#proxy

OpenAI compatible API on top of the free web clients

High-performance OpenAI & Anthropic compatible API gateway for Qwen with multi-account rotation, interactive TUI dashboard, and resilient tool calling.

Qt/C++ OpenAI-compatible reasoning degradation guard proxy with GUI, CLI, deb and AppImage packaging

Local multi-provider proxy for Claude Code — automatic failover, priority routing, auto-recovery, usage analytics, and a provider catalog

Local proxy so Claude Code and grok-build (Grok CLI) can use Cursor models (Fable), plus Codex, Kimi, and Grok

🦀 Ultra-minimalist, high-resilience LLM routing gateway in Rust. OpenAI-compatible with auto-retry, backoffs, circuit breakers, SIGHUP hot-reloads, and open telemetry. Ideal for free provider surfing.

用住宅 ISP 出口访问 Claude：Clash 全局脚本与 VPS + Mihomo 两种落地

A lightweight local proxy for free AI models, with an OpenAI-compatible API, automatic key rotation, a dark usage dashboard, and one-click Kimi Code setup.

Credential proxy for the AI era — agents use credentials without seeing them

Client-side HTTPS egress proxy for TokenSaver — MITM capture for Claude Code / Cursor / agents.

OpenAI-compatible local API proxy for FreeModels Chat and Cherry Studio.

OpenAI and Anthropic compatible LLM proxy for Ollama Cloud — panel→judge→synth fusion + smart routing, with task-specialized presets for coding, research, and agents.

⚡ OpenAI-compatible proxy with smart routing across 146 free AI models. Zero failures, auto-fallback, admin dashboard, Docker ready. Powered by Puter.js.

给纯文本大模型装上原生视觉：流式真实思考链 · 跨轮次无感重看 · 像素级证据与 SVG 图元 · OpenAI/Anthropic/Responses 三协议兼容 | Native vision for text-only LLMs: streaming real thinking chain, cross-turn re-view, pixel-level evidence & SVG primitives, OpenAI/Anthropic/Responses compatible.

Run-scoped LLM observability control plane backed by LiteLLM

OpenCode AI Proxy Clone 2026 – Free GitHub API Tool for Claude Max Access

OpenAI-compatible jailbreak proxy for Devin SWE-2 (server.codeium.com Connect-RPC) - system-layer override, category framing, invisible retry, RU/EN/ZH refusal handling

Open-source local proxy that strips personal data, machine metadata and location fingerprints out of Claude Code's API requests — before they leave your machine, without breaking any tool. Zero dependencies, MIT.

基于Cursor-byok二次开发的项目，能够正常在Cursor的IDE和CLI中使用自定义模型和Ultra的部分功能，目前仅在Windows进行测试

Monk LLM Gateway: one API in front of every model. An LLM gateway and router built from scratch (proxy, routing, retry/fallback, caching, budgets), with an interactive course.

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

A local proxy for Claude Code: see what every request costs, send chosen work to a local LM Studio model, keep secrets on your machine, and keep working when Claude is down.

A lightweight macOS menu bar proxy for connecting custom model providers to OpenAI Codex.

Unlock DeepSeek V3 and R1 Pro APIs with an OpenAI-compatible wrapper and rotating shared keys. Access powerful DeepSeek models with a simple API setup, flexible integration, and streamlined access for development, testing, and AI-powered applications.

OpenAI-compatible proxy for WorkBuddy AI: use WorkBuddy models from any OpenAI client, no desktop app required.

Use Claude Code with your OpenAI Codex, Kimi, Grok, OpenCode Go or Cursor Agent subscription. Local proxy with a built-in monitor.

A tiny, auditable, self-hosted LLM gateway. One OpenAI-compatible endpoint, deterministic fallback across OpenAI, Anthropic, Gemini, and local models. No database, no dashboard, no control plane.

Go-прокси для Notion AI: пул аккаунтов, авторотация при достижении 80% лимитов, OpenAI- и Anthropic-совместимый API. Один бинарник, SQLite, без CGO. Гейтик просто существует.

Unlock AI Coding with OpenCode Local Provider 2026 - Auto-Detect Ollama LM Studio

Install Claude Code on your machine with one click to use DeepSeek models via domestic mirrors without needing a VPN.

Local-model gateway for Claude Code, Zoo Code, and Kilo: route AI coding agents through llama.cpp/Ollama/vLLM on Distrobox. No API keys, no cloud fallback, nothing auto-starts - local mode either works or fails cleanly. Classic LiteLLM proxy, or the optional single-provider Kilo mode.

OpenAI and Claude API purity checker with no-store local reports

OpenAI-compatible gateway that turns any LLM into a more capable one by fusing it with a reusable fabric of MCP servers.

Self-hosted routing proxy for Claude Code and any Anthropic-format client: nine modes across Anthropic, MiniMax, GLM/z.ai, Qwen and local models. One endpoint, per-chat isolation, no IDE restarts.

Use OpenCode Go/DeepSeek/GPT in Claude Code & Codex CLI. CPA-like proxy with auto format conversion.

Proxy gateway for OpenCode API to use Claude Code natively with OpenCode models.

Ad-subsidised LLM proxy for Claude Code and Codex. Injects one sponsor message on the recap turn; relays every other byte untouched. Written in Nim.

Proxy MCP server for AI agents: generate residential, mobile, datacenter, ISP and IPv6 proxies with country/city/ASN targeting, rotating or sticky sessions, HTTP or SOCKS5 — plus scrape, SERP search, map and crawl through the same pool. 25 tools. npx -y quantumproxies-mcp

A stethoscope for Claude Code: token accounting, raw API traffic capture, and a live web inspector for the agentic loop

A database guardrail proxy: blocks destructive SQL by real blast-radius, not just keyword shape. Freeze mode, tamper-evident audit, MCP-native for AI agents.