cyberlife-coder/VelesDB

VelesDB is a local‑first AI data engine written in Rust that unifies vectors, full‑text and graph in a single file with a familiar SQL‑like language. Instead of sending every RAG or semantic search query to a remote cluster, VelesDB runs directly on your server, laptop, browser, mobile or edge device — no cloud dependency, no external services, ..

37
/ 100
Emerging

AI agents often struggle with remembering past interactions or understanding complex relationships within data. VelesDB provides a solution by acting as a local-first memory for AI agents, combining vector search for similarity, graph capabilities for connections, and structured data storage for facts. It takes in various types of data and allows agents to query it all with a single, familiar SQL-like language, ensuring they retain context and knowledge. This is ideal for developers creating AI applications who need to give their agents robust, private, and portable memory.

Use this if you are building AI agents and need a single, embedded database that provides semantic, episodic, and procedural memory without relying on external cloud services.

Not ideal if your application strictly requires a simple key-value store or already has a deeply integrated, existing database system for all data types.

AI agent development local-first data management semantic search knowledge graphs data sovereignty
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 13 / 25
Community 7 / 25

How are scores calculated?

Stars

28

Forks

2

Language

Rust

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/cyberlife-coder/VelesDB"

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