MCP servers and skills: search, filter by where they run, and compare.
MCP server that transforms linear AI reasoning into structured, auditable thought graphs
Node.jsMITFew starsNo key
Official Python SDK + MCP protocol implementation for LogicMem — the memory server for AI agents. Includes A2A agent-to-agent sharing, audit chain, and reasoning engine.
SkillMIT★ 1Few starsNo key
Open-source Repository Intelligence & Code Reasoning Engine
PythonApache-2.0★ 2Few starsNo key
28 agentic design pattern skills for Gemini CLI, Antigravity, and Claude Code. Supports English, Korean, Japanese, and Chinese triggers.
SkillMIT★ 4Few starsNo key
Mechanistic-reasoning engine for the environmental exposome of neurodegeneration. Uses AI to recover causal pathways for Parkinson's and Alzheimer's.
GoMITFew starsNo key
Graph analysis and visualization toolkit built in Python and Rust with PyPI distribution.
PythonMIT★ 6No key
SOTA NPM module for agentic processes using local or cloud LLMs.
SkillMIT★ 5No key
Multi-round extended thinking critic performing backtracking, hypothesis testing, and factual ground checks
SkillLink only★ 7
Multi-round extended thinking critic performing backtracking, hypothesis testing, and factual ground checks
SkillLink only★ 7
Monotropic Deep-Systems Reasoning for Agents — depth-first systems reasoning, complementary to breadth-first divergent ideation
SkillMIT★ 2Few starsNo key
Local-first MCP server, CLI and SDK for evidence, formal checks, planning and experimental image-to-3D workflows. Includes real mesh demonstrations, reproducible comparisons and model provenance. Deve
Node.jsMITFew starsNo key
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms.
SkillMIT★ 1Few starsNo key
Sparse Mixture-of-Experts (MoE) router and code reasoning engine (Mistral style)
SkillLink only★ 8
PythonCC0-1.0★ 1Few starsNo key
Xploit47 — systematic AI-powered penetration testing reasoning MCP server (Beam Search + MCTS attack path planning)
Node.jsMIT★ 1Few starsNo key
A systematic, AI-powered penetration testing reasoning engine (MCP server) for attack path planning, CTF/HTB solving, and automated pentest workflows. Features Beam Search, MCTS, attack step scoring,
SkillMITFew starsNo key
MCP server for recursive deep reasoning — structured what-if analysis trees for Claude Code
PythonMITFew starsNo key
Expert cybersecurity skill for Claude — OWASP, NIST CSF, ISO 27001, CIS Controls, LLM Security
SkillMIT★ 1Few starsNo key
Multi-agent reasoning MCP server for Claude Code. Spawns parallel research agents to find knowledge LLMs don't have. +23.1% on Terminal Bench 2.0 SWE tasks.
SkillMIT★ 1Few starsNo key
🧠 Self-growing Claude agent skill system — auto-discovers, fetches from GitHub, creates via web research, and self-improves. Works in Claude.ai + Claude Code.
SkillMITFew starsNo key
Neuromorphic threat intelligence for AI agents — this MCP server applies **8 brain-inspired and mathematical frameworks** to cyber threat detection, pulling live data from **15 sources** spanning vuln
SkillMITFew starsNo key
Epistemic reasoning engine for AI Agents — assess claim credibility with calibrated confidence. Includes a ready-to-use .skill package for agent frameworks. 87%+ accuracy with evidence, 85%+ abstain w
SkillLink only★ 2Few stars
Persistent project memory powered by Cognee. Engram captures the why behind your code using a local-first knowledge graph
SkillMITFew starsNo key
AI Diagnostic Reasoning Engine — Claude Code plugin for clinical differential diagnosis with Bayesian reasoning, safety scanning, and multi-causal analysis
SkillLink onlyFew stars
Who stands behind it
