Custom agents

A shared repository for skills. Intended to be used with Letta Code, Claude Code, Codex CLI, and other agents that support skills.

Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local project files.

Technical webinars on reverse engineering, malware analysis, and software protection.

EvoPolicyGym is infrastructure for evaluating coding agents and generating training experience through Autonomous Policy Evolution.

把Claude Code的UltraCode模式带给DSH，把 DSH 的一次性多 Agent 调度，升级为可生成、可保存、可治理、可观察、可恢复的 Workflow 层

将 Wind 丰富的金融数据、专业工具、技能Skill与专家Agent能力开放给各类 Agent 和智能应用。通过 MCP、Skill、API 等标准化方式，为不同场景下的 Agent 提供股票、债券、基金、期货、期权、宏观、行业、新闻、研报、会议等全市场、全资产、全品类资讯能力。不仅支持行情、财务、新闻、公告、研报、会议等资讯的查询能力；更可将Wind Alice的多专家Agent能力全面输出，让你的Agent与AI系统直接完成行业与公司分析、资产分析与策略回测、估值与建模计算、风险识别、报告生成等复杂专业任务。让每一个需要金融能力的 Agent 都能够快速连接 Wind，获得可信的金融数据与专业技能。

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

An open standard for AI registries

Multi-agent to generate LangGPT prompts.

Self-knowledge through numbers

A voice chatbot based on GPT4All and talkGPT, running on your local pc!

Multi-Agent Conversation Framework in TypeScript

OpenMAS is an open source multi-agent simulator based in Matlab for the simulation of decentralized intelligent systems defined by arbitrary behaviours and dynamics.

OpenClaw aka (Clawdbot, MoltBot) is an open agent platform that runs on your machine and works from the chat apps you already use. WhatsApp, Telegram, Discord, Slack, Teams—wherever you are, your AI assistant follows.

A lightweight secure Self-evolution engine built in Rust, featuring a built-in native system-level sandbox, zero dependencies, and fully local execution.

OpenClaw skill for scraping any URL using the Decodo Web Scraping API.

A third-party component library based on Gradio. Integrates Ant Design, Ant Design X, Monaco Editor and more advanced components to help you build applications efficiently.

A set of prompts and agents that process daily journal entries

🌈 这是一个专注于大语言模型人格定制的预设包集合库：DAN机器人、猫娘、丁真、律师、诗人、辩论家、小说家等等，为用户提供了丰富多样的AI角色设定，让聊天体验更加个性化和有趣。

AI VTuber Waifu and voice assistant

DocMason is a repo-native agent that turns your complex office files into a local LLM knowledge base and your second brain. The repo is the app. Codex is the runtime.

World's first fully integrated and fully Automated Kubernetes management and orchestration solution

Connect your Claude agent to Google NotebookLM — add sources automatically, query notebooks, generate branded slide decks.

Đây là bộ SKILL, WORKFLOW, RULE do Anh Tester xây dựng dành riêng cho cộng đồng Tester để thiết lập AI Agent trên Antigravity hỗ trợ kiểm thử phần mềm.

桌面 AI 副屏 Skill：M5Paper 墨水屏 + AI Agent 推送 widget。装 Skill 后由 Agent 自动引导烧固件、配 Wi-Fi、推送内容。本地运行、无云依赖。

Native desktop shell for Pi Coding Agent (Tauri + Lit), extension-first and multi-session aware

Open-source multi-agent coding CLI for the terminal (TypeScript, MIT). Switch models mid-session; finish goals only when your test passes.

Moved to github.com/davidondrej/cloudroom

Chat with PDF files with source highlights

No-No Debug — Self-evolution system for AI coding assistants. 10 minutes writing code, 2 hours debugging? This skill makes your AI remember all its bugs.

We present the first systematic study on the scaling property of raw agents instantiated by LLMs. We find that performance scales with the increase in the number of agents, using the simple(st) way of sampling and voting. Our method is called Agent Forest, as a tribute to the classic Random Forest.

👷‍♂️High performance agent framework that can do everything. Minion is designed to execute any type of queries, offering a variety of features that demonstrate its flexibility and intelligence.

A lightweight annotation standard that helps AI agents navigate codebases faster, with fewer file reads and tool calls

Ultra-Lightweight, Pure Python Multimodal Agent.

