jina-ai/jina-grep-cli

Semantic grep powered by Jina embeddings v5 (MLX on Apple Silicon)

39
/ 100
Emerging

Supports four distinct modes—pipe-mode semantic reranking of grep results, direct file search with natural language queries, zero-shot classification, and specialized code search with task variants (nl2code, code2code, etc.). Uses unified MLX checkpoints with dynamic LoRA adapter switching to keep a single base model in GPU memory (~20ms adapter swap), eliminating PyTorch/transformers overhead and enabling ~3-7.5ms query latency on Apple Silicon via Metal GPU acceleration.

180 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 11 / 25
Community 8 / 25

How are scores calculated?

Stars

180

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Feb 27, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/jina-ai/jina-grep-cli"

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