schwabauerbriantomas-gif/m2m-vector-search

Edge Vector search engine with Vulkan GPU acceleration, hierarchical indexing (HRM2), and native LangChain integration. Gaussian splat-based architecture for similarity search on resource-constrained devices.

53
/ 100
Established

This helps AI developers and data scientists build 'memory' into their AI agents or applications. You feed it text and related information, and it efficiently stores and retrieves relevant data based on meaning, not just keywords. This allows AI agents to remember past interactions and information, enabling more context-aware responses and actions.

Available on PyPI.

Use this if you need an AI agent to remember past information, conversations, or decisions and retrieve them quickly and intelligently, especially on devices with limited computing power.

Not ideal if you simply need to store and retrieve exact keyword matches in a traditional database or if you're not working with semantic understanding for AI applications.

AI-agent-memory semantic-search edge-AI contextual-AI natural-language-processing
Maintenance 10 / 25
Adoption 6 / 25
Maturity 20 / 25
Community 17 / 25

How are scores calculated?

Stars

24

Forks

9

Language

Python

License

AGPL-3.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

9

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/schwabauerbriantomas-gif/m2m-vector-search"

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