DeepSeek-OCR-WebUIvsVisionState
Two self-hosted projects, compared on the numbers selfhost.directory tracks live: score, popularity, release cadence and setup effort.
| DeepSeek-OCR-WebUI | VisionState | |
|---|---|---|
| Score | 47/100 | 48/100 |
| Rank in category | #3 of 4 in OCR | #77 of 104 in Home Automation |
| GitHub stars | 447 | 171 |
| Stars, last 30 days | — | +40 |
| Stable releases, 12 months | 0 | 20 |
| Latest release | — | v0.11.0 · 27 Oct 2026 |
| Setup | Advanced | Moderate |
| Official Docker image | Yes | No |
| License | MIT | Apache-2.0 |
| Main language | Typescript | Python |
Which one should you pick?
VisionState scores 48/100 against 47/100 for DeepSeek-OCR-WebUI, so it is the safer default.
VisionState ships more often: 20 stable releases in the past year, against 0 for DeepSeek-OCR-WebUI.
If you want the quickest setup, VisionState is easier to run; DeepSeek-OCR-WebUI needs more configuration.
VisionState is growing faster right now (+40 stars in 30 days).
DeepSeek-OCR-WebUI details →VisionState details →
Swap a project
Keep DeepSeek-OCR-WebUI, compare it with
Keep VisionState, compare it with