MCP servers and skills: search, filter by where they run, and compare.
The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.
SkillCC-BY-4.0★ 91No key
Multi-agent shared brain across Claude Code/Desktop, Codex, Gemini, Copilot, VS Code. Cross-session memory, self-improving skill loops, inter-agent signaling — one local MCP server.
PythonMIT★ 14No key
3D vision and medical imaging in one Python package: 73 algorithms, 43 datasets in one line, Open3D / SimpleITK / PyVista, MCP server for AI agents
PythonApache-2.0★ 8No key
Memory and continuity for Claude Code, Codex, Cursor, pi.dev and similar.
PythonMIT★ 5No key
Afterlife lets you, an agent running on a local model, nominate experiences from your activity for training into a small LoRA adapter to isekai your future self.
SkillApache-2.0★ 4Few starsNo key
A research harness for ML, built on the Claude Agent SDK. Claude Code with a literature funnel, a prediction ledger, and gates in front of every dollar.
SkillMIT★ 7No key
Agent-native, Git-backed product decision system: from customer evidence to a measured outcome, with the decision trail intact.
PythonApache-2.0★ 4Few starsNo key
AI skills and agents that research technologies and generate structured learning paths with runnable code labs, detailed explanations, and guided walkthroughs.
SkillMIT★ 1Few starsNo key
AI-assisted code review and release automation for Python repos — built to learn every Claude Code feature (agents, hooks, skills, slash commands, MCP).
PythonMIT★ 2Few starsNo key
Memory for AI agents you can cat, grep, and git. Markdown-native, MCP-compatible, you own the files.
PythonApache-2.0★ 2Few starsNo key
Compound-learning email skill for Claude Code — every reply feeds the reference, drafts snowball over time. CS / BD / recruiting / partnerships / sales 모두 사용 가능.
SkillMIT★ 4Few starsNo key
One shared memory for coding agents (Claude Code, Codex, Cursor) over MCP — token-budgeted recall that keeps context cost flat as memory grows, with a published benchmark and its controls
PythonMIT★ 1Few starsNo key
Persistent memory for AI coding assistants. Mines transcripts, deduplicates, makes them searchable.
PythonMIT★ 1Few starsNo key
Agent Memory — universal memory / learning / evolution infrastructure for AI agents (cross-session memory, auto-sedimentation, hybrid retrieval BM25+vector+Rerank)
SkillMIT★ 1Few starsNo key
Turn textbooks into adaptive AI tutoring. Knowledge graphs, problem-first learning, and memory across sessions.
SkillMIT★ 2Few starsNo key
MUSCLE - Self-learning code review that gets smarter with every task
SkillMIT★ 1Few starsNo key
Explain-it-back as an MCP connector: it grounds a check in your own sources, scores it with verified evidence (not model vibes), and resurfaces what you don't yet know. Local-first, opt-in, no telemet
PythonMITFew starsNo key
A micro-journaling tool to reflect on AI coding process -- Aims to provide data for insights
PythonAGPL-3.0Few starsNo key
MCP memory server for Claude Code: a git-diffable Markdown vault (opens in Obsidian) with hybrid semantic search, a wiki-link graph, and bi-temporal facts — plus hooks that pull context in automatical
PythonApache-2.0Few starsNo key
Explore AI agent architecture with deep dives, PDF notes, and a minimal Python teaching project for learning core agent structure
MCPLink only★ 1Few stars
Who stands behind it
