Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 13 of 41
Claude Pro/Max OAuth model provider for DeepSeek Harness with Google/Gmail login in Settings, auto-token refresh, live model discovery, and real-time quota tracking
Token 超支?快给史密斯打电话! Better Call Smith. Adaptive model routing, a glassy Codex usage monitor, and reproducible benchmarks with receipts.
白嫖免费大模型 API 合集|10 个免魔法、免绑卡、OpenAI 兼容的公益接口(DeepSeek / Qwen / GLM / Gemini / 商汤),含 Base URL、每日额度与实测评价。Free LLM API list — no VPN, no credit card required.
Personal LLM gateway for saving expensive tokens
Grok Bot BYOK (Bring Your Own Key) inference adapter. Route Grok Bot's AI inference through your own LLM API keys with automatic failover, latency-based routing, and circuit breaking.
Multi-site AI gateway and control plane — unified routing across OpenAI, Anthropic, Codex, Grok, Gemini and more, with protocol conversion, OAuth orchestration, cost tracking, and real-time traffic observability
Self-hosted gateway that turns Muse web capabilities into an OpenAI-compatible API, with a React admin console.
Get balances of your openai key.
The Requesty integration package for the Vercel AI SDK.
chatkore为开发者提供优质稳定的OpenAI相关的API调用接口,方便国内用户使用各类开源ChatGPT项目或者AI领域的库的使用。
ChatGPTWebService is an API application that allows users to access the chatbot functionality of ChatGPT using a given API key. Written in C# and built with the latest version of the .NET framework, ChatGPTWebService allows developers to integrate ChatGPT's natural language processing capabilities into their own chatbot applications.
Simple backend proxy API to handle requests between your macOS SwiftUI app and the Mistral AI API (or another third-party AI API)
openAI/chatGpt 用户名、密码授权登录 jar 包封装
Using GitHub Copilot API like OpenAI API.
Implement Open AI API using Firebase Functions
Universal gateway for Generative AI providers (WIP)
A CLI to query AI model capabilities, context limits, and pricing from PublicProviderConf.
起夜级 OpenAI API 反向代理与负载均衡灵车
A simple wrapper for the OpenAI REST API written in pure Golang.
Self-hosted LLM proxy, tracing, cost tracking, and routing in one Go binary. Apache 2.0 proxy core. BSL 1.1 full platform.
OpenAI PHP API Client
This code example is a FastAPI server that contains multiple API endpoints for interacting with an OpenAI model.
基于 oaifree 的GPT私人拼车实现
Practical use of Azure API Management's AI Gateway to manage Azure OpenAI operations.
Make OpenAI batch easy to use.
Docker image for a self-hosted LiteLLM AI gateway proxy. Unified OpenAI-compatible API for 100+ LLM providers. Features auto-config on first start, virtual key management, spend tracking, and persistent data via Docker volume.
基于 Electron 的 AI API HTTPS 代理。通过 SNI 动态证书 + Hosts 劫持拦截 OpenAI/Anthropic/Gemini 流量,支持路由转发与模型名称自动映射。支持Trae等应用
Drop-in AI gateway. Route any coding agent through any LLM provider. Auto-failover, Anthropic<->OpenAI format conversion, 15 PII guardrails, multi-tenancy, multiple subscription support.
High-performance, multi-provider LLM SDK for Go. Unified access to OpenAI, Anthropic, Gemini, Ollama, OpenRouter with adaptive rate limiting and concurrency control.
Extremely Lightweight Antigravity-Claude-Proxy
Minimal Rust SDK port of LiteLLM – unified async client for OpenAI, Anthropic, Gemini, and xAI
An AZD template to deploy LiteLLM, open-source Python AI LLM Proxy API with support of 100+ LLMs, to Azure Container Apps with Azure Database for PostgreSQL.
A single-binary proxy that lets Claude Code drive OpenAI-compatible backends.
Unofficial ChatGPT Puppeteer API: A lightweight Node.js/Express backend that automates the ChatGPT web interface—with persistent sessions, conversation threading, and “Reason” & “Search” modes—via Puppeteer.
LLM plugin providing access to AI models through 1min.ai API with web search, mixed context, and persistent options
⚡ Intelligent routing layer that auto-selects the right LoRA adapter for each task in your local LLM agent loop.
CLI tool to manage AI provider configs for Claude Code (and more). Switch between API providers with one command, auto backup, atomic write.
Fixes Codex registration failures by restoring OpenAI OAuth, workspace, and token flow in codex-manager-based tooling
Reliability control for the Anthropic Python SDK
Self-hosted AI gateway for agents — route providers, virtual models, limits, and usage from one console.
