Havuz

面向 AI 编程智能体的任务包工作流工具，用可验证的范围、证据和 Git 门禁管理长期改动。(Task-package workflow for AI coding agents with verifiable scope, evidence, and Git gates.)

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

Supercharge the AI you already use. Greener. Better. Faster. Cheaper.

Agent-native investment research workspace for evidence-tracked, refreshable investment theses across equities, earnings, macro, and portfol

Claude Code plugins for the work that keeps coming back: repo maps, conditional rules, ticketed parallel work, extra subscription models, lo

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

Local-first CLI for agent skills, browser automation, knowledge bases, external CLIs, and terminal AI chat.

[ICML 2026] Autonomous AI agent for end-to-end spatial proteomics analysis, with SP-Bench for agentic multiplexed-imaging workflows.

Google Health CLI — one command-line tool for the Google Health API. Includes AI agent skills.

Local-first, multi-agent Skill governance, collaboration panel, and shadow routing (v5.0).

PaperGraph MCP, matematik makalelerindeki sonuçları, kanıt izlerini ve dış kaynak bağımlılıklarını AI agents için kaynak gösteren okuma haritalarına dönüştürür.

Neden yükseliyor · 26 günlük yaşına karşılık 269 yıldız ve son 28 günde 84 commit dikkat çekiyor; ancak bu commitlerin tek yazardan gelmesi, hareketliliğin geniş bir geliştirici topluluğuna yayıldığını göstermiyor. Yükselişin özel nedenini mevcut verilerle doğrulamak mümkün değil.

Open-source MCP servers for Latin American commerce — Pix, NF-e, banking, fiscal, logistics, and messaging across Brazil, Mexico, Argentina,

Run Hermes Agent - a self-evolving AI assistant - on any Android device using Termux. One-line installation.

Pre-build idea-to-spec workflow skills for Hermes Agent: turn rough ideas into design docs, implementation specs, and Superpowers-ready buil

DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Ten

Agent skill to reverse engineer a SaaS product through the browser into a knowledge base for rebuilding it: screens, rules, data model, desi

Design systems, skills and visuals for coding agents

基于 DeepSeek Harness（DSH）的稳定桌面端，集成Git、内置浏览器与记忆功能 | DeepSeek Harness desktop GUI with local workspaces, Git, browser and memory.

Android companion for DeepSeek Harness | chat, goals, approvals & notifications from your phone, over your LAN. Kotlin + Jetpack Compose.

YouTube transcript skills for Claude Code, Cursor and Codex. Agent Skills to get transcripts, search YouTube, read channels and playlists, a

A local-first, long-term memory for anything you'd otherwise forget.

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

Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language.

Jev karar motorunu Agent Harness ortamlarına eklenti olarak bağlayıp araç, Skill veya görev sorumlusu seçimi için yapılandırılmış değerlendirme sunuyor.

Neden yükseliyor · Repo yalnızca 8 günlükken 215 yıldız almış olması kısa sürede dikkat çektiğini gösteriyor; ancak bunun benimsemeye mi yoksa geçici ilgiyi mi yansıttığını anlamak için veri yetersiz. Son 28 gündeki 7 commit’in tek yazardan gelmesi de topluluk katkısı konusunda henüz güçlü kanıt sunmuyor.

Asks what to optimise and how to measure it, then runs experiments on its own branch.

Agent-readable docs, verified examples, and skill manifest for @zapier/zapier-sdk

An engineering team in a box for Claude Code — 12 specialized agents, 15 automation hooks, and the P7/P9/P10 methodology.

Open-source MCP server for safe, stateful AI-agent phone calls with OpenAI Realtime and Twilio.

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

Toward Autonomous Scientific Discovery

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

106 social media skills for AI agents - strategy, writing, video, design, platform growth, publishing, and analytics. Works with Claude, Cur

Open protocol for AI agent work contracts and verifiable execution — authorization, evidence, and acceptance for multi-agent systems

Harnessclaw is a powerful, Electron-based desktop application designed to manage, chat with, and operate AI agents and skills seamlessly.

Kane CLI by TestMu AI (Formerly LambdaTest)

A living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, delegate, learn & hold meetings. Per-agent swappabl

Tactical AI Workspace Monitor & EDR

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

One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (des

Poirot is a deep research agent kernel built for those who care about how agents are architected.

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self

Beta. Self-hosted panel for running a VPN for others: family, friends, a community or a small team. Hysteria2, VLESS REALITY and AmneziaWG,

Gives a coding agent eyes and ears for any social video: timestamped frames plus a transcript, about 50x cheaper than sending the whole file

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation,

Turn your Win, Mac or DGX Spark into an AI hotspot. Nightshift races hundreds of attempts overnight and keeps what passes. Plus the open con

Let your agents read, send, and react to email autonomously, without human involvement

Small plugins and mods that make your life (and Claude Code) better

An agent design team you control: 10 agents that run an inclusive design process while you direct.

Maintenance mode: bug fixes only, no new features. Lighter option, no app to install: forgent3d/forgent3d-skills

Create product launch assets with Remotion, then review and distribute them through guarded, dry-run-first workflows.