kelindar/search

Go library for embedded vector search and semantic embeddings using llama.cpp

47
/ 100
Emerging

Enables brute-force vector search with SIMD optimizations and GPU acceleration via Vulkan, supporting GGUF-format BERT models loaded through purego (cgo-free C bindings). Persists embeddings to disk-based indices optimized for datasets under 100,000 entries. Integrates with Go applications requiring lightweight semantic search without external service dependencies.

528 stars. Actively maintained with 1 commit in the last 30 days.

No Package No Dependents
Maintenance 16 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 12 / 25

How are scores calculated?

Stars

528

Forks

23

Language

Go

License

MIT

Last pushed

Mar 06, 2026

Commits (30d)

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/kelindar/search"

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