Havuz

Free desktop app to run AI coding agents in parallel: Claude Code, Codex, Cursor, OpenCode, Kimi, Grok. Worktree per thread, shared memory.

ChatGPT Web plans; local Luna executes via pure MCP, with direct file/terminal tools and refresh-safe image previews.

Test what AI watermark and provenance evidence exists, whether it verifies, and what survives publishing.

Plugin marketplace for AI-assisted reverse engineering across Codex and Claude Code.

通过微信安全管理本机 Codex｜Control local Codex from WeChat with persistent first-class Threads.

A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharin

Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep chara

VibeGame: Vibe Your Dream Game -- An open-source self-evolving multi-agent framework with an AI-Native game engine that turns your natural l

ESP32-S3 AMOLED for Claude Code & Codex usage, live agent activity, and answerable NEEDS YOU alerts. Local-first macOS/Windows host; optiona

JobAppAgent: open-source AI job application agent (Agent Skill + CLI). Searches wide, matches one verified résumé, applies within your rules

A live layered dependency map for bottom-up development — MCP server + terminal pane for Claude Code, Codex CLI and any MCP client. Ghost th

MCP server: repo map, code search, and token-aware context packs for AI coding agents

让 AI 像人一样说话、创作的规则集。Ruleset for making AI talk and write like a human.

Codex skill for evidence-preserving academic rewriting in Chinese and English.

Local-first, resumable AI maintenance pipelines with single-writer safety and deterministic verification.

AI Context Linker is a privacy-first context compiler. Turn local project context into reviewable Markdown for ChatGPT planning and Codex de

A calm agent multiplexer with familiar IDE features, for macOS, with an iPhone app.

Safety-first GUI and CLI for auditing, backing up, importing, cleaning, and trimming Codex conversations without editing internal storage.

Create handoff documents and migrate active sessions between Claude Code and Codex.

Kit de la clase Adversarial Review (Imperio Agéntico): app de demo con 43 fallas + prompts de auditoría UI/UX/seguridad + checklist + report

Your AI coding agents keep working while you sleep. Drive Claude Code, Codex, Gemini, opencode & more from your phone: resume past usage lim

Универсальные безопасные Agent Skills для любых конфигураций 1С / Universal safe Agent Skills for any 1C:Enterprise configuration

No Termux required to use AGENTCODI. No WebView shell. No separate gateway setup. with its own native sandbox in protected mode - With its o

Git diff for AI agent repository instructions. Shows the blast radius of AGENTS.md and CLAUDE.md changes.

A practical workflow for reliable AI-assisted software development

Stop That Shit, AI coding agent’ların izinsiz kapsam genişletmesini ve gereksiz savunma kodu eklemesini Skill kuralları ve platform Hook’larıyla sınırlamaya çalışır.

Neden yükseliyor · AI coding agent’ların gereksiz iş üretmesi ve kullanıcıların sınır koyma ihtiyacı güncel, anlaşılır bir sorun. Repo 47 günde 2304 yıldız almış; son 28 günde 37 commit ve 3 farklı yazar aktiviteye işaret ediyor. Yıldızlar ilgi göstergesidir, gerçek kullanım veya etkililik kanıtı değildir.

website-rebuild-skill, bir AI agent’a web sitesini arşivleyip kaynak kodunu izlenebilir biçimde yeniden kurma ve sonucu otomatik karşılaştırmalarla doğrulama iş akışı sağlar.

Neden yükseliyor · 1291 yıldızın 48 günde gelmesi ve son 28 günde 70 commit dikkat çekiyor; README’deki ayrıntılı iş akışı, örnekler ve Trendshift rozetleri de görünürlüğü artırmış olabilir. Ancak commit’lerin tek yazardan gelmesi ve başarı örneklerinin proje tarafından raporlanması, ilginin bağımsız benimseme ya da doğrulanmış kalite kanıtı olarak görülmesini sınırlar.

OpenMausBot, kullanıcının kendi makinesindeki agent CLI’larını sohbet arayüzünde birden fazla kişilikli bot olarak çalıştıran, bilgisayar ve uygulama erişimi sunan açık kaynak bir masaüstü uygulamasıdır.

Neden yükseliyor · 54 günde 4.011 yıldıza ulaşması, yerel ve kendi agent’larını kullanma yaklaşımına yönelik belirgin ilgiyi gösteriyor. Ancak son 28 günlük commit ve farklı yazar verileri ölçülmediğinden, ilginin proje gelişimine veya topluluk katkısına ne ölçüde dönüştüğü belirsiz.

`xxg-portrait-rebuild-light` is an image-edit skill for existing portrait photos. It reconstructs the key light, fill, shadows, and backgrou

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

A practical Codex skill for evidence-backed repository health audits

🌃 Capri — Edgerunners-inspired AI agent for your desktop. Works with Claude Code, Codex, Antigravity & more.

Turn npm, Python, and Rust release evidence into bounded Codex maintenance tasks.

面向 AI 上下文管理的 Agent Skill：为 Codex 上下文管理、Cursor 上下文切换和 Claude 上下文管理提供跨窗口续接，用 Git 保存可验证的功能说明与变更记录。AI coding context management and agent handof

Privacy-conscious native macOS and StickS3 companion for Codex and local coding agents

A Codex plugin that quietly captures meaningful project work and syncs it to Plane.

An end-to-end encrypted channel between coding agents, anywhere

让 ChatGPT 通过 MCP 调用本机原生 Codex 会话的轻量桥接器。

Guardrails for AI coding agents — Claude Code, Codex and Antigravity — enforced by a real git pre-commit gate. One command installs AGENTS.m

⌘-click an element in your running app, say what to change, and Claude, Codex, Cursor or another AI agent opens with the exact file and line

One command turns every agent session already on your disk into a graph: subagents, tool calls, retries, the moments you said no. Ask your a

Open-source agentic terminal. Finds the agent sessions already on your machine, keeps them alive after you close the app, and lets you reach

Agent skills for spec-driven development. An automated agentic delivery loop coordinates planning, implementation, and cross-agent code revi

監看 Claude Code 與 Codex 的 session，即時用繁體中文講評你打的英文 prompt

lnwjud — local AI-agent runtime & MCP gateway

Git-based test distillation for Codex agents: catch aggressively, commit reluctantly

A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.

A build playbook that turns your coding agent into the foreman of a website build. It interviews you, forces the design and scope decisions,

Evidence-gated Claude and Codex council orchestration.

Навык для ИИ-агентов (Claude Code, Codex, Cursor): упрощает русский технический текст по ГОСТ Р 58049—2017 — комментарии в коде, документаци