Havuz

借脑：把团队里 AI 用得最好的那个人的 AI，借给每个人。Let coding agents on different machines start, continue and read each other's sessions (Claude Code ↔ Codex),

Open-source macOS app for steering tmux-backed agents with a live sidebar tree and current-canvas fleet state. Apple Silicon.

Agent skill that turns scripts or fact lists into Vox-style paper-collage explainer videos — narration-first pipeline with AI-generated cuto

Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it te

Avito MCP server for chats, listings, orders and analytics. 148 tools, read-only profiles, dry runs and confirmations. Try the local demo wi

Research Software Engineering skills for AI coding agents

Make it easy to automate personal desktop tasks

Cross-platform native desktop control for DeepSeek Harness (Windows first): screen_shot, screen_read, click/type/scroll/key, app_list/app_la

Local document knowledge base for DeepSeek Harness: library_add/remove/list, hybrid semantic+keyword library_search with diversity re-rankin

Evidence-graded, agent-executable thinking-method skills - 63 frameworks reduced to their working mechanism, honestly graded, and producing

bb-huge 🤗 , Personal bug bounty findings hub and bug bounty orchestration for multiple agents

Memory backbone for AI agents. Four-tier store — working, episodic, semantic, procedural — with decay, consolidation, and association graphs

The open-source Agentic Development Environment (ADE) for FPGA/ASIC work

Lightweight multi-agent trading analysis framework with A-share, HK, and US market support

Your engineering taste, in every coding agent. Shadowclone learns your rules and delivers them as skills to Claude Code, Codex, Cursor, Pi,

Suijin is an open-source fully autonomous red teaming / web app pentesting framework for AI models. Powered by LangGraph, designed for bug b

Let your coding agent develop firmware on the real board, with the hardware as the gate.

Agent skill: the design of one change as one interactive page — zoomable map, your decisions as controls, lock it. For Claude Code, Codex &

免费、本地优先的长篇网文写作桌面软件：九大结构化资料板块、可审阅智能体系统、逐章生文工作流、去 AI 味工具链。Electron + Vue 3，数据全在本地。

An audit agent that proves whether a person's data is really gone: resolves identity across systems, judges state at the audit cutoff, finds

Machine-readable architecture decision records. Git-native decision memory and governance for human and agent-authored plans -- lint, CI, an

Lightweight, open-source, self-hosted Git server and forge written in Rust. Gitea/Forgejo/GitHub alternative with pull requests, CI/CD and b

Route AI web browsing through your home residential IP via Tailscale. Bypasses Cloudflare Turnstile, Amazon anti-bot blocks, and datacenter

Viglet Turing: open source enterprise search with generative AI. Faceted semantic search, RAG chat with citations and AI agents over your ow

Gang — the agent-only launchpad on BNB Chain: bonding-curve tokens, V3 tax tokens with holder dividends, and 打新 fair mints, gated by Binance

Agent operating system for Claude Code: a CEO agent plans, five roles execute, you get 15-minute tasks and decisions. Plain Markdown files,

The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learn

AI-authored 2D rigging and animation, verified before it is written. rigc compiles a rig spec into skeleton data in the Spine 4.3 format, ga

为 DeepSeek Harness 设计的破限插件：卸掉宿主的提示词限制和审批拦截，让助手照你说的做，不半路拒绝、不反复请示。补丁逐条可选，随时还原原版。 A jailbreak plugin for DeepSeek Harness: it strips the host's

Offline personal-agent runtime + life apps: seeded persona factory with planted ground truth, tool registry, policy engine with PII redactio

Agent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.

Humanlike — deterministic persona, context, memory and privacy controls for conversational AI agents · Детерминированное поведение ИИ-агенто

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

Self-hosted archive for YouTube, TikTok, Instagram and LinkedIn analytics, with an MCP server for AI agents.

Community hub for Skylit agents, APIs, and MCP projects

Wenshu（文枢）— 面向人文社科研究的 AI 知识处理工作流：本地知识库 / RAG / 中文引文 / 理论谱系。AI knowledge workflow for humanities & social sciences: local knowledge base, RAG

Stealth antidetect browser for Playwright — patched Chromium 151 with C++ persona, persistent profiles, humanize & GeoIP. launch() in, Chrom

Postmodernist critique skill for Claude and Codex. Pressure-test AI-generated strategy and marketing slop. Debug reality.

A phone-friendly web interface for Herdr: monitor agents, receive notifications, open real terminals, and send files.

An agent skill that reads a photo the way Sherlock Holmes reads a stranger (福尔摩斯): observe first, deduce second, every conclusion cites its

MCP server that lets AI agents (Claude, Codex) build complete Counter-Strike 2 maps: geometry, materials, lighting, entities, mechanics and

Deterministic tree-sitter + SQLite/FTS5 code knowledge graph for coding agents and developers: symbols, calls and dependencies over a CLI, a

The best of Matt Pocock's Skills, Superpowers, and Compound Engineering. One complete, simple, supercharged SDLC system for your coding agen

GB/T mechanical CAD skills for Codex, Claude Code and AI agents: AutoCAD/MCP, 2D/3D, strict DRC, assemblies and product safety gates.

Ship iOS and Android apps from your AI agent. MCP server for App Store Connect, Google Play Console and Expo EAS.

Developer and product skills for Claude Code, Cursor and Codex: 1-file AI evals and Chrome extension store assets.

187 plug-and-play AI agent personas in Korean (한국어) — Korean translation of agency-agents + 3 Korean-market originals (Coupang/KakaoTalk/Nav

🌐 Persistent 3D/2D spatial world model MCP server for AI agents. Entity tracking, object permanence, AABB collision simulation & view frustu

Open-source, self-hosted AI employees that ask before they act. 46 business roles, approval-gated autonomy, untrusted-content safeguards, sa

Plugin de skills e agentes para Claude Code workflows de engenharia reais, do PRD ao PR