Recall – local multimodal semantic search for your files

Local multimodal memory with semantic search.

Embed images, audio, video, PDFs, and text into a local vector database — then find anything with a natural language query. A text search for "team dinner" surfaces the photos, even though the photos have no text metadata.

Comes with an animated setup wizard and a Raycast extension for instant visual search.

Powered by Gemini Embedding 2 (768-dim, free tier) and ChromaDB stored entirely on your machine.

You Gemini Embedding 2 ChromaDB (local)
| | |
|-- team-dinner.jpg -------->|-- 768-dim vector ------>|-- stored on disk
|-- meeting-notes.pdf ------>|-- 768-dim vector ------>|-- stored on disk
|-- "team dinner" (query) -->|-- query vector -------->|-- cosine search
|<---------------------------|<-- ranked results -------|

Cross-modal search works out of the box. No tagging, no renaming, no metadata required.

git clone https://github.com/hughminhphan/vector-embedded-finder.git
cd vector-embedded-finder
pip install -e .
python setup_wizard.py

That's it. The animated setup wizard handles everything end-to-end, from API key validation to folder indexing and Raycast configuration.

Files are SHA-256 deduplicated — re-ingesting the same file is a no-op. Visual grid search with image thumbnails is available right from your launcher via Raycast.

All vectors are stored locally in data/chromadb/. The only outbound traffic is embedding API calls to Google — your files never leave your machine.