Havuz

Keep Codex thread history aligned to one provider bucket.

Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orches

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable

Turn Codex threads into an organization of long-lived domain agents.

Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) r

Agent Skill for turning Chinese classical poems into vertical Chinese-art videos with ImageGen stills, Docker I2V, calligraphy captions, ret

Turn Codex into your investment workflow team

A Simple and Universal Product Rehearsal Engine, Speccing Anything. 简洁通用的产品推演引擎，推演万物。

An MCP server for RenderDoc: Empowering AI assistants to analyze GPU frame captures and debug graphics pipelines.

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

Academic Paper Search：中文科研用户的 Codex / Claude Code / DeepSeek Harness Skill + MCP；跨 CrossRef、PubMed、arXiv、OpenAlex、Europe PMC 检索去重，支持 MeSH、引用

A lightweight Windows/macOS desktop widget that keeps your Codex quota visible from your local Codex Desktop session.

14 installable skills for Claude Code, OpenAI Codex, and Hermes: find unknowns, clarify requirements, manage context, test assumptions, and

Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with memory and skills that compound.

Markdown-first shared memory vault for Claude Code and Codex with SQLite, Zvec, Git, closeout, and audit

Put the world's best AI agents to work. One workspace for all of them -- Claude Code, Codex, Gemini, Grok and more, running side by side on

Stop babysitting local AI agents. Just notifications, approve, and resume your Codex,Pi,Grok, or Claude code sessions anywhere. 0-Intrusion

AI icon set generator skill for Claude Code & Codex. 帮你生成整套风格统一的图标。

A portable project-planning skill for Codex, Claude Code, pi, Hermes, and Agent Skills-compatible harnesses. Evidence before build advice.

Run Claude Code dynamic workflows on a local Codex (GPT) backend, plus an interactive run viewer

AI chat and agent tooling for Godot, with both MCP support and in-built native chat window.

Agnes AI 全模态 API 非官方帮助中心：完整 API 文档 + 通用支持 Skill。已同步 Agnes 3.0 Flash（512K 上下文 / 65,536 输出 / 三端点 / Thinking）与 Image 2.5 Flash，覆盖文本、图像、视频模型接入，适

The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, C

Mine your Claude Code and Codex logs into a local you.md agent profile.

Local cockpit for Codex imagegen, pixel art, image editing, animation, and sprite-sheet workflows.

Create high-fidelity Codex companions from 2+ photos with local open-weight neural editing and no OpenAI API key.

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite fi

Reusable AI agent skills for Codex, including a PowerShell skill for safe Windows command invocation and optional MCP utilities.

Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents.

Search WeChat public account articles by keyword via Sogou WeChat Search. Returns structured JSON — no API key required.

Age of Agents — watch your AI coding sessions grow a peaceful pixel-art realm. Run it with npx age-of-agents.

AI Agent Skills for Chinese Knowledge Workers: iMandalArt, FIRE, planning, and publishing workflows for Claude Code, Codex, and LLM agents.

Agent Skills for theming AI desktop apps: reference image → reversible Codex/WorkBuddy skin → verify, repair, publish. | 给 AI 桌面应用换肤的 Agent

Image generation (gpt-image-2) and GPT-5 subagents for Claude Code — through the Codex CLI login you already have. No OpenAI API key.

Create reusable bots powered by Claude Code, Codex, or OpenCode. Run them locally across your repositories with persistent threads and permi

Reusable Skills for LLMQuant Agent, Claude Code, Claude.ai, Cursor, Hermes Agent, OpenClaw and Codex, grounded in LLMQuant Data

Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.

Research-backed, eval-driven skills for AI agents

Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas

协调探索、执行和独立评审，让复杂任务按明确职责并行推进，由主 Agent 统一验收。

Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.

A repository for skills that are essential to my daily work

Reusable AI prompt and project brief system for cinematic scroll-driven 2.5D websites.

The open-source company brain. Run your entire company with AI agents, skills, and a self-improving context.

25 fixed illustration styles for Codex: 9 skills, prompt recipes, and visual references

24 open-source agent skills that turn taste into instructions — ten genre identities, each proven by a same-brief before/after demo

Harness-native agent components for Codex and Pi: a DeepSeek V4 Flash subagent and a DSH Minimal mimic for V4 Pro.

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacem

Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub

🧠 Production-grade memory sidecar for AI agents — gbrain + Hindsight + 3-tier recall. Agent-agnostic, battle-tested. | 生产级外挂记忆系统，兼容Hermes/Cl