cesp99/odino

A local semantic search CLI that finds code and text using natural language queries, powered by embedding models with no internet required.

36
/ 100
Emerging

Builds embeddings using the lightweight Sentence Transformers library with the embedding-gemma-300m model, storing vectors in ChromaDB for fast semantic retrieval. Supports incremental indexing with configurable chunking (512-token default with 50-token overlap), file-type filtering via `.odinoignore` patterns, and handles memory constraints on Apple Silicon through automatic batch processing and device fallback logic.

Available on PyPI.

Maintenance 10 / 25
Adoption 8 / 25
Maturity 18 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Python

License

GPL-3.0

Last pushed

Mar 02, 2026

Monthly downloads

25

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/cesp99/odino"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.