Quran, Hadith, Translations, Tafaseer, Corpus Linguistics. Everything for NLP

-- -- File generated with SQLiteStudio v3.2.1 on Sun Feb 7 14:58:28 2021 -- -- Text encoding used: System -- PRAGMA foreign_keys = off; BEGIN TRANSACTION; -- Table: Commands CREATE TABLE Commands (Command_No INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL, Name TEXT REFERENCES Programs (Name) NOT NULL, Description TEXT NOT NULL, Command TEXT, File BLOB); INSERT INTO Commands (Command_No, Name, Description, Command, File) VALUES (1, 'Kerbrute', 'brute single user password', 'kerbrute bruteuers [flags]', NULL); INSERT INTO Commands (Command_No, Name, Description, Command, File) VALUES (2, 'Kerbrute', 'brute username:password combos from file or stdin', 'kerbrute brutforce [flags]', NULL); INSERT INTO Commands (Command_No, Name, Description, Command, File) VALUES (3, 'Kerbrute', 'test a single password agains a list of users', 'kerbrute passwordspray [flags]', NULL); INSERT INTO Commands (Command_No, Name, Description, Command, File) VALUES (4, 'Kerbrute', 'Enumerate valid domain usernames via kerberos', 'kerbrute userenum [flags]', NULL); INSERT INTO Commands (Command_No, Name, Description, Command, File) VALUES (5, 'Name-That-Hash', 'Find the hash type of a string', 'nth --text ''<hash>''', NULL); INSERT INTO Commands (Command_No, Name, Description, Command, File) VALUES (6, 'Name-That-Hash', 'Find the hash type of a file', 'nth --file <hash file>', NULL); INSERT INTO Commands (Command_No, Name, Description, Command, File) VALUES (7, 'Nmap', 'scan for vulnerabilites', 'nmap --script vuln <HOST_IP>', NULL); INSERT INTO Commands (Command_No, Name, Description, Command, File) VALUES (8, 'Nikto', 'Scan host for vulnerabilites', 'nikto -h <HOST_IP>', NULL); INSERT INTO Commands (Command_No, Name, Description, Command, File) VALUES (9, 'SMBClient', 'check for misconfigured anonymous login', 'smbclient -L \\\\<HOST_IP>', NULL); INSERT INTO Commands (Command_No, Name, Description, Command, File) VALUES (10, 'Hydra', 'Brutforce a webpage looking for usernames', 'hydra -l <user wo

An MCP server providing web search and content extraction capabilities. Integrates DuckDuckGo search functionality and URL content extraction into your MCP environment, enabling AI assistants to search the web and extract webpage content.

Self-hosted AI assistant with tool use, multi-agent orchestration, coding copilot and a lightweight Flask + vanilla JS stack.

Autonomous Assumed Breach Penetration-Testing Active Directory Networks

Benchmark for LLM-based Agents in Computational Biology

Open-Source AI App Builder for Mobile — Build apps with AI like vibecodeapp, rork, lovable & bolt.new but fully open source. Describe what you want → AI builds it → Preview on your phone. Built with Claude Code, Expo, React Native, Convex, E2B.

[ICLR/AAAI/KDD/EMNLP2026] Open-Source LLM-Based Data Analysis Agents

Claude Code skill: 5 AI agents analyze crypto, stocks, forex & commodities in parallel, adapt to your risk profile, and render an interactive bilingual (EN/ES) dashboard. Hybrid keyless market data. Educational market research, not financial advice.

I'm building a virtual Insurance Agent using Retrieval Augmented Generation(RAG)

Claude Code skill: find PR/backlink opportunities on Qwoted, build a sourced statistics page as a linkable asset, and pitch journalists — all from your AI agent.

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.

2026 Multi-Agent AI Town Simulation | Polis Darwin LangGraph

The solo founder's AI engineering stack. Fork of gstack, rebuilt for bootstrappers, indie hackers, and people who want to quit their day job. Pieter Levels energy. Ship fast, charge money, skip the pitch deck.

Open-source governance and hard gates for AI coding agents across Claude Code, Codex CLI, and Pi.

Local-first agent workspace for knowledge, tasks, documents and verifiable workflows · Локальная агентная система для знаний, задач и проверяемых процессов · t.me/romarayt

GPT-6 Astra 提示词写作 Skill：基于官方指南生成、优化、压缩与诊断提示词，支持 Codex、Agent 和 Responses API。

Web search MCP server that does search result reranking locally on your machine, formerly known as mcp-local-rag. ✨ no API keys ✨

WhiteLightning distills massive, state-of-the-art language models into lightweight, hyper-efficient text classifiers. It's a command-line tool that lets you create specialized models that run anywhere—from the cloud to the edge—using the universal ONNX format for maximum compatibility.

Local Topsha 🐧 AI Agent for simple PC tasks - focused on local LLM (GPT-OSS, Qwen, GLM)

Yang's PhD work

Prompt focused MCP Server for .json and .csv agentic data analytics for Claude Code

Model Context Protocol server to allow for reading and writing from Pinecone. Rudimentary RAG

Your AI mate into your favourite terminal

All your AI Agents like Claude Code, Codex CLI in a single TUI to keep things organized.

