Havuz

Keep your AI coding sessions named after what they actually became — Claude Code, Codex, Cursor and more. Auto-renames idle sessions, search

Your AI workspace for smarter conversations, creative tools, and powerful agents. Bring your favorite models together and make it your own.

One brain, many arms — spawn multiple specialized Codex agents as MCP servers

On-device MCP server for Android. Connect ChatGPT through OpenAI's official secure tunnel, let AI agents operate your phone and run schedule

Self-hostable channel-native AI teammate for Slack. Open source alternative to Claude Tag. LLM-agnostic.

Model router for AI coding agents: routes routine work to cheaper models with routing rules, 8 subagents, hooks and a CLI runner

Prism — a one-click desktop LLM gateway. Embeds 37 providers (OpenAI / Anthropic / Gemini / Bedrock / …) behind one OpenAI-compatible endpoi

Jev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage

Find out which model actually answers your Codex requests (detects silent model substitution, e.g. gpt-6-astra served by gpt-5.6-luna)

Desktop realtime speech translator for routing translated audio between virtual audio devices in calls.

Automate x.ai registration with a web console, batch runner, WARP egress, and grok2api token sink in one project

Open-source Kanban where every column is an AI agent

Adversarial LLM Reversal for hermes-agent

A minimal browser-agent harness - six tools, any model. pi for the browser.

A free, private, local AI for any app. One command, OpenAI-compatible, no API key.

小白也能上手的 Claude Code / Codex 上游配置切换桌面应用 | A cross-platform, site-driven desktop app for switching Claude Code & Codex providers

Self-hosted document library and PWA reader for PDF, Markdown, and text files, with NAS folder watching, full-text search, sharing, annotati

Review-only AI code review for GitHub pull requests. Cross-check PRs with model-agnostic reviewers that can comment inline but cannot approv

AI-powered meeting recorder on XIAO ESP32-S3 — live transcription, summaries, and AI chat

Advanced RAG (Retrieval-Augmented Generation) system for private document intelligence. Uses OpenAI GPT-4o and Vector Databases to provide z

A minimal yet ready-to-use AI agent harness, built on best practices for frontier models.

sigma is a Go package for provider-neutral AI model calls.

Enhanced Sub2API distribution focused on OpenAI/Codex account operations, quota inventory, proxy routing, and upstream compatibility.

Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients

Open-source AI short-form video generator — turn a topic into a captioned YouTube Shorts / TikTok / Reels video with AI visuals (fal) or fre

A Minesweeper benchmark for LLM agents. One identical board, up to nine models in parallel, one clock, one tool layer.

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.

网页版登录态 → OpenAI 兼容本地反代：DeepSeek / Qwen / Doubao 免费额度驱动 ZCode。Web login → OpenAI-compatible local API.

Free, open-source Windows account manager for Codex Desktop and VS Code. Quota tracking, automatic account switching, experimental conversat

Per-key smart routing for New API: automatic failover, shared health, self-healing recovery, actual-route billing, and explainable decisions

Progressive agentic reading harness: sentence maps, bounded chunks, Chronicle Markdown books, packets, validation. Python CLI + Next.js demo

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

The agent harness for Ruby applications. Durable sessions, streaming, human-in-the-loop approval, compaction, structured output, sub-agents,

WorkForge is a Windows MCP gateway that lets ChatGPT inspect files, resume Git work, make SHA-guarded edits, read images, and run supervised

A lightweight (10 MB) AI IDE alternative to Cursor and Windsurf

Free security skills for AI-built apps — run /lictor-security-check in Claude Code before you ship. Plain English, read-only, no telemetry.

Token-efficiency linter for LLM prompts and payloads

OpenAI-compatible Go gateway for Vertex AI Gemini with explicit model routing, live catalog refresh, and Cloud Run setup.

Independent local Stream Deck Plus companion for the Codex desktop app.

Give agents access to virtual hardware.

Codex skill that disables Responses Lite model mapping to restore hosted Web Search through OpenAI-compatible gateways.

🛠️ Codex 插件修复工具集

A medical FAQ chatbot powered by Retrieval-Augmented Generation (RAG) using FastAPI, LangChain, Qdrant, and React.

Give AI coding agents a voice. Cross-agent skill that wraps OpenAI gpt-realtime-2 for Claude Code, Hermes, and OpenClaw.

AI 生图 Web 应用

Codex-style apply_patch tool extension for pi

把 pi coding agent 装进安卓手机：扩展生态和电脑上完全一样——直接用自然语言让 AI 自己搜、自己写、自己装扩展、技能和主题。

macOS menu bar app that tracks usage limits and switches accounts across Claude Code, Claude Desktop, and OpenAI Codex — one click to flip w

Adversarial multi-model consensus protocol for Hermes Agent. Independent solve. Adversarial critique. Formal scoring. Verified synthesis.

A lightweight Windows badge for Codex usage limits, reset times, and reset credits. Tauri 2 / Rust. 余量