Better Harness
An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes. Turn task evidence into actionable team and organization insights.
Built with OpenAI Codex
1068 published projects on this site carry OpenAI Codex's own mark in their commit history, 194 of them found in the last seven days.
This is evidence rather than self-report. OpenAI Codex writes a trailer into the commits it makes, and that trailer is what this count is built on — not a badge, not a survey, and not anybody's word about their own work. A further 142 projects name OpenAI Codex because their creator said so; those are marked on the card and are not in the number above. About OpenAI Codex.
Codex Security
OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
Raven
The Harness of Harnesses • built for RSI: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
Octo Web
Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-class AI agent UX.
Litellm Agent Control Plane
1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.
REA
Reverse engineer anything with agents, from app behavior down to native binaries.
Graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Compozy
An operating system for AI agents. Plug in the agent CLIs you already use (Claude Code, Codex, Gemini CLI, Cursor) and they become a team: they split the work, hand tasks to each other, run automated on jobs and loops, and share one project memory. You steer everything from the browser.
Pua
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
Buzz Privacy and Support
A hive mind communication platform
Avoid Ai Writing
Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Hermes.
Routa
Workspace-first multi-agent coordination platform for AI development, with shared Specs, Kanban orchestration, and MCP/ACP/ A2A support across web and desktop.
Agent Orchestrator
Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.
Codex Desktop Linux
Unofficial ChatGPT desktop app for Linux (formerly the Codex app), built locally from OpenAI’s official macOS app. Includes Chat, Work, and Codex. Packages for Debian/Ubuntu (.deb), Fedora/openSUSE (.rpm), Arch (pacman), Nix/NixOS, and AppImage, with Wayland and X11 support.
Cmux
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.
SubConverter Extended
基于 subconverter 演进的多客户端订阅转换后端，重点增强 Mihomo Provider、远程资源、安全与多平台部署。
Netcatty
SSH workspace, SFTP, and terminals in one
Okou
Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.
Voyager
Enhancement suite for Gemini, AI Studio, Claude, ChatGPT & DeepSeek — plus a prompt manager for any website, DeepSeek Harness included. / 面向 Gemini、AI Studio、Claude、ChatGPT 与 DeepSeek 的增强套件；其中的提示词管理器可用于任意网站，如 DeepSeek Harness。
A framework for efficient model inference with omni-modality models
A framework for efficient model inference with omni-modality models
Claude Mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Harbor
Framework for evaluating and improving agents
GitNexus
GitNexus: The Zero-Server Code Intelligence Engine
memU: Your Personal Memory, Across Every Agent
Personal memory across agents
LeetGPU
LeetGPU Challenges
AI Accelerator System Benchmark
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
OpenList
A new AList Fork to Anti Trust Crisis
ChunkHound
Your entire engineering context, deeply understood