MCP servers and skills: search, filter by where they run, and compare.
Create branded CompleteTech LLC security, safety, and launch-readiness review PDFs for agentic workflows.
SkillMITFew starsNo key
An end-to-end agentic pipeline that accepts code repositories, log files, screenshots, and architecture diagrams, runs specialized MCP (Model Context Protocol) security tools, correlates findings acro
SkillMIT★ 1Few starsNo key
Native Claude Code + Codex skills for AI security review. Also ships instruction files for Cursor, Copilot, and Windsurf. Checks 33 risks: OWASP LLM Top 10 2025 · applied RAG/MCP/agent checks · OWASP
SkillMIT★ 6No key
Karpathy LLM based claude harness for PenetrationTesting / Bugbounty using obsidian
SkillMIT★ 336No key
Give your agents a secure, containerized SQL sandbox with MCP or API access enabled with DuckDB. No infra required, quick spin-up cycle. Push any CSV — query, analyze, and move on.
DockerMIT★ 21No key
A Model Context Protocol (MCP) server implementation exposes document processing capabilities through natural language, supporting both direct human interaction and AI agent tool calling.
Node.jsMIT★ 62No key
General Luddite is an agentic code platform for managing multiple projects, models, model vendors, credentials, map, skills, etc. This is distributed as a single, self contained binary of the python c
SkillMIT★ 4Few starsNo key
A self-hosted AI agent that thinks, acts, and improves itself – all running privately on your own machine. Browses the web, writes and executes code, manages files, sends emails, monitors URLs, builds
SkillMIT★ 12No key
Локальная мульти-агентная система на self-hosted LLM (Ollama), 0 обращений к облачным LLM-API. Роли Planner/Executor/Critic, цикл thought → action → observation. 3 канала: Telegram, MAX, консоль. 19 и
SkillMIT★ 6No key
Agent permission firewall for MCP tools, shell, files, and x402/Base payments.
Node.jsMIT★ 6No key
Offline-first AI coding assistant for 1B–7B local models (Ollama, LMStudio, llama.cpp). Terminal REPL with file editing, project map, agents, scripts, post-processors, and parallel multi-model queries
PythonMIT★ 2Few starsNo key
Autonomous multi-agent coding framework that plans, builds, validates and document software for you
SkillMIT★ 4Few starsNo key
A secure, highly capable MCP server written in Rust. It exposes a comprehensive suite of filesystem operations as tools for AI agents.
SkillMIT★ 5No key
Forges file:line-grounded skills from your code, then replays your own shipped tickets blind — against a bare-model baseline — to measure whether they help.
SkillMIT★ 1Few starsNo key
File comparison, multimedia management, and developer workspace tools using Beyond Compare
PythonMIT★ 5No key
Opinionated Claude Code foundation — Explore → TDD → Audit workflow, auto-detected stack presets (nextjs, fastapi, astro, ...), curl | bash install. MIT.
SkillMIT★ 5No key
Semgrep/Opengrep rules and an AI-agent triage skill for auditing agent skill files (SKILL.md) against the OWASP Agentic Skills Top 10
SkillMITFew starsNo key
Security scanner for AI agent skills and MCP servers. Detects secrets, CVEs, supply chain attacks, and prompt injection in SKILL.md files before they're installed. Pre-install gate for Claude Code, Op
SkillMIT★ 3Few starsNo key
A curated collection of technical skill documentation. Covers Claude API integration, prompt engineering, agentic AI systems, backend architecture, and product management. Organized markdown guides fo
SkillMIT★ 2Few starsNo key
A tool to scan skills files for dangerous patterns & malicious intent
SkillMIT★ 1Few starsNo key
Turn social-media creators' videos into a searchable, curated knowledge base — Next.js download/manage app + GPU transcription (faster-whisper) + RAG
SkillMIT★ 12No key
A society of AI agents with impeccable standards and zero tolerance for 'fix stuff' commits.
Node.jsMIT★ 2Few starsNo key
MCP server that enables your agents to use coding rules from any or your GitHub repository. Instead of workspace rules files, you can now prompt agents to access the your coding rules from any reposit
Node.jsMIT★ 13No key
NFA - Nonfunctional, Functional, Agentic. The requirements doc you write before your coding agent writes code. Template, worked example, agent prompts.
SkillMIT★ 2Few starsNo key
Who stands behind it
