#5050th of 60 in RAG, knowledge and search
trace.moe
Reverse image search that identifies the anime, episode and timestamp of a screenshot
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 5k
- License
- MIT
- Last commit
- Sep 2026
4,923 on 21 Apr 20265,043 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Index repo for the trace.moe system, which matches an anime screenshot to its title, episode and the moment it appears. Self-hosting uses a compose.yml that runs the web server and API server, with Postgres and Milvus storing hashes of your own video files. The repo itself is mostly a pointer to sub-repos (API, www, Telegram bot, MCP server, browser extension, image-vector library).
Who it is for: Self-hosters indexing their own anime video library for scene lookup
Strengths
- Returns anime, episode and exact timestamp for a screenshot
- Compose file brings up web and API; scans VIDEO_PATH every minute for new files
- Pre-hashed database dump available on Hugging Face to skip indexing
- Separate API, Telegram bot and MCP server repos for integrations
Weaknesses
- This repo is an index page; code lives in separate repositories
- Full pre-hashed dataset needs about 140GB RAM to load into memory
- Loading hashes into Milvus may take 24 hours, optimization days more
- Only .mp4, .mkv and .webm files indexed, organized by anilist ID folders
What it needs
- Compose
- Needs Docker Compose, PostgreSQL, Milvus, zstd (for database dump)
- Models: .mp4, .mkv, .webm
- port 3000
Also in RAG, knowledge and search
See all 60| Rank | Project | Score |
|---|---|---|
| 1 | RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval | 90 out of 100 |
| 2 | Open NotebookSelf-hosted NotebookLM alternative for research notebooks, chat, and podcasts | 90 out of 100 |
| 3 | LightRAGGraph-based RAG framework with a REST server and WebUI | 90 out of 100 |
| #4 | deeptutorTutoring workspace with knowledge bases, guided learning, memory and quizzes | 89 out of 100 |
| #5 | MaxKBEnterprise knowledge-base agent platform with RAG, workflows and MCP tools | 89 out of 100 |