-Butler-for-OpenClaws★ 4

One interface, every model at your command. Your local AI routing butler. | 一个接口,万模随心。你的本地 AI 智能路由管家。 | Built for OpenClaw & AI agents.

multi_llm★ 4

A cost-aware, multi-LLM routing agent using Gemini as the default and external models on demand.

local-llm-server★ 4

Autonomous AI Agent Infrastructure Platform — OpenAI-compatible AI gateway with MCP support, multi-agent orchestration, tool calling, observability, memory, RAG, AI workflows, and unified infrastructure for any LLM provider.

routesmith★ 4

Host-aware model routing for coding agents. Python library + MCP server for Claude Code, Codex, Gemini CLI, Copilot, Cursor, and Aider.

ai-sdk-provider★ 4

A Vercel AI SDK provider for Helicone, enabling seamless integration with Helicone's AI gateway and observability platform.

langchain-fused-models★ 4

Unified multi-provider ChatModel manager for LangChain. Supports routing, rate limits, fallbacks, and structured output across multiple LLMs.

a3m-router★ 4

🔀 One prompt in. The right model out. Open-source LLM router with 100% routing accuracy, 47+ providers. Budget enforcement, semantic cache, intelligent failover. Zero ML, 19.5KB. MIT.

openclaw-provider-manager★ 4

OpenClaw Skill: AI模型供应商管理器 - 自动发现模型、追踪额度、多Agent共享状态、额度用完自动切换

openrouter-api-go★ 4

openrouter api integration in golang

ChatGPT_RestAPI★ 4

ChatGPT integration via RestAPI

ChatGPT-API★ 4

A lightweight ASP.NET Core API for ChatGPT/OpenAI. Supports requests for chat, completions and moderation

NolimitAI★ 4

This ia a libary to python(pip) and typscript(npm) with a inteligent router for multiple providers of LLMs

ChatGpt_Conection_Python★ 4

Conexion rapida a chat gpt sin key, configurable

ga★ 4

A lightweight middleware for service-oriented architecture

SUSTAIN★ 4

SUSTAIN is an environmentally-friendly, token-optimized AI wrapper designed to reduce compute costs and increase productivity.

rsazure-openai-toolkit★ 4

A fast, secure, and auditable toolkit to integrate with Azure OpenAI — with a friendly CLI and dev-first architecture.

one-router★ 4

Unified LLM API router — route OpenAI & Anthropic protocols to Bedrock, Gemini, and more

anyresponses★ 4

The Universal Gateway making every model speak the Open Responses standard.

openai-go★ 4

OpenAI API wrapper for golang

ccswitch-terminal★ 4

在终端中一键切换并管理 Claude Code、Codex CLI、Gemini CLI、OpenCode、OpenClaw 的 provider 与 API Key,适合服务器、CI/CD 等无 GUI 环境

budgetguard-core★ 4

A FinOps control plane for AI APIs - Drop-in API gateway that enforces hard budgets, rate limits, and custom policy checks before any request reaches AI providers. Stop surprise AI bills with multi-tenant budget controls, complete audit trails, and sub-20ms latency overhead

llm-api-rs★ 4

A Rust library unifying multiple LLM providers

glide★ 4

🪂 Latency-aware model cascade for agentic LLM workflows. Auto-switches to a faster model when yours is slow.

llm_optimizer★ 4

Smart gateway for LLM calls in Ruby/Rails. Semantic cache (Redis + cosine similarity), model router, stop word compressor, and sliding window history manager.

kaizen-sdk★ 4

Open source client SDKs to Save AI cost via Kaizen AI Cost Optimization Infrastructure.

