Havuz

Drop-in OpenAI-compatible cache that replays repeated computer-use and agent workflows at near-zero cost.

A PostgreSQL proxy that keeps each user's data in their own region. Shards by a key you name, splits reads from writes, pools connections, a

SEPCC — A Claude Code proxy with context that survives. Route Claude Code through 17+ providers, resume sessions across restarts, and never

SunnyNet WPF 是基于 SunnyNet Go 核心的 Windows 抓包分析工具，使用 C# + WPF 重绘界面，支持 HTTP/HTTPS、WebSocket、TCP/UDP、断点拦截、重放、请求规则、请求构造器、MCP、检查更新与常用调试工具。

Losslessly compress the tool output your AI agent sends the model, prove every value survived, and report the exact tokens removed. Run it a

Fast, lightweight SOCKS5 server in Rust — TUI dashboard, headless mode, secure by default.

Windows-native terminal proxy that eliminates scroll-jumping and flicker for AI CLI tools. Sits between your terminal and Claude Code, Ge

Use Claude Code's UI with OpenAI GPT-5.6 (Sol/Terra/Luna) as the engine — powered by your ChatGPT Plus/Pro subscription via a local Codex pr

Multi-region Psiphon tunnel manager for a single Linux server: web panel + SSH CLI, SOCKS proxies bound to 127.0.0.1 only

Automated proxy config builder: converts VLESS/VMess/Trojan links and JSON to FlClash YAML

Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with any LLM.

Free proxy list by country: verified SOCKS5, SOCKS4, HTTP and HTTPS proxies, rechecked every 30 minutes, as TXT, JSON and CSV.

Paused Codex App auth-split proxy experiment; future work would need a Responses-to-Chat-Completions adapter.

Proxy CodeBuddy with OpenAI-compatible and Anthropic-compatible APIs for Codex, Claude Code, and standard SDK clients.

Use ChatGPT/Codex OAuth in Claude Code without an API key

Local-first MCP policy proxy. Tool-block, SQL-mutation gate, PII redact, audit, rate-limit, OpenTelemetry, vault secrets, first-use quaranti

Self-hosted LLM gateway — route OpenAI/Anthropic/Gemini traffic by config, not code. Fallback, protocol translation, telemetry.

让 Codex 白嫖 NVIDIA 免费顶级模型，一键接入 | Transparent proxy between Codex and NVIDIA NIM — use NVIDIA's free hosted top-tier models with Codex

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

Compare web access APIs (web unblockers / scrape APIs) head-to-head against a fixed suite of ~90 real-world, hard-to-scrape URLs

Real-time data anonymization for LLMs: secure your logs and conversations across cloud or local environments. Docker-ready & Multi-IA suppor

Smart AI proxy router that connects Claude Code, Cursor, Codex, Copilot, and 50+ coding tools to 40+ AI providers with 100+ models. Saves 20

Self-hosted AI API gateway 鈥?proxy OpenAI / Claude / DeepSeek behind one endpoint; works with Codex CLI / OpenCode / Cherry Studio.

Router-hosted control panel for VPN routing on Keenetic + Entware: xray VLESS Reality, sing-box UDP, per-group selective TCP/UDP routing wit

HTTPS overlay for operators. macOS and Android clients. Secure admin session that holds through short disconnects and packet loss. Protocol

zen-proxy is a local translation proxy that bridges Claude Code's Anthropic Messages API with OpenCode Zen's OpenAI‑compatible Chat Completi

ModelFlux: OpenAI-compatible model traffic router with health-aware key-pool scheduling and failover

Run Claude Code and Codex across multiple subscription accounts. A local Rust proxy that sends each request to the account with quota left,

一个面向 LLM API 的本地反向代理转发工具。上游服务（如 Coding Plan）过载返回时，自动按固定间隔重试，直到拿到数据。完整透传请求/响应（含 SSE 流式），对客户端透明。

Compare Mihomo / OpenClash nodes by service. Retest candidates, compare with your current node, and review switch outcomes. 按服务复测与对比节点，让切换有依

Bash automation to deploy a private VLESS + Telegram (MTG) proxy stack on a clean VPS: 3x-ui/Xray behind HAProxy, nginx masking, Let's Encry

Transparent Codex wrapper and account-rotation proxy

Архив. Проект переехал в https://github.com/jytt8u/Marvia

GLM-5.2 NVIDIA NIM Go 客户端 / OpenAI 兼容反向代理 — 自动化 hCaptcha 凭证池 + 流式推理，支持 Docker 部署。Go client & OpenAI-compatible proxy for NVIDIA Playground's

免费节点,每天更新，支持 Clash、sing-box、v2ray。 可按国家订阅，可覆盖全球多个地区，如日本、美国、新加坡、香港、欧洲等 客户端支持：FlClash、Clash Verge、ClashX、v2rayNG、Shadowrocket、sing-box 等。

Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Oll

Multi-protocol e-mail migration proxy

Chrome and Firefox extension (Manifest V3): leak protection for a SOCKS5 proxy or a system VPN/TUN. Matches timezone, language and geolocati

Terminal-native manager for the mihomo proxy core — subscriptions, local nodes, proxy chains, rule-based routing. TUI + CLI, no Electron, no

CLI-first, local LLM cost tracker for indie devs — drop it in front of any OpenAI-compatible API and watch token usage + spend in real time.

Session-layer circuit breaker for LLM & agent traffic — a transparent streaming proxy that meters every session and kills the one that goes

Lightweight asynchronous reverse proxy and load balancer with health checks, circuit breaker, and Prometheus metrics. MIT licensed.

Open source control-plane proxy for AI agents: identity, policy, budget, audit for MCP and beyond

The ops layer for running Claude Code and Codex all day on a Mac: subscription-first routing with overflow to GLM/OpenRouter/Bedrock, pausel

Desktop proxy workbench for macOS and Windows, plus CLI and Docker. Browse 150 cataloged sources, collect 106 supported feeds, verify proxie

Open-source browser automation broker for AI agents: persistent Chrome profiles, proxy-aware identities, remote API, MCP tools, browser-use/

Terminal Xray / VLESS Reality client for macOS with a TUI: subscriptions (Marzban, Remnawave), failover, TUN, SSH always bypasses the VPN ·

让 Codex 在 CC Switch 的 OpenAI Official 与第三方 Provider 之间切换后，仍能继续原来的会话。Continue Codex sessions across OpenAI Official and third-party providers

9Router fnOS app — FREE AI Router & Token Saver packaged for 飞牛 NAS