3 jobs · 6 apps
Best open source OCR tools you can self-host
To turn scans into searchable text, the best self-hosted picks are Paperless-ngx for searchable document archives, Stirling-PDF for OCR on PDFs and images and TaxHacker for reading receipts.
Every app here mentions OCR (optical character recognition) in its own description or topics: PDF toolkits that run OCR on files, and document archives that OCR every scan they ingest.
Updated · data from GitHub, refreshed daily
Top picks
- Rank 1:
Paperless-ngx
paperless-ngx/paperless-ngx
Scan, index, and archive all of your paper documents with an improved interface (fork of Paperless).
Active · last commit Oct 28, 2026
Document ManagementPythonDockerAI-nativeStands out for AI features named in its own description. Paperless-ngx has 47,176 GitHub stars, uses the GPL-3.0 license, ships a Docker image and had 1,786 commits in the last year.
- Rank 2:
Docspell
eikek/docspell
Auto-tagging document organizer and archive.
Active · last commit Oct 27, 2026
Document ManagementElmDockerStands out for its Elm codebase. Docspell has 2,342 GitHub stars, uses the AGPL-3.0 license, ships a Docker image and had 88 commits in the last year.
- Rank 3:
Papermerge
papermerge/papermerge-core
Document management system focused on scanned documents (electronic archives). Features file browsing in similar way to dropbox/google drive. OCR, full text search, text overlay/selection.
Active · last commit Oct 27, 2026
Document ManagementPythonDockerStands out for a permissive Apache-2.0 license. Papermerge has 549 GitHub stars, uses the Apache-2.0 license, ships a Docker image and had 232 commits in the last year.
At a glance
Open source OCR tools you can self-host compared
Picked by hand for each job from apps whose own description or topics match it, in curated order inside each section, with GitHub data from October 2026; an app appears only once.
| App | Stands out for | License | GitHub stars | Commits (12 mo) | Last commit | Docker image |
|---|---|---|---|---|---|---|
| Paperless-ngx | AI features named in its own description | GPL-3.0 | 47,176 | 1,786 | Oct 28, 2026 | Yes |
| Docspell | its Elm codebase | AGPL-3.0 | 2,342 | 88 | Oct 27, 2026 | Yes |
| Papermerge | a permissive Apache-2.0 license | Apache-2.0 | 549 | 232 | Oct 27, 2026 | Yes |
| Stirling-PDF | the most GitHub stars | Apache-2.0 | 95,215 | 2,068 | Oct 28, 2026 | Yes |
| SnapOtter | the most commits in the last 12 months (3,694) | AGPL-3.0 | 2,870 | 3,694 | Oct 28, 2026 | Yes |
| TaxHacker | – | MIT | 6,764 | 68 | Sep 28, 2026 | Yes |
1 of 3 · 3 picks
Document archives with OCR
- 1
Paperless-ngx
Scan, index, and archive all of your paper documents with an improved interface (fork of Paperless).
Document ManagementDockerAI-nativeStands out for AI features named in its own description. Paperless-ngx has 47,176 GitHub stars, uses the GPL-3.0 license, ships a Docker image and had 1,786 commits in the last year.
- 2
Docspell
Auto-tagging document organizer and archive.
Document ManagementDockerStands out for its Elm codebase. Docspell has 2,342 GitHub stars, uses the AGPL-3.0 license, ships a Docker image and had 88 commits in the last year.
- 3
Papermerge
Document management system focused on scanned documents (electronic archives). Features file browsing in similar way to dropbox/google drive. OCR, full text search, text overlay/selection.
Document ManagementDockerStands out for a permissive Apache-2.0 license. Papermerge has 549 GitHub stars, uses the Apache-2.0 license, ships a Docker image and had 232 commits in the last year.
2 of 3 · 2 picks
PDF and file toolkits with OCR
- 1
Stirling-PDF
Local hosted web application that allows you to perform various operations on PDF files, such as merging, splitting, file conversions and OCR.
Document ManagementDockerStands out for the most GitHub stars. Stirling-PDF has 95,215 GitHub stars, uses the Apache-2.0 license, ships a Docker image and had 2,068 commits in the last year; it replaces Adobe Acrobat.
- 2
SnapOtter
Suite of 200+ web tools for converting and editing images, videos, audio and PDFs, including a layer-based image editor, OCR, transcription, background removal and batch processing pipelines…
Document ManagementDockerAI-nativeStands out for the most commits in the last 12 months (3,694). SnapOtter has 2,870 GitHub stars, uses the AGPL-3.0 license, ships a Docker image and had 3,694 commits in the last year.
3 of 3 · 1 pick
Receipts and invoices
- 1
TaxHacker
Self-hosted AI accounting app that extracts data from receipts and invoices, converts currencies and organizes income and expenses.
Accounting & InvoicingDockerAI-nativeTaxHacker has 6,764 GitHub stars, uses the MIT license, ships a Docker image and had 68 commits in the last year.
Which open source OCR tool is best for scanned paper?
Paperless-ngx is built for it: scan, index and archive paper documents, with OCR so they become searchable. Docspell and Papermerge are document archives in the same spirit.
Is Paperless-ngx free?
Yes. Paperless-ngx is open-source software released under the GPL-3.0 license, so you can self-host it at no cost. You only pay for the server it runs on, and some projects also offer an optional paid cloud plan.
Can I run this stack with Docker?
All 6 apps here publish Docker images, including Paperless-ngx, Docspell and Papermerge, so most of the stack can run side by side with Docker Compose on one server. Size the server for the heaviest app and add off-site backups.
How is this list ranked?
Picked by hand for each job from apps whose own description or topics match it, in curated order inside each section, with GitHub data from October 2026; an app appears only once.
The weekly digest
New self-hosted apps, every week
Fresh releases, rising projects and one deploy guide a week. Join home labbers and engineers who self-host.