A framework for fine-tuning retrieval-augmented generation (RAG) systems.

A knowledge source about TTPs used to target GenAI-based systems, copilots and agents

AI-powered analysis engine for Argentine government open data. Multi-agent pipeline (LangGraph) with 10 data connectors, NL2SQL, semantic caching, and real-time streaming. Built with FastAPI, PostgreSQL + pgvector, Celery, and Gemini/Claude LLMs.

Official Implementation of "Psychologically Enhanced AI Agents"

🐒 Sub-Agents Directory is a curated collection of 100+ sub-agent prompts and MCP servers for Claude Code.

The Ultimate AI-powered app for consultants worldwide (EY, Deloitte, PwC, KPMG, McKinsey, BCG, Bain, etc) to do their research and complete work in hours instead of days, weeks and months.

Research Agent for multi-hop reasoning QA — 1st place in Alibaba Cloud Data+AI Global Competition (College Track). Built on PAI-LangStudio with Qwen models, featuring ReAct reasoning, dual-engine search, and web content extraction.

AI-native IDE workspace for legal and document-heavy workflows: files, agents, plugins, built-in document editing with tracked changes, OCR, evidence chains. VS Code for lawyers.

:four_leaf_clover: Healthcare AI agent app that combines medical records with AI-assisted conversations

22 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management, governance, ops, and quality audits (eval-leakage, doc-drift, single-source-of-truth, skill routing). Works with Claude Code, Codex, and Cursor.

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.

HBG Agent Skill for Chinese life-simulation narrative videos with consistent comic IP, rapid multi-life openings, Edge TTS, synchronized captions, zoom/pan motion and final MP4 QA.

Graph Engineering, simplified — with GraphCode. #graphcode

🚴 Claude Code / Codex skill for FIT & KML sports analysis — cycling, running, hiking, sensor and grade insights, local 3D route reports, PNG & H.264 MP4 exports. 运动轨迹分析与 3D 路线故事

Asamana is an AI-driven emergent narrative engine.

A multi-agent engine for data distillation and long evolutionary collaborative reasoning.

Native Windows Bash for AI coding agents. Run Claude Code, Codex, opencode & Gemini CLI without Git Bash, MSYS2 or WSL. Built in Rust, with MCP support.

Production-grade RAG API built in Rust. Hybrid search with HNSW dense vectors and BM25 sparse matching, cross-encoder reranking, layout-aware document extraction via Docling, and 94.5% accuracy on Open RAG Bench. Powered by Cerebras, Groq, Milvus, and Jina AI.

HiveMind Protocol - A Local-First, Privacy-Preserving Architecture for Agentic RAG

[NeurIPS2021] Learning Distilled Collaboration Graph for Multi-Agent Perception

XMPP/Jabber echo bot (written in sed)

Pebblo enables developers to safely load data and promote their Gen AI app to deployment

Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]

Toolkit for rapid AI and agent prototyping

[EMNLP 2024] OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs.

Prompt Line is a macOS app developed to improve the prompt input experience in the terminal for CLI-based AI coding agents such as Claude Code, Codex CLI, and Gemini CLI.

多AGV路径规划演示模型（CBS算法）

Tool that just makes your open source project better using LLM agents

🤖Free Agent Line Bot with Web Search, Google Image Search, Image Generator, Video Generator...

Claude Code Agents Prompt templates for Claude Code's subagent system. Run parallel code audits, automate fix cycles, get stuff reviewed. Built for the Claude Code Task tool. Not a framework. Just prompts that work. What This Does Claude Code can spawn subagents via Task(). These are the prompts those agents receive.

see live demo of chatbot. follow the link

Tools and agents for interacting with the Data Commons Knowledge Graph using the Model Context Protocol (MCP).

MCP server for token-efficient large document analysis via the use of REPL state

[NeurIPS 2025] ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World

Keyboard-first desktop Kanban workspace for AI coding agents with embedded terminals, git worktrees, and hook-driven task tracking.

Protocol-agnostic CesiumJS AI control runtime for MCP, WebMCP, function calling, and browser agents.

Workshop materials and demo app for 'Principles of Agentic Engineering' by Cole Medin — the AI layer concept, the PIV loop, and 15 reusable Claude Code commands you can drop into any project.

"Never send a human to do a machine's job" - Open Source AI hacking agent

Apple HIG reference and cross-framework UI audit tooling for agents.

一个通用、不绑定技术栈的 Claude Code 技能：在写第一行代码之前，先为项目铺好 Agent 规则、文档与架构，并在项目演进中持续把它们当作"源真相"。

A skill catalogue of 36 copy-ready admin UI shapes an AI agent installs and composes into a real back-office. Built on TanStack Start, Drizzle + better-auth, shadcn + Tailwind v4.