A-Eye

A-Eye is a self-hosted AI photo intelligence tool that uses a local Ollama vision model to understand, describe, tag, and rename your photos — no cloud…

  • AI
  • Media Applications
  • Productivity
  • Tools & Utilities
A-Eye is a self-hosted AI photo intelligence tool that uses a local Ollama vision model to understand, describe, tag, and rename your photos — no cloud required, everything runs on your own hardware. Supports automatic renaming, manual review mode, XMP sidecar writing (compatible with Immich, Lightroom, and digiKam), natural language photo search, quality detection for blurry or accidental shots, and a temporary workspace for processing photos from other devices. Works as a full photo renamer, a metadata enrichment tool, or a non-destructive read-only catalogue.

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.

60/100 Good

Maintained
73last commit 46 days ago
Popular
41113 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
No data
Security check
85no serious findings, tests

Based on 4 of 5 factors.

Availability: platform listings confirmed today, links checked 14 days ago

GitHub stars
113
Open issues
11
Last commit
2026-09-26
Activity
stale

Checked 20 days ago - source: GitHub (SpaceinvaderOne/a-eye)

Resources & Compatibility

Requirements not published yet.

Checked 43 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Docker / Compose Use the repository's docker-compose.yml for Docker installs; it runs A-Eye with Ollama for local vision-model processing. source
  • Ollama Dependency A-Eye requires a running Ollama instance with a vision-capable model (e.g., llava) to perform AI photo analysis. Start Ollama alongside the A-Eye container before first use. source

Fetched 28 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Does A-Eye require a cloud service to process photos?

No. It uses local vision models and runs on your own hardware.

Can A-Eye tag and rename photos in a local library?

Yes. It can understand, describe, tag, rename, and search photos locally.

Does A-Eye support natural language photo search?

Yes. You can install it locally and search photos by natural language.

Answers sourced from github.com, imtaqin.id

Community

Collected 36 days ago - public community threads