Havuz

WAI Play - AI web game testing and quality evaluation platform

Your AI SEO house. Audit your website, write useful content, compare competitors and plan backlinks inside your AI assistant. Free and open

Codex 风格的推理等级滑条（DeepSeek Harness 插件）：可拖动连续滑条 + 高档位渐变星尘特效

50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.

Automated quality checks that nudge AI coding agents toward better habits

Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex

Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and CLI. Local, fast, free.

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

dgx-spark-qwen38 is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Ace

Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl-

Community-maintained skills for specialized HyperFrames workflows.

Phil is a self-improving trader: an AI agent that trades short-term prediction markets and rewrites his own strategy after every settled bet

Jev Review, AI coding agents için kod değişikliklerine Jev API üzerinden yapılandırılmış yazılım kalitesi değerlendirmesi sağlayan yerel bir MCP server’dır.

Neden yükseliyor · MCP ve AI coding agents çevresindeki ilgiye, agent iş akışına eklenebilen ölçülebilir kalite geri bildirimi vaadi eşlik ediyor. 11 günlük yaşında 227 yıldız dikkat çekici erken ilgi gösterse de son 28 günde 4 commit ve 1 farklı yazar, sürdürülebilir geliştirme için henüz sınırlı kanıt sunuyor.

Build portable agent teams across models and harnesses, with shared memory, skills, tools, and workflows — then bring them into Codex, Claud

ZCodium, ZCode’un güvenlik ve gizlilik denetimine odaklanan, izleme ve telemetri bileşenleri çıkarılmış açık kaynak masaüstü fork’udur.

Neden yükseliyor · Repo çok yeni; 4 günlük yaşına rağmen 78 commit ve 6 farklı yazar kaydedilmiş. İlgi, ZCode’un gizlilik ve telemetri tartışmalarına verilen hızlı bir topluluk yanıtından kaynaklanıyor olabilir; yıldız ve aktivite verisi tek başına benimseme ya da denetim kalitesini kanıtlamaz.

Open-source stealth Chromium with engine-level fingerprint spoofing - de-Googled, drop-in Playwright, fully buildable and verifiable from so

Private AI on premise

Govern: one Decionis verdict before a workflow step runs — a deploy, a migration, an infrastructure change, an agent's action — with a signe

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they exe

Compact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule.

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts wit

Turn any CAE files into structured text an agent can use

🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers

Hermes Agent made portable desktop for Windows — 100 tools, GUI, local models via LM Studio, TTS, Music, ComfyUI, workflows, tool maker. No

Comfy Cloud product skills: slash commands for generating images, video, audio, and 3D with Comfy Cloud agents. Single source of truth for t

Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats

The open standard for runtime agent control — declarative hooks, policy enforcement, and observability across AI agent frameworks.

The memory & storage database engine for AI agents. Multi-model, edge-to-cloud, PostgreSQL-compatible. Supports graph, vector, array, timese

AutoCAD MCP server for AI agents (Claude, Cursor, any MCP client): 240+ tools to draw, edit and read DWG/DXF drawings. Live AutoCAD via COM,

Eyeline teleprompter meets editing agents: JSON-driven animation and motion graphics workflow

SRT 驱动的双后端 B-roll Agent Skill：自动路由 HyperFrames / Remotion，集成 152 张 Shotcraft 镜头卡

A multi-agent research system for the humanities and social sciences.

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

MobileCode, AI coding agent deneyimine iOS ve Android projelerini derleme, çalıştırma ve canlı cihaz önizlemesi özellikleri ekleyen bir opencode fork'udur.

Neden yükseliyor · Henüz 23 günlük bir repo için son 28 günde 214 commit ve 17 farklı yazar kayda değer geliştirme hareketliliğine işaret ediyor. Yıldız sayısı 239; ilginin büyüklüğünü tek başına kanıtlamasa da hareketlilikle birlikte projenin erken dönemde dikkat çektiğini gösteriyor.

CRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observati

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

Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops to company infrastructure with

Self-hosted, open-source financial data MCP server for AI agents — SEC filings, XBRL financials, 13F holdings, insider & congressional trade

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

Let AI agents edit Word documents without breaking them: fill in forms, update tables, restyle, write reports, and redline with tracked chan

CLI-first hub for agent skills: one npx install, manage in chat, distribute to 70+ agents

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

Keeps your Claude session warm for you

Expert-thinking AGENTS.md profiles that teach AI agents to reason like senior scientists and engineers.

Claude skill that analyzes images, websites, and Figma files and generates a structured design.md with token system, component inventory, an

Research-backed, eval-driven skills for AI agents

🔮 Run all your AI coding agents in tmux: jump to the one that needs you, spawn them into worktrees, and hand work between them

开源的企业版的数字员工工作台, OPC-Nexus（One Person Company Nexus）是一款本地优先的桌面 AI Agent 管理器。它为单人公司 / 独立开发者提供统一的 AI 数字员工管理平台 —— 从 Agent 创建、任务编排、多引擎接入，到消息渠道集成、

Give Claude its own dev team: one supervisor, four specialists, and bulletproof plans/builds without losing context.

PeerBridge MCP, farklı coding agent'ları yerel bir çalışma alanında yönetip görev, izin ve kanıt kayıtlarını ortak bir kontrol odasında birleştirir.

Neden yükseliyor · 41 günde 239 yıldıza ulaşmış; ancak bunun nedenini gösteren veri yok. README'deki çoklu agent yönetimi ve audit/evidence yaklaşımı ilgi çekici olsa da son 28 günde 4 commit ve 1 farklı yazar, sürdürülen geliştirme ve bağımsız katkı hakkında sınırlı kanıt sunuyor.