ProxyMe★ 4

Local AI Proxy Management Plugin for JetBrains Rider IDE - Configure multiple AI models, control which models are available, and manage API keys securely

claude-code-api-wrapper★ 4

Bridge Claude Code CLI to a REST API. Leverage your Claude Pro/Max subscription as a free API with FastAPI, featuring a built-in Web UI and multi-directory support.

unigateway★ 4

Lightweight, local-first LLM gateway for developers. A stable, single-binary unified entry point for all your AI tools and models.

claude-max-proxy★ 4

Drop-in fix for OpenClaw — route agents through Claude Code CLI on your Max subscription. No API key, no per-token billing.

llm-web-relay★ 4

A FastAPI gateway for local LLMs that adds intelligent web research, multilingual recency/how-to detection, time-anchored guidance, context injection, and OpenAI-compatible SSE streaming. Turn any local model into a recency-aware, context-enhanced assistant instantly.

onekey-agent-router★ 4

AI Agent OneKey Router Route any AI agent request to the right skill with a single API via Free Tier or Discounted APIs.

PlugMyAI★ 4

Plug your AI provider / local AI to any apps (macOS)

21pins★ 4

Local-first key custody and policy routing for AI apps. Set keys once, route across providers through one OpenAI-compatible endpoint.

llm-gateway★ 4

Multi-provider LLM gateway with automatic fallback and cost tracking. Single API across DeepSeek, Gemini, OpenAI, and Anthropic.

claude-api-cost-optimization★ 4

💰 Optimize your Claude API usage to save 50-90% on costs with batching techniques and efficient request management.

llm-adapter★ 4

UniversalLLMAdapter class initializes the appropriate client based on the specified provider.

ferrolabs-python-sdk★ 4

Ferro Labs AI Gateway Python SDK - Instrument your LLM app, Works with any LLM or framework

hermes★ 4

A universal, highly intelligent LLM API proxy gateway. Seamlessly translates heterogeneous AI protocols (OpenAI, Anthropic, Gemini) with built-in multi-account rotation, circuit breaking, and zero-config deployment.

jetbrains-ai-gemini-local-proxy★ 4

Fix the JetBrains AI Assistant + Google Gemini "Something went wrong" error. A zero-buffer FastAPI + httpx proxy for the OpenAI-compatible (BYOK) provider: strips IntelliJ's model-id prefixes, returns a clean /models list, filters unsupported params, and disables Gemini 2.5 thinking to beat the commit-message streaming timeout.

openai-node★ 4

Openai & ChatGPT Node.js Rest Api

ccNexus★ 4

Smart API endpoint rotation proxy and local API provider for Codex CLI/GUI, Claude Code CLI/GUI, Hermes Agent CLI/GUI, and OpenClaw

openai-api-proxy★ 4

Proxy for the OpenAI API that keeps track of tokens and cost

AI-as-a-Service★ 4

An API for managing chat completions, fine-tuning, payments, plans, and configurations.

phantom-mock★ 4

An AI API platform

IRIS_project★ 4

IRIS — Integrated Runtime Intelligence Service. Multi-provider AI router with MCP server (13 tools), 16 providers (5 native + 11 OpenAI-compatible registry), council fan-out, batch APIs, circuit breakers, mTLS, mDNS, audit log, Prometheus metrics, 'iris provider add' CLI for any custom API.

ccs★ 4

Tiny Claude Code provider switcher for Anthropic-compatible endpoints. Homebrew, DeepSeek/OpenRouter presets, no proxy or daemon.

tessera-sdk★ 4

Drop-in LLM cost-optimization proxy. Auto-route + cache + compress + batch. Flat monthly pricing by token volume, keep 100% of savings. Free 60M tokens/mo.

NakshGuard★ 4

On-premises proxy that catches runaway AI agent loops before they drain your API budget

llm-fallback-router★ 4

Never get a 503 from your AI again. Intelligent routing, automatic failover, latency-aware selection, and cost-controlled fallback across every major LLM provider.

openrouter-go★ 4

A zero-dependency Go client library for the OpenRouter API with full streaming support, comprehensive error handling, and complete API coverage including chat completions, tool calling, structured outputs, and web search.

ai-rate-limiter★ 4

Universal, drop-in rate limiter, quota manager, and cost tracker for any LLM API — OpenAI, Claude, Gemini, Mistral, and more.

suture-stream-repair★ 4

Ultra-low-latency reverse proxy that repairs truncated & malformed JSON in LLM streaming responses (OpenAI, Anthropic, Vertex AI, Bedrock) — fixes JSONDecodeError / serde_json EOF on truncated tool calls.

asq★ 4

Ask LLM a question with selected prompt

agents-gateway★ 4

Production-ready FastAPI + Agno gateway for serving AI agents — agents, teams, supervisor execution, skills, knowledge bases, OAuth tokens, toolkits, OpenTelemetry.

agent-gateway-hub★ 4

🚀 Opendray v2 2026 – Universal AI Agent Gateway (Slack, Telegram, Discord, DingTalk)

free-gpt35★ 4

docker region:us

GPT4Free★ 4

gradio region:us

CostMarshal★ 4

Cost-aware multi-model orchestration for Codex CLI: route hard work to strong agents, replay proven paths with cheaper agents, and track cost, memory, and project evolution.

agent-voir★ 4

AgentVoir is an open-source enterprise AI agent registry, LLM gateway, model proxy, semantic cache, and governance control plane for agentic AI systems.

ErisPulse-OpenAI★ 4

A unified OpenAI API wrapper module for ErisPulse | OpenAI 通用接口封装模块

deepinfra★ 4

Lightweight OpenAI/OLLaMA/GenAI compatible caller, originally designed for DeepInfra.

claude-proxy★ 4

Use Claude Code with ChatGPT/Codex, OpenAI, GitHub Copilot, Gemini, OpenRouter, Anthropic, or custom backends. A single-binary Rust gateway with OAuth, smart model routing, virtual 1M context, and built-in TUI observability.

claude-p★ 4

OpenAI-compatible API server wrapping Claude Code in headless mode. Use Claude via any OpenAI client.

hapax★ 4

The reliability layer between your code and LLM providers. Hapax is a production-ready AI infrastructure layer that ensures uninterrupted AI operations through intelligent provider management and automatic failover. It is designed to address common challenges in managing AI infrastructure

Alayra-Nexus★ 4

Open-source AI gateway and operations platform. Bring your own provider API keys and unify every AI model behind a single OpenAI-compatible endpoint with production-ready routing, analytics, backups, restore, clustering, team management, and enterprise-grade operational tooling. Self-host in minutes or run with Nexus Cloud. To follow on X: https://x.com/alayranexus

AIRelays★ 4

Independent OpenAI-compatible local relay for your own ChatGPT and Claude subscriptions: one standard /v1 API (chat completions, responses), multi-account balancing with automatic failover and retry, and a cross-platform desktop app. Single-user personal use; not affiliated with any provider.

Luna★ 4

Stop paying for API credits twice. Luna bridges your existing premium AI subscriptions apps into a seamless, OpenAI compatible local gateway

corp-llm-gateway★ 4

Corporate LLM gateway. Sanitizes traffic between developer Claude Code instances and Anthropic/OpenAI before it leaves the corp boundary.

OninOneProxy★ 4

Self-hosted AI gateway & LLM proxy: zero-downtime failover, MOA Fusion, token-saving compression. One OpenAI-compatible endpoint for Claude Code, Cursor, Codex, Cline + 40+ providers.

BatchLLM★ 4

Batch processing for LLM APIs - CSV/JSONL in, processed out. Concurrent requests, retries, checkpointing, cost tracking.

openai-promo-bypass★ 4

An easy-to-use GUI application to safely bypass regional restrictions for OpenAI/ChatGPT Promos using built-in SSH tunneling.

vision-relay★ 4

Vision Relay 是一个本地桌面客户端式的多接口 AI 模型中转工具。

aiplug★ 4

A lightweight runtime that unifies 490+ AI providers behind a single, OpenAI-compatible API.

More in Agent frameworks & infrastructure