sanonone/kektordb

An in-memory Vector Database & AI Gateway written in Go. Supports HNSW, Hybrid Search (BM25), GraphRAG context, a built-in RAG Pipeline, and can be embedded directly into your apps.

39
/ 100
Emerging

Combines lightweight semantic graph relationships with HNSW vector search, enabling rich context retrieval beyond flat similarity matching through automated entity extraction and weighted edge relationships. Offers dual deployment modes (embedded library or REST microservice), AOF+snapshot persistence, and semantic caching/firewall capabilities as an AI gateway middleware. Integrates seamlessly with LLM ecosystems (Ollama, OpenAI) via OpenAI-compatible API endpoints and includes vision support for OCR-based document processing.

No Package No Dependents
Maintenance 13 / 25
Adoption 8 / 25
Maturity 9 / 25
Community 9 / 25

How are scores calculated?

Stars

64

Forks

5

Language

Go

License

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/sanonone/kektordb"

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