Browse / LLM wiki / Second brain / matryca-plumber
matryca-plumber
MarcoPorcellato
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).
Open MarcoPorcellato/matryca-plumber → Does not match the four rules.
agentic-memoryai-agentsandrej-karpathyautonomous-agentsfastmcpknowledge-graphllmllm-wikillm-wiki-karpathylocal-firstlogseqmarkdown
Works with any agent
ships AGENTS.md, the cross-tool instruction file.
In its own words
Karpathy LLM-Wiki inspired.
I gave an AI agent access to my notes. It corrupted them. I built Matryca Plumber so that never happens again.
v2.0.0 is stable and available now. Matryca Plumber's default-on external Shadow DB, Strict Read Only protection, Markdown authority, and fail-closed fallback contract are now published on GitHub Releases and PyPI. Read the release record and changelog for the exact scope and upgrade notes.
Local-first agentic memory and maintenance for Logseq OG. Matryca Plumber gives humans and agents one safe, structured interface to a Markdown knowledge graph—without turning an opaque database or a model provider into the owner of that knowledge.
Quick start · Why Matryca · Memory model · Architecture · Shadow DB · v2.0.0 release · Agent guide · Documentation
Quick start
Requires Python 3.12 or newer and a Logseq OG graph.
Open select a cloned Logseq graph, review the pre-flight checks, and start the engine when ready.
Start with a clone of your graph, especially before enabling writes or applying an import. See the operator contract, security policy, and support guide.
To install the stable release explicitly:
What v2.0.0 changes
The stable v2 release makes the Shadow read path a practical default while keeping ownership and mutation boundaries explicit:
- External Shadow DB by default: healthy FTS5 and subtree reads use a disposable
cache outside the Logseq graph; set MATRYCA_SHADOW_DB_ENABLED=false to opt out.
The repository's own description, then 19% of its README. Read the rest on GitHub ↗
Read from the repository's git tree on 2026-08-17.