# jdagdelen/hyperDB

A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $135M cap.

Repository: https://github.com/jdagdelen/hyperDB
Canonical: https://ross.abutalabs.com/products/hyperdb
Language: Python
License: MIT
License Family: permissive
Last push: 2025-02-07T22:15:55+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 5, release rhythm 8, longevity 88
- inputs: {"age_days": 1235, "days_push": 572, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1406, forks 88 (observed 2026-08-28T04:04:38.353838+00:00)

## What it is
HyperDB is a lightweight, local vector database library for Python with a C++/MKL-accelerated backend, designed to store and query document embeddings for LLM agents. It offers a simple API for indexing documents with metadata and performing fast similarity searches.

## Use cases
- store and query document embeddings locally for LLM agents
- build retrieval-augmented generation pipelines without a server
- semantic search over JSONL documents with metadata
- quickly prototype vector search in Python
- persist and reload a vector index from disk

## When to choose
- you need a fast, dependency-light local vector store with no server setup
- you're prototyping RAG or agent memory in Python
- your dataset fits in memory and you want hardware-accelerated similarity search

## When to avoid
- you need distributed, production-grade vector search with replication and scaling
- you require advanced filtering, hybrid search, or managed cloud features
- you need long-term support guarantees from a mature project

## Facets
- artifact type: library
- maturity: experimental
- function: vector-database, rag, llm-inference, search-engine
- domain: databases, large-language-models
- platform: python, cross-platform
- tags: embeddings, similarity-search, local-vector-store, llm-agents, mkl-blas, ai-agents, retrieval-augmented-generation

## Member repositories
- jdagdelen/hyperDB (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:38.353838+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:38:42.370986+00:00, confidence not recorded.
  - readme: https://github.com/jdagdelen/hyperDB (fetched 2026-08-28T04:04:38.353838+00:00, sha 2db4a8f86ff6)
- Data as of 2026-08-30T08:39:29.467469+00:00.