Back to browse
GitHub Repository

SNKV - powered storage backend for LightRAG — no external databases needed

2 starsPython

Query years of Ask HN and Show HN discussions as a knowledge graph

by swaminarayan·May 10, 2026·4 points·5 comments

AI Analysis

MidShip ItNiche Gem

Single-file DB for LightRAG is clever, but HN scraping is solved by existing tools.

Strengths
  • Merges vector, graph, and key-value storage into one embedded file, removing external dependencies.
  • Auto-ingestion daemon keeps Hacker News data fresh without manual script intervention.
  • Relative time queries work naturally without special syntax thanks to date injection.
Weaknesses
  • Author admits early stage issues and zero stars suggest unstable production readiness.
  • Database innovation lives in a separate repo, making this mostly an integration wrapper.
Category
Target Audience

Developers building RAG pipelines, HN data enthusiasts

Similar To

LightRAG · LanceDB · Chroma

Post Description

I built lightrag-snkv, Basically it uses lightRAG https://github.com/HKUDS/LightRAG ,this requires various storage databases like key value store, graph database, vector database, I built single embedded file based database which covers all these requirements: https://github.com/hash-anu/snkv. And developed ingestor which ingest data from Algolia's HN search API. Here auto ingestion timings can be configured either using server.py or it can be configured by ingester code file or can be configured in env file.

This is very early stage and you might hit issues.

Demo video and quick-start in the README. Let me know if you run into issues.

Similar Projects