MarcoPorcellato

MarcoPorcellato / logseq-matryca-parser

Public

Stop feeding broken Markdown to your AI. A deterministic Logseq parser that preserves parent-child context for RAG, plus a 60FPS visualizer.

ai ast knowledge-graph local-first logseq
10
1
100% credibility
Found Apr 28, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A tool that reads Logseq note collections, preserves their structure, and creates interactive visualizations or exports ready for AI use.

How It Works

1
🔍 Discover the tool

You find this helpful tool while browsing for ways to better understand your Logseq notes, and try the free online demo to see your thoughts as a beautiful connected map.

2
📥 Get it ready

Download and set up the tool on your computer in just a few minutes, no complicated steps needed.

3
📁 Pick your notes folder

Point the tool to the folder where your Logseq notes live, like your pages and daily journals.

4
⚡ Watch the magic scan

In seconds, it reads your entire collection of notes, perfectly preserving the hierarchy and connections between ideas.

5
Choose your adventure
🗺️
Make an interactive map

Generate a stunning, zoomable visual of your knowledge graph that you can explore and filter.

📤
Prepare for smart AI

Export clean, structured notes ready to chat with AI assistants without losing context.

📊
Get quick insights

Scan for stats like total ideas, connections, and tasks across your notes.

🎉 Enjoy the results

Open your new brain map or AI-ready files and feel the power of seeing your thoughts connected and alive.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is logseq-matryca-parser?

This Python tool parses Logseq graphs from pages and journals, building a structured AST that keeps parent-child hierarchies intact instead of blindly chunking text. It stops feeding broken Markdown to your AI by exporting clean JSON, flat Markdown, or RAG-ready documents for LangChain and LlamaIndex, plus a CLI for scanning stats and demos. Run `matryca-parse visualize /path/to/graph output.html` for a local graph explorer, or use the Python API to parse pages directly.

Why is it gaining traction?

Unlike generic Markdown splitters that trash context, it delivers deterministic parsing at high speed—901 pages in 32 seconds—and injects hierarchy into AI metadata so LLMs grasp note relationships. The 60FPS visualizer with ForceAtlas2 physics and filters (hide journals/tags) lets you explore 10k+ node graphs smoothly in HTML. Privacy-first, local-only design appeals to sovereign PKM users tired of leaky cloud tools.

Who should use this?

Logseq power users feeding graphs into local RAG pipelines for custom AI queries. PKM devs visualizing knowledge topologies without Obsidian plugins. AI engineers at startups building second-brain retrieval who need structured exports over raw dumps.

Verdict

Solid alpha with excellent README, CLI, and live demo—install via pip and test in minutes—but only 10 stars and 1.0% credibility signal low adoption and unproven scale. Worth a spin if Logseq+RAG is your jam; skip for production until more battle-tested.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.