maurocanuto/mempack

MemPack is a blazing-fast, lightweight alternative to heavy vector databases: a knowledge pack with an ANN index for fast semantic search.

30
/ 100
Emerging

This helps you create a portable, fast-searching knowledge base from your text documents. You feed it your articles, notes, or any other text, and it outputs two small files: one containing your compressed information and another for ultra-fast semantic search. Anyone building AI assistants, offline applications, or edge computing devices that need quick access to large text collections would use this.

No commits in the last 6 months.

Use this if you need to perform extremely fast, efficient semantic searches over millions of text chunks without relying on complex, resource-heavy online databases.

Not ideal if your knowledge base requires real-time updates, complex filtering beyond semantic search, or is for multi-tenant SaaS applications needing robust database integrations.

AI-assistants offline-applications edge-computing knowledge-management information-retrieval
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Sep 28, 2025

Commits (30d)

0

Get this data via API

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

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