MT Photos AI
MT Photos AI is a self-hosted API service that adds text recognition via OCR (optical character recognition), image-content understanding, and image search by…
Platform availability
Available on 1 of 9 platforms
- Unraid
- TrueNAS (not listed)
- Umbrel (not listed)
- ZimaOS (not listed)
- Proxmox (not listed)
- Helm (not listed)
- Mac (not listed)
- Windows (not listed)
- Linux (not listed)
Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.
48/100 Fair
- Maintained
- 58last commit 176 days ago
- Popular
- 41116 GitHub stars
- Easy to install
- 351 install platform, install notes, Docker image
- Light to run
- No data
Based on 3 of 4 factors.
Availability: platform listings confirmed today, links checked 11 days ago
- GitHub stars
- 116
- Open issues
- 8
- Last commit
- 2026-04-22
- Latest release
- v1.2.0
- Activity
- stale
Checked 9 days ago - source: GitHub (MT-Photos/mt-photos-ai)
Resources & Compatibility
ARM (e.g. Raspberry Pi) is supported.
Checked 17 days ago - source: Docker Hub image tags and published docs
First-install notes
- Choose the image variant for your hardware Run the AI service as a separate container and pick the image tag to match your hardware: onnx-latest (or latest) for a standard x86_64 CPU, or a CUDA tag such as cuda-latest or cuda-12.4 when you have an NVIDIA GPU. source
Fetched 9 days ago - each note links to its source
Variants
Alternatives
No alternatives collected yet.
Common questions
What port does MT Photos AI 1.2.0 use by default?
The default port changed from 8000 to 8060. Use that port in MT Photos and map it if the service is run in a container.
How can I keep MT Photos AI running in the background on Windows?
Register mt-photos-ai-server.exe as a Windows service with NSSM, because closing the console window stops the API.
What connection details should I enter in MT Photos for the AI API?
Enter the AI host IP and port, such as 8060, and use the default API_AUTH_KEY mt_photos_ai_extra unless it was changed in .env.
What should I do if the Windows program flashes and exits immediately?
This can be caused by missing Visual C++ runtime DLLs. Install Microsoft Visual C++ redistributable vc_redist.x64.exe, then start MT Photos AI again.
Answers sourced from mtmt.tech
Community
- Topaz Community (other)
- mtPhotos's Content - Unraid (forum)
Collected 16 days ago - public community threads