ai-agent

immich: Self-Hosted Media

Get high-performance photo and video management with immich, a solution.
108,804 stars6,342 forksTypeScriptGuide quality 9/10Updated 7/26/2026100% free · open source
What it does

Immich is a high-performance self-hosted photo and video management solution that allows you to store, organize, and analyze your media files in a private and secure environment.

When to use it
  • When you need to manage a large collection of photos and videos across multiple devices
  • When you want to keep your media files private and secure, without relying on cloud services
  • When you need to automate tasks such as tagging, categorization, and album creation for your media files
Ready-to-paste prompt
curl -X POST -F 'file=@/path/to/image.jpg' http://localhost:2283/api/upload -H 'Content-Type: application/json' -d '{"tags": ["vacation", "beach"]}'
Heads up: You need to have Docker and Docker Compose installed on your system, and you must configure the 'docker-compose.yml' file to use a valid PostgreSQL database connection
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/immich && curl -fsSL https://workflowstacks.com/api/skills/immich/claude-skill -o ~/.claude/skills/immich/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How immich: Self-Hosted Media works
Codeflow
Free to inspect

Immich: Self-Hosted Media is a very large TypeScript project (~299k lines across 2437 code files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, AGPL-3.0 license, has a test suite.

Size
Very large codebase
~299k lines · 2437 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js · Docker
No API keys detected
TypeScript 52%Dart 29%Svelte 13%Python 2%Kotlin 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    package.json
    Dependencies and the commands it exposes
What's in each folder
mobile/Folder1241 files
web/Frontend / UI741 files
server/Backend / API683 files
docs/Documentation295 files
i18n/Translations89 files
e2e/Tests — proof it works87 files
packages/Sub-packages / plugins62 files
machine-learning/Folder51 files
READMEHas testsDocumentedCI checksDocker readyAGPL-3.0 licenseUpdated this month
Quick Actions
Details
Creator
immich-app
Language
TypeScript
Category
ai-agent
Published
2/3/2022

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.