# karpathy/reader3

Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.

Repository: https://github.com/karpathy/reader3
Canonical: https://ross.abutalabs.com/products/reader3
Language: Python
License Family: other
Last push: 2025-11-18T02:37:51+00:00

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 52, release rhythm 35, longevity 20
- inputs: {"age_days": 289, "days_push": 289, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3842, forks 488 (observed 2026-08-28T04:08:24.011842+00:00)

## What it is
A lightweight, self-hosted EPUB reader web app that presents books one chapter at a time so users can easily copy text into an LLM and read along with it. It is a small Python demo project by Andrej Karpathy, explicitly provided as-is without support.

## Use cases
- read EPUB books alongside an LLM chapter by chapter
- self-host a simple epub reader with a local library
- copy book chapters into a chatbot for discussion
- load Project Gutenberg books for AI-assisted reading

## When to choose
- you want a minimal local epub reader designed for LLM-assisted reading
- you want a simple Python/uv example to hack on with an LLM

## When to avoid
- you need a full-featured epub reader with annotations and sync
- you need maintained, supported software

## Facets
- artifact type: application
- maturity: abandoned
- function: pdf, llm-inference, self-hosted, developer-tools
- domain: large-language-models, developer-tools, files
- platform: python, self-hosted, cross-platform
- tags: epub-reader, llm-assisted-reading, vibe-coded, demo-project, web-server

## Member repositories
- karpathy/reader3 (main) score 40

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:24.011842+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:26:13.160560+00:00, confidence not recorded.
  - readme: https://github.com/karpathy/reader3 (fetched 2026-08-28T04:08:24.011842+00:00, sha 43f9f6fe50a7)
- Data as of 2026-08-30T08:39:29.467469+00:00.