Repository files navigation

Anime Scene Search Engine

Trace back the scene where an anime screenshots is taken from.

It tells you which anime, which episode, and the exact moment this scene appears.

Try this image yourself.

Link to trace.moe from other websites, you can pass image URL in query string like this:

https://trace.moe/?url=https://images.plurk.com/32B15UXxymfSMwKGTObY5e.jpg

For Bots/Apps, refer tohttps://soruly.github.io/trace.moe-api/

This repo is just an index page for the whole trace.moe system. It consists of different parts as below:

Client-side:

• trace.moe-www - web server serving the webpagetrace.moe
• trace.moe-WebExtension - browser add-ons to help copying and pasting images
• trace.moe-telegram-bot - official Telegram Bot

Server-side:

• trace.moe-api - API server for image search and database updates
• trace.moe-media - media server for video storage and scene preview generation, now integrated into trace.moe-api
• trace.moe-worker - includes hasher, loader and watcher, now integrated into trace.moe-api
• LireSolr - image analysis and search plugin for Solr, now integrated into trace.moe-api

Others:

• anilist-crawler - getting anilist info and store in mariaDB, now integrated into trace.moe-api
• slides - past presentation slides on the project

You're going to need these docker images. They are provided in thecompose.yml file.

Parts	Docker CI Build	Docker Image
trace.moe-www
trace.moe-api

You need docker compose for your OS. Windows is supported via WSL2.

1. Create directory/mnt/c/trace.moe/video/

2. Create subdirectory using anilist ID as folder name.

3. Put video files in it. The full path should look like this/mnt/c/trace.moe/video/{anilist_ID}/foo.mp4

4. Copy.env.example to.env and setVIDEO_PATH to/mnt/c/trace.moe/video/

5. Start the containersdocker compose up -d

It will scan theVIDEO_PATH every minute for new video files (.mp4 .mkv .webm files only, others are ignored).

You can check the indexing process the from logs of api server

6. Openhttp://localhost:3000 and start searching

Other configurations like port mapping are defined in compose.yml

You can also increaseMAX_WORKER to make hashing faster.

Loading all 100,000+ files to Milvus requires about 192GB RAM. (will crash if it runs out of memory)

1. Download the pre-hashed data here:trace.moe database dump 2025-10

2. Install zstd

sudo apt install zstd   # Ubuntu / Debiansudo yum install zstd   # CentOS / RHELsudo dnf install zstd   # Fedorasudo pacman -S zstd     # Arch Linux

3. Start all containers

docker compose up -d

4. Load the database dump to postgres

docker exec -i tracemoe-postgres-1 psql -U postgres postgres < <(zstdcat dump.sql.zst)

This process takes a few minutes. You can ignore all errors likeERROR: relation "xxx" already exists.

5. Load all hashes to Milvus

docker exec -i tracemoe-postgres-1 psql -U postgres postgres < <(echo "UPDATE files SET status='HASHED'")

wait a minute for scan to start, or trigger it manually by

curl http://localhost:3001/scan

This process may take 24 hours. You can check the progress by

docker exec -i tracemoe-postgres-1 psql -U postgres postgres < <(echo "SELECT status, COUNT(*) FROM files GROUP BY status")

Once all files are LOADED, it's ready for search. But background optimization in Milvus may take a few days to complete.

To remove all docker containers and delete all database volumes:

docker compose down -v

Finally, manually clean up theVIDEO_PATH directory if you need to.