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
MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.
PythonMIT★ 346No 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
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
Research project: Personal local AI collaborator exploring cognitive architectures and agentic systems
PythonMIT★ 3Few 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
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
🎓 一键同步 UNSW Moodle 课件，然后让 AI 陪你复习 | Sync your Moodle course materials, then let AI revise them with you — built-in MCP server for Claude Code, Obsidian export, spaced-repetition planning
PythonMIT★ 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
Local-first, Obsidian-aware RAG MCP server — hybrid retrieval (dense + BM25 + RRF), contextual retrieval, and cross-encoder reranking on a Clean Architecture skeleton.
PythonMITFew starsNo key
PythonMIT★ 1Few starsNo key
MCP server exposing StudyLife (self-hosted study platform) data to Claude and other MCP clients.
PythonAGPL-3.0Few starsNo key
Cognitive memory substrate for AI agents that encodes selectively, consolidates autonomously, and shares context across sessions.
PythonMIT★ 1Few starsNo key
PythonMITFew starsNo key
Who stands behind it