Lightweight Python client for DuckDuckGo's AI Chat API (unofficial duck.ai). Supports GPT-4o, Claude, LLaMA, Mixtral & more. Fast, minimal, production-ready.
Developer infrastructure for discovering and comparing LLM models and providers
Lightweight OpenAI-compatible proxy for OpenRouter's free models. Automatically routes to the best available free (privacy-first) model with seamless failover.
已停止维护。推荐改用 yetone/magpie:装好即用,把 ChatGPT / Claude / Copilot 订阅共享给 DSH 等所有工具
Reusable starter kit for routing Hermes Agent through a local LiteLLM-based free/free-tier model router with clean aliases, fallback examples, systemd service templates, and terminal-first setup.
OpenAI-compatible API server powered by the GitHub Copilot SDK. It exposes the classic OpenAI endpoints so you can use standard OpenAI clients (including the official Python OpenAI SDK) against a local Copilot-backed proxy.
低价中转api_中转api为什么便宜_为什么AI中转站价格会便宜_Api中转平台_中转api推荐,推荐低价Chatgpt中转api_Openaiapi中转_Gemini中转api_Claude中转api
Access DeepSeek V3 and R1 Pro API without limits via shared API key rotation.
GenPark AI Agent Skill - Multi-tier model cascading router dynamically selecting optimal models (e.g. Small vs Medium vs Large) based on task complexity, cost budgets, and SLA constraints.
封装为本地 OpenAI/Anthropic 兼容 API 的 Android 原生实现 · 无需 Python/Docker,装到手机即用 · Kotlin + 原生 HTTP 服务 + SQLite
Prism is a modern multi-model AI gateway and subscription platform with an OpenAI-compatible API, model marketplace, tool use, quota windows, billing, admin console, file parsing, web search, and PWA/Tauri clients.
A transparent same-protocol LLM proxy that routes cheap tasks to Flash and hard ones to Pro by structural signals — no keyword guessing.
OpenAI-compatible API gateway for your Cursor subscription. Point any OpenAI client at it — streaming, tool calling, sessions, 80+ models. Self-hosted, with web dashboard, CLI, autostart & Hermes Agent addon.
Reasoning layer for the official DeepSeek Harness: every request stays on native max effort, with isolated Flash/Vision/Pro depth controls, stability axes and reasoning toolboxes built above it. Delivered build only; commercial use open, reverse/modify/extract closed.
OpenAI-compatible local media bridge and model-scoped reasoning/structured-output compatibility proxy.
Self-hosted AI gateway: model-level failover, inspectable routing, private API keys, tenant isolation and a model lab. Docker and lightweight native desktop apps.
Cross-vendor AI consultation CLI: query up to 11 models in parallel and receive a source-attributed union of distinct findings for design reviews, threat modeling, and risk analysis.
Use free OpenCode models inside Codex. Paste one prompt, Codex installs the bridge, reopen the app and pick the model from the menu.
ClawCut-MLX Proxy - A high-performance bridge between OpenClaw and LLM.
AI Gateway for multi-LLM orchestration with cost optimization and MCP integration
Multiple account support and automatic failover for GitHub Copilot in OpenCode.
Self-hosted AI control plane for intelligent local LLM orchestration. OpenAI-compatible API · ML-powered multi-model routing · LoRA finetuning · vector memory · RAG
The Universal LLM Gateway - Integrate ANY AI Model with One Consistent API
pwshBedrock is a PowerShell module designed to simplify interaction with Amazon Bedrock foundation models. It enables users to send messages, retrieve responses, manage conversation contexts, generate images and videos, and estimate costs. Supporting both InvokeModel and Converse API, it streamlines AI integration in PowerShell workflows.
A TypeScript library for easily interacting with various Large Language Model providers through a unified interface.
Single file PHP + Curl class to send a single chat request to OpenAI, Anthropic, Gemini, or ollama.
Lightweight AI inference gateway - local model registry & parameter transformer (Python SDK) - with optional Envoy proxy processor and FastAPI registry server deployment options.
A rust optillm port, for use with just-ever/code (or at least my fork of it)
Multi-backend AI CLI & OpenAI-compatible API server (Claude, Codex, Gemini)
A gamified, single-binary LLM gateway for small teams to pool API quotas, featuring a built-in point economy and a neoclassical UI.
数游AI平台为您聚合了包括OpenAI、Google、Anthropic、Grok、DeepSeek、通义千问在内的众多前沿大模型。无论您面临智能对话、AI绘画还是视频生成的复杂需求,我们都能为您提供全方位、持续进化的智能创作服务。
Use Hermes Agent (NousResearch) with Crazyrouter — 600+ AI models, 30-50% cheaper than OpenRouter
an llm provider gateway in rust, fully rig compatible
LLM Foundation for TYPO3 - Shared AI foundation: configure LLM providers once for every AI extension, with encrypted API keys and services for chat, translation, vision and embeddings.
