GitHub Repository

Turn articles and book chapters into linked reading trees you can browse alongside the original text.

2 starsJavaScript

Reading Tree, a weighted outline for articles instead of a summary

Name: Reading Tree, a weighted outline for articles instead of a summary
Availability: InStock
Author: ModelVoyager

by ModelVoyager·Mar 26, 2026·2 points·2 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainNiche Gem

Bidirectional links between outline nodes and source paragraphs beat lossy AI summaries.

Strengths

•Weighted importance nodes show argument structure at a glance, not just flat summaries.
•Bidirectional linking preserves original text while adding navigable structure layer.
•Produces static HTML output—no signup, works offline, no vendor lock-in.

Weaknesses

•Only tested with Claude Opus 4.6 and GPT-5.4 Thinking, fragile model dependency.
•Essentially prompt engineering wrapper, not standalone application with own infrastructure.

Post Description

I built this for close reading, especially philosophy chapters, long essays, and dense nonfiction. AI summaries are useful in many cases, but sometimes the source is good enough that I want to read it properly, not just get the gist. Those are exactly the cases where a summary can leave out the parts I would care about most.

Reading Tree keeps the original words in place. Every node links to the passage it covers, and every paragraph links back to the node that explains its role. Nodes are weighted by importance so you can see at a glance which parts carry the most weight.

Demo (desktop only): https://modelvoyager.github.io/ReadingTree/on-liberty-ch1-re...

GitHub: github.com/ModelVoyager/ReadingTree

It's an agent skill (a set of instructions and templates you upload to an AI chat) that works with Claude and ChatGPT. Only tested with Claude Opus 4.6 (extended thinking) and GPT-5.4 Thinking. Other models may not produce usable results. Free and open source. I designed the interaction model and UX, then used AI to build it out. Most of the effort went into actually reading with it and fixing what didn't work.

I've been the only user for a few weeks. If you read things where the argument structure matters and summaries feel like they lose too much, I'd like to hear whether this helps.