HN Showcase
Back to browse
GitHub Repository

Wrapper for Chromium screen-ai OCR

21 starsPython

Locro – Fast and accurate local OCR through Chrome's screen_ai

by zzleeper·Mar 24, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidShip ItBig Brain

Unlocks Chrome's hidden OCR engine for Python without launching a browser window.

Strengths
  • •Bypasses browser overhead by calling screen_ai library directly via ctypes.
  • •Supports PDFs and images across Windows and Linux out of the box.
  • •Significantly faster than Tesseract for standard text extraction tasks.
Weaknesses
  • •Depends on Chrome's internal ABI stability; updates could break compatibility.
  • •macOS support missing, requires manual porting despite author's claims.
Target Audience

Python developers, data engineers needing local OCR

Similar To

Tesseract · EasyOCR · Google Cloud Vision

Post Description

A month ago, @Stagnant posted in this thread about how Chrome ships with a open source OCR tool that is only available from the browser:

https://news.ycombinator.com/item?id=46977802

This looked incredibly useful but sadly there were no Python wrappers, so I followed his instructions and built one.

It's incredibly fast and accurate (I had my doubts but wow!). I tested the Windows and Linux implementations, and I'm sure expanding the wrapper for macOS should be trivial for a decent LLM.

Hope it's also useful to other users, and thanks again Stagnant for mentioning it in the first place!

Similar Projects

Developer Tools●●Solid

Dracula-AI – A lightweight, async SQLite-backed Gemini wrapper

SQLite memory beats JSON bloat; async streaming works—but it's still a Gemini wrapper.

Ship ItSolve My Problem
suleymanibis
203mo ago