Havuz

Local-first observability CLI for Codex and Claude Code

A repository for skills that are essential to my daily work

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

The ADE for AI agents. Automate everything else. Do your true work.

Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.

Automatically resume Claude Code, Codex CLI, Grok, Qwen Code, Kimi CLI, OpenCode, and Antigravity sessions when 5-hour or weekly usage limit

Share AI resources and collaborate across your devices and authorized teammates. Delegate tasks through Codex or Claude Code, collect files

UmaDev: A coding agent that works like a real dev team, commanding the Claude Code / Codex / OpenCode you already use.

VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with revie

CodexIsland - AI usage limits in your MacBook notch

带 AI 精读大型开源仓库的方法论：四阶段流程、可复用模板、28 条踩坑清单，核心是让每个技术论断都可回溯到源码具体行

Claude Code skill for AI filmmaking — shot lists, keyframe & video prompts, with 10 director-style overlays (Spielberg, Kubrick, Wong Kar-wa

Claude Code 专属会话管理器：多会话统一管理 + AI 成本可视化仪表盘 + 会话摘要知识库。终端 CLI 与 VS Code 扩展双形态，流式解析会话日志，按模型/项目/日期归因成本并支持预算预警，会话退出自动生成结构化摘要沉淀知识。

OnlyShot · 神仙鱼 AI 短剧工业流水线 Claude Skill — 一句话 → 剧本/分镜/分镜图/视频/剪辑 五步 → 可发红果抖音的完整短剧。集成即梦/Seedance，17 失败模式沉淀。

File-backed workflow harness for reliable Claude Code and Codex sessions.

LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented an

The open-source trading harness for Claude Code / Codex agents.

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

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

Vlad's Playbook — a 48-chapter operator field manual where every artifact is live, clickable, and forwardable. 31 interactive widgets, a sel

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

The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it

SV Number agent skill, AI agent’ların farklı ülkelerden tek kullanımlık telefon numarası alıp SMS doğrulama kodunu API üzerinden okumasını sağlar.

Neden yükseliyor · 51 günde 225 yıldız almış; agent tabanlı otomasyon ve telefon doğrulama ihtiyacının kesişimine odaklanması ilgi çekmiş olabilir. Ancak yükselişin nedenini doğrulayacak ek veri yok; README’deki 200+ ülke kapsamı iddiası canlı API üzerinden kontrol edilebilir, bağımsız olarak doğrulanmış değil. Son 28 günde commit ve farklı yazar görünmüyor.

The first self-evolving AI agent. Rewrites its own source code in real-time. 6 AST mutation strategies. Absorbs GitHub repos autonomously. 7

OpenKeylet — Local password and credential manager for AI agents via MCP. Use passwords, API keys, SSH, and TOTP while keeping hidden plaint

Han: AI skills and agents for "Solo" product engineers and small teams

11 Claude skills for SEO: page audits, linkbuilding, article writing, E-E-A-T audits, semantic gap analysis, link building. Methodology from

design-os-3d-blender, AI agent’ların Blender içinde 3D parçalar üretip sonuçlarını denetlemesine yönelik araçlar, kurallar ve örnek yapım dosyaları sunuyor.

Neden yükseliyor · 22 günde 81 yıldız ve son 28 günde 51 commit dikkat çekiyor; ancak commitlerin tamamı tek yazardan geldiği için ilginin bağımsız katkıcılara veya yaygın benimsemeye dönüştüğüne dair kanıt yok. AI agent iş akışını Blender üretim kontrolleri ve görsel örneklerle birleştirmesi ilgi çekici bir sunum sağlıyor.

Turn any tutorial video into a verified, installable AI-agent skill. Reads the screen, not the transcript. Runs locally. MIT.

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

Subpool, ekiplerin yetkili AI abonelik ve API hesaplarını tek bir self-hosted gateway üzerinden havuzlayıp yönetmesini sağlar.

Neden yükseliyor · 25 günlük yaşına rağmen 83 yıldız ve son 28 günde 61 commit dikkat çekiyor. Commit temposu yüksek; ancak yalnızca 2 farklı yazar görünmesi katkı tabanının şu an dar olduğuna işaret ediyor.

Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agent

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

ChengOS is a visual AI data processing and agent workflow system. This directory contains deployment scripts, infrastructure configs, and ru

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

Agent control panel for Claude Code, Codex, OpenCode, Pi and 40+ agents with articles and boards supported

Run many Claude Code (or Codex) sessions in parallel — across every project — from one screen. Local-first, git-worktree-isolated tasks, no

Your work, already underway. A personal AI assistant for your job: mail, chats and tickets become tasks, the agents you already use (Claude

Generate a compact codebase index for AI assistants — saves 50K+ tokens per conversation

Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI.

Spotkit, feature açıklamalarını tutarlı bir design system içinde minimal SVG ürün illüstrasyonlarına dönüştürmek için agent’lara yönergeler sağlayan bir skill’dir.

Neden yükseliyor · 19 günlük bir repoda 63 yıldız ve son 28 günde 29 commit erken ilgi ve yoğun geliştirme gösteriyor; ancak tek farklı yazar olduğundan bu veriler yaygın benimsenmeyi kanıtlamıyor. İlginin kesin nedenini ölçümlerden çıkarmak mümkün değil.

Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you. Local, tmux-backed, MIT.

Local, zero-dependency dashboard for Claude Code: live token usage and context, lost-session recovery, full-text search, and approve tool ca

A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.

18 portable Agent Skills for voice-native AI, human judgment, microbets, social tact, writing, life systems, and safe deployment.

Open database of 29,000+ CCTV camera specs across 230+ brands, with Frigate and ONVIF/RTS integration, CC0

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

Local subagent orchestration for Codex and Claude, with persistent task state, reusable teams, and interruption recovery.

Long-term memory for any AI agent. One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Self-host free or use Uteke Cloud.

The Open Analytics design language as an agent skill: component recipes with type-checked source, token CSS, and a CLI. Works with Claude Co