Self-hosted spend firewall and gateway for LLM ( OpenAI / Anthropic / Gemini ). Hard per-user & per-project budget caps that block runaway costs before the API call, plus cost-per-customer tracking, semantic caching, and failover. One line of code, single Go binary.
Local OpenAI- and Anthropic-compatible API gateway backed by Codex OAuth.
Open-source AI Gateway, all enterprise features included.
The open standard AI gateway — PII protection, audit, reliability & cost control as composable interceptors. Same API in Python, Java & JavaScript.
⚡Switch LLM providers for any agent/app with one click: A single-binary LLM gateway with auto API translation and traffic inspection
Protocol-faithful, multi-provider AI gateway for OpenAI, Anthropic, Gemini, and OpenAI-compatible APIs — native wire types, streaming SSE, zero lowest-common-denominator abstractions.
Self-hosted family AI gateway with parental controls. Runs on Linux, macOS, and Android (Termux) — Raspberry Pi, mini PC, old laptop, homelab server, even a phone. Telegram, Discord, web. Privacy-first, works with any LLM (local or cloud), OPA content filtering, MCP skill scanning.
Go proxy enabling Cursor to use DeepSeek V4 (Pro/Flash) via OpenAI-compatible API. Supports zero-config thinking mode and multi-turn reasoning_content bridging.
Single-binary LLM gateway (gw) in Rust — OpenAI/Anthropic-compatible APIs, multi-provider routing, per-key auth/quotas/rate-limits, failover, streaming, and a billing ledger
Hub unificado para múltiplos modelos de IA com API compatível OpenAI, chat integrado e gerenciamento de credenciais
Self-hosted AI gateway. Route, translate and track requests across providers, with access keys, budgets, and a built-in dashboard.
Ferrox - High-performance, stateless LLM API gateway written in Rust. Sits in front of LLM provider APIs (Anthropic, OpenAI, Google Gemini, AWS Bedrock) and exposes a single OpenAI-compatible HTTP API surface. Inspired by nginx/envoy proxy design — stateless, lock-free, horizontally scalable.
Desktop client for the Asale token-sharing network: sell idle Claude, ChatGPT/Codex, Gemini, Kimi and Grok subscription quota for USDT, or buy capacity the moment you hit a rate limit.
Switch models, not context. Terminal agent host that routes each prompt between a cheap primary and a deep escalation agent (local, Bedrock, Claude Code, aider, …) with full context handoff — plus tools, MCP, multi-agent workflows, persistent memory, loop detection, and milk eval.
Fail over Claude Code and Codex across subscriptions, API keys, and third-party providers; wait through quota resets; teleport sessions between harnesses.
A transparent same-protocol LLM proxy that routes cheap tasks to Flash and hard ones to Pro by structural signals — no keyword guessing.
Share local Ollama/vLLM or authorized OpenAI/Anthropic backends through a self-hosted hub — a sharing economy for tokens.
An AaaS platform and Agent Gateway with cross-platform clients. You can also use it as a client for Claude Code, Codex, and Pi.
Protocol-faithful, multi-provider AI gateway for OpenAI, Anthropic, Gemini, and OpenAI-compatible APIs — native wire types, streaming SSE, zero lowest-common-denominator abstractions.
Enterprise Cloud FinOps & Multi-Model LLM Inference Cost Governor. Monitors tenant token burn rates across Tencent Cloud and multi-model runtimes, routes queries across Flash-Lite, Flash, and Pro reasoning tiers based on task complexity and | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550
Dynamic Cognitive Load, Latency & Token Budget Router. Monitors running agent loops, estimates token consumption and monetary cost, prunes verbose thinking chains when nearing limits, and routes sub-tasks between fast/cheap models and deep reasoning engines.
Akhub —— AI 协议网关与组内负载均衡:Chat Completions / Responses / Messages 互转、严格优先级调度与失败切换
给 Agent 用的本地通道:CLI + 本地面板双壳共享 sing-box 内核,Python 标准库零依赖,只监听 127.0.0.1
Sinuo — AI 编程工具的本地网关:Claude / OpenAI 请求转发、端点故障转移、请求追踪、Codex 账号池
Command Code for DSH|订阅接入:将 Go / GOAT / Pro / Max 订阅接入 DeepSeek Harness,支持模型同步、推理预设、用量提醒和联网搜索。
Model-delegation router for Claude Code and Codex: lookups, checks and test runs go to cheaper models; savings show in the statusline.