ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
Local persistent memory store for LLM applications including continue.dev, cursor, claude desktop, github copilot, codex, antigravity, etc.
An MCP server for converting Markdown to interactive mind maps with export support (PNG/JPG/SVG).
Transform YouTube videos into a compounding knowledge base with transcripts, vision analysis, and agentic search. Works as an MCP server for Claude, Copilot & more.
MCP server for reverse engineering tasks in Ghidra 👩💻
28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools
MCP Server with ArcGIS Pro Add-In
Use cultivar to test your Agent Skills, run them in sandboxes, and across different agents.
Batch-download reference PDFs from a DOI or paper PDF using Crossref and your institutional Edge session.
Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Docker deployment.
A memory system using mem0 for AI applications. Enables long-term memory for AI agents as a drop-in MCP server.
Stop your AI coding agent from reinventing the wheel. A Claude Skill that checks Free vs. Build vs. Buy before writing code, and actually vets what it finds (license, maintenance, security) instead of stopping at star count
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure
Connect Cursor, Copilot & Claude AI directly to Cheat Engine via MCP. Automate reverse engineering, pointer scanning, and memory analysis using natural language.
Marketing frameworks that AI actually executes. Designed for Claude Code, but could be used for OpenClaw, etc.
Thinking partner skill for AI agents — 150+ mental models, orientation detection, cognitive operations. Works with Claude Code, Cursor, Windsurf, Cline, GitHub Copilot.
Raindrop MCP Server
WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.
Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.
make agents think, thoroughly
One SQL interface for 60+ tools (e.g., GitHub, Notion, Airtable). Plug into any LLM through MCP.
Turn any website into a compact CLI tailored for AI agents. Browse the web in hundreds of tokens, not tens of thousands.