Open-source alternatives to Google Document AI
2 open-source projects that do what Google Document AI does. Picked or featured by Willet; numbers are from GitHub.
Last updated
| Project | What it does | Stars | License | Last commit | Self-hostable |
|---|---|---|---|---|---|
| OCR model converting scanned pages and PDFs into layout-aware Markdown | 12.5k | Apache-2.0 | No | ||
| Self-hosted platform for extracting structured JSON from documents with LLMs | 7.3k | AGPL-3.0 | Yes |