// Read docs & web pages
Umi-OCR
Free offline OCR for screenshots, batch images and PDFs.
Open source Maintained Dual-use For agents
IN ONE PARAGRAPH
Umi-OCR is free offline OCR for screenshots, batch images and PDFs.
Good for: Developers who want their agent (Claude Code, Codex, Cursor…) to read docs & web pages.
Not for: people who don’t want to install and run tools themselves.
01How to start
- 1Read the official README for requirements and permissions.
- 2Install it as the official guide describes.
- 3Tell your agent the command exists (e.g. in AGENTS.md / CLAUDE.md) so it knows when to call it.
02Alternatives & comparison
Compare side by side →03Related
Versions, why it is listed, for AI to read
Popularity evidence (third-party snapshots)
- GitHub stars:47,700 · whatstrending.ai 2026-10-10
- GitHub stars:47,546 · repos.ecosyste.ms 2026-10-10
- GitHub stars:47,796 · repos.ecosyste.ms 2026-10-12
- GitHub stars:47,796 · repos.ecosyste.ms 2026-10-13
- GitHub stars:47,796 · repos.ecosyste.ms 2026-10-14
- GitHub stars:47,796 · repos.ecosyste.ms 2026-10-15
- GitHub stars:47,796 · repos.ecosyste.ms 2026-10-16
- GitHub stars:47,796 · repos.ecosyste.ms 2026-10-19
- GitHub stars:48,022 · repos.ecosyste.ms 2026-10-20
- GitHub stars:48,022 · repos.ecosyste.ms 2026-10-21
- GitHub stars:48,022 · repos.ecosyste.ms 2026-10-22
For AI agents
- Interfaces:its own app or website
- Machine-readable record:/api/v1/software/umi-ocr.json · llms.txt
- Added 2026-10-10 · updated 2026-10-22