anaslimem/CortexaDB

It is a simple, fast, and hard-durable embedded database designed specifically for AI agent memory. It provides a single-file-like experience (no server required) but with native support for