MCP servers and skills: search, filter by where they run, and compare.
Context-aware marketing skills for Claude Code, with B2B, industrial, regulated, and consumer playbooks.
SkillMITFew starsNo key
Defensive security audit tool for AI Agent and MCP (Model Context Protocol) environments. Detects risky localhost exposure, weak bindings, and confused-deputy risks. Lightweight, SARIF + HTML reports,
SkillMIT★ 1Few starsNo key
Drive your coding-agent fleet from your pocket. A local-first cockpit and context store for CLI coding agents.
SkillApache-2.0★ 3Few starsNo key
MCP server for managing and serving AI Agent skills via Model Context Protocol
SkillMITFew starsNo key
CLI that convenes Claude sub-agents as an AI advisory board to discuss business questions. Multi-round conversations with orchestrator-gated turns, HITL clarifications, a web dashboard with live strea
SkillApache-2.0★ 1Few starsNo key
Counts how many copies of each MCP server your Claude Code, Codex and Grok sessions are running, and plans which to share, remove or keep. Read-only.
SkillMIT★ 5No key
Knowledge docs for agents. Git-native MDX. Publish on merge.
SkillMIT★ 2Few starsNo key
Keep secrets out of agent context while giving local commands scoped access.
SkillMIT★ 1Few starsNo key
Git for agent beliefs — a governed memory broker for AI agents with provenance, approval, and rollback enforced in code, not prompts.
SkillMIT★ 2Few starsNo key
SkillMIT★ 1Few starsNo key
Sanitized Codex skill for direct WeChat public-account drafting in 135 Editor.
SkillMIT★ 4Few starsNo key
Claude Code autopilot with self-healing memory: one command → build → test → localhost. Trajectory tracking, learned routing, and stop-hook enforcement across runs.
SkillLink only★ 7
Claude Code skill for context-efficient browser automation via subagents
SkillMITFew starsNo key
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or crea
OfficialSkillMIT★ 40k in collectionNo key
Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-
SkillAGPL-3.0★ 1.6kNo key
A Go-based platform for running AI agents on schedules with tasks, skills, and persistent memory. Single binary, three operating modes — from single-node to distributed.
SkillMIT★ 5No key
An open registry of 76 fully specified AI agent skills — taxonomy, canonical schema, composer, governance model, and a fleet runner that deploys hundreds of agents against one objective and rehearses
SkillMIT★ 6No key
Full Chromium automation in 3 tools, 3.9 KB. Same pages, same clicks, same scrapes — without the 24-tool handshake eating your context window before you load a page.
SkillMITFew starsNo key
Hermes Agent skill: research-grounded maintenance for three-layer agent memory (local L1, Hindsight L2, LLM-wiki L3)
SkillMIT★ 2Few starsNo key
Turn scattered links into a structured, queryable Markdown bookmark library for AI agents.
SkillMITFew starsNo key
It leverages the latest versions of the RuVector architecture to build knowledge base-based applications.
SkillMIT★ 1Few starsNo key
Let AI coding assistants remember your team's knowledge across sessions
SkillMIT★ 2Few starsNo key
Who stands behind it
