Havuz

基于 ARTEX 的 AI 自主渗透测试系统，支持多 Agent 协作、资产探索与漏洞管理，提供本地部署面板。

1Password for coding agents: find, use, and save secrets without exposing them

Open-source adversary emulation for AI agents and MCP servers.

A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine

Oficina 3D con agentes de IA para tu negocio. Funciona con Claude Code: clona el repo, escribe /instalar y Claude lo configura contigo.

AI coding agent harness. Five modes: practice to playoffs. Stop your AI from over-engineering. Code like a man. Elbow out bloat. Score clean

Open-source React UI components for developers and AI agents. Typed APIs, design tokens, and source code you can customize.

Open GRC skills for AI agents. By ISMS Copilot.

A curated registry of reusable Mercury Agent, Open Claw or Hermes Agent skills designed for real developer workflows, persistent memory, and

Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human G

Industry and company research domain pack for DeepSeek Harness: methodology skills, industry chain mapping, public-source policy/news tracki

Ten Engines. One local-first Harness OS.

Official Nexscope guides for AI product video workflows, ecommerce Data APIs and free product listings. Compare workflows, watch examples an

SkillRanker, agent oturumunun bağlamına göre kullanılabilecek skills öğelerini sıralayan ve sonucu CLI, JSON veya hook üzerinden sunan bir Rust aracıdır.

Neden yükseliyor · 10 günlük bir repoda 121 yıldız ve 962 commit dikkat çekiyor; agent skills seçimi güncel bir geliştirici aracı ihtiyacına hitap ediyor. Ancak commitlerin tamamının tek yazardan gelmesi, bu hareketliliğin bağımsız katkı veya benimsenme kanıtı olmadığını gösteriyor; yükselişin kesin nedeni mevcut verilerden anlaşılamıyor.

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

Self-hosted web cockpit for AI coding agents: an isolated container per user, up to 4 chats side by side, harness-agnostic (Codex today; Ope

WAI Play - AI web game testing and quality evaluation platform

⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, loca

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.

Agent-driven video editing with Studio, ComfyUI Apps, CLI and MCP. Turn photos, footage and music into finished edits.

LLX Desk is a project-first development environment, built for working with agents: terminals, browser tabs and a task board per project, in

On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives t

An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

Give your agents a soul. Soulgent turns every Claude Code, Codex and WorkBuddy session on your Mac into a character you can see: who is work

Reverse engineered Deepseek chat into an OpenAI compatible API. Access V4 and R1 models through a simple REST interface without API keys or

Store, share, and resume AI coding sessions.

Give your agents the power to publish reviewable HTML documents. Self-hosted server + CLI + remote MCP; agents push, humans review with comm

A dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The ga

Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus vers

Browser automation and computer use for AI agents. One CLI and MCP server for your signed-in browser, native macOS apps, and real iPhones.

Avoid common App Store and Google Play rejections. Open playbook and pre-submission guard with 117 documented rejection patterns and fixes,

A swarm of disposable agents for unattributable web interaction

neatroots: see, check and replay your AI agent's runs on your machine while you build it. Local-first, by Neatlogs.

The open source operating system for AI-powered businesses

Videos verticales con agentes de Claude, a la vista y paso a paso. Código abierto para uso libre, sin reventa.

AI financial audit and task economics: connect usage, supplier charges and business outcomes to calculate task costs, cost per verified succ

Claude Code ve Codex geçmişindeki tekrarlanan istekleri bulup proje içinde kullanılabilir kısa agent komutlarına dönüştüren bir Agent Skill.

Neden yükseliyor · Agent araçları arasında tekrar kullanılabilir iş akışlarına ilgi çekiyor olabilir; ancak yükselişin nedenini doğrulayacak bağımsız kanıt yok. 9 günlük yaşında 104 yıldız ve son 28 günde 17 commit başlangıç ilgisi ve hareketlilik gösteriyor; 2 farklı yazarla proje henüz küçük ölçekli.

Local MCP server for ComfyUI — run your local ComfyUI from AI agents

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

Open source agentic SAST. The engine behind hundreds of disclosed zero-days. 100+ AI security agents, any repo or PR diff, bring your own mo

jev-use, macOS’ta sesli veya yazılı komutları Accessibility tree üzerinden uygulama eylemlerine dönüştüren bir computer-use aracı.

Neden yükseliyor · README, vision model kullanmadan Accessibility tree ile bilgisayar kontrolü vaadini ve hızlı kurulum akışını öne çıkarıyor. Ölçümlerde repo 8 günlük, 100 yıldızlı; son 28 günde 8 commit ve 2 farklı yazar var. Bu, erken ilgi ve bir miktar geliştirme faaliyeti gösteriyor ancak benimseme veya olgunluk kanıtı değil.

Plugin for Butterbase.ai

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

Policy-adherent, auditable reasoning for AI Agents.

MCP server that watches video footage and returns license-safe BGM matches, hook windows, and ffmpeg ducking specs for agents.

The lightest sandbox. A process-based sandbox for Linux, no container, no VM, no privilege, no prompt injection

AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multipl

红狐数据（RedFoxHub） 技能合集：面向 Agent 的可复用 SKILL 集合，覆盖灵感、选题、文案创作、数据复盘等场景，持续更新。

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.