MarcoPorcellato/matryca-plumber

View on GitHub ↗

Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud, no Logseq API). Karpathy LLM-Wiki inspired.

91 ★17 forksPythonUpdated 18d ago

What you need to know

Local-first, 100% offline data-orchestration MCP server (FastMCP stdio) with extensive testing

Install

Python 3.12+ with pip

Usage

  • Orchestrate data pipelines fully offline via MCP

Key features

  • 100% offline data orchestration
  • large test suite (1139+ tests, coverage >= 70%)
  • mypy strict, Ruff

Best for

Offline data workflows

Caveats

  • Python 3.12+; macOS/Linux/Windows
Platforms: macOS · Linux · WindowsClients: Claude · any MCP client

Reviewed 2026-08-11

Topics

agentic-memoryai-agentsandrej-karpathyautonomous-agentsfastmcpknowledge-graphllmllm-wikillm-wiki-karpathylocal-firstlogseqmarkdownmatrycamcpmodel-context-protocoloutlinerpkmpythonragsecond-brain
Stars
91★
Forks
17
Language
Python
License
Apache-2.0
Created
2026-05-17
Last push
2026-08-18