cd /news/artificial-intelligence/i-built-deepread-an-evidence-first-r… · home topics artificial-intelligence article
[ARTICLE · art-98894] src=dev.to ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

I Built DeepRead: An Evidence-First Reading Skill for Articles, Books, and PDFs

A developer has released DeepRead, an open-source tool that transforms articles, books, and PDFs into structured reports centered on claims, evidence, data, and relationships. The tool links important claims to supporting evidence and source locations, explicitly noting when evidence is absent, and can compare multiple documents to identify agreements and conflicts. DeepRead is MIT-licensed and available on GitHub.

read2 min views1 publishedAug 16, 2026

I recently built an open-source project called DeepRead to solve a problem I kept seeing with AI reading tools.

Most tools can summarize a document quickly, but they often blur the line between the author's actual claims, the evidence provided by the source, and the model's own inferences. With long documents, source locations and the context around numerical claims can also disappear.

DeepRead turns articles, books, PDFs, and document sets into structured reports organized around claims, evidence, data, and relationships. Important claims are linked to supporting evidence and source locations. If the source does not provide evidence, the report says so instead of filling the gap.

quick

deep

map

feynman

book

DeepRead can also compare 2–10 documents and identify agreements, conflicts, and complementary evidence.

The portable skill has no additional runtime dependencies:

npx skills@latest add xiehuan123/dsh-deepread

Example prompt:

Deep-read architecture.pdf in knowledge-map mode.
For every important claim, show the supporting evidence and page location.

The full plugin includes a reading panel, PDF extraction, background jobs, live progress, batch comparison, cost estimates, and Markdown, HTML, or XMind-compatible export.

dsh plugin --profile web add dsh-deepread

GitHub:

https://github.com/xiehuan123/dsh-deepread

v0.5.4 Release:

https://github.com/xiehuan123/dsh-deepread/releases/tag/v0.5.4

The repository contains three real output examples rather than hand-written mockups. DeepRead has already been included in several DeepSeek Harness and DSH community collections. Its GitHub Awesome Copilot submission has also passed the automated specification, lint, installation, and version checks and is waiting for maintainer review.

The project is MIT licensed. I would especially like feedback on one question:

Is explicit claim-to-evidence tracing useful in your reading workflow, or does it make the report too heavy?

Issues and pull requests are welcome.

Suggested DEV tags: showdev

, opensource

, ai

, productivity

Suggested Show HN title: Show HN: DeepRead – Evidence-first reading for books, articles, and PDFs

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @deepread 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/i-built-deepread-an-…] indexed:0 read:2min 2026-08-16 ·