MCP servers and skills: search, filter by where they run, and compare.
An open-source personal knowledge workspace for you and your AI agents. Connect ideas, explore an interactive knowledge map, and trace answers to sources. Mac + Codex first.
PythonApache-2.0Few starsNo 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
Reliable memory and context infrastructure for AI coding agents: source-backed facts, review-gated learning, MCP/SDK/UI, and replaceable Qdrant/Graphiti retrieval.
PythonApache-2.0★ 7No key
Memory and continuity for Claude Code, Codex, Cursor, pi.dev and similar.
PythonMIT★ 5No key
A Hermes-based learning system that gets super personalized and builds routine around your life. It builds real, deepresearch-based courses and grades what you learned, asks for proof — your calendar,
SkillMIT★ 3Few starsNo 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
Research project: Personal local AI collaborator exploring cognitive architectures and agentic systems
PythonMIT★ 3Few starsNo key
An AI tutor prototype that uses Obsidian notes and iMessage check-ins to help interrupted study resume.
SkillMIT★ 1Few starsNo 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
Codex skill for converting handwritten math notes into Obsidian-ready Markdown
SkillMIT★ 3Few 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
A Codex skill for Linux embedded learning, bringup, debugging, source reading, and performance work. This skill is designed as a broad Linux embedded development companion rather than a narrow single-
SkillMIT★ 5No 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
Self-hosted PII exposure detection and personal data removal system. Scans public sources for data leaks and automates removal requests.
PythonMIT★ 4Few starsNo key
Local MCP server for a Zotero + MinerU + Tencent ima literature pipeline.
PythonMIT★ 1Few 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
Multi-backend, agent-friendly forecasting for publishable charts, cards, markdown, and JSON.
PythonMIT★ 3Few 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
Who stands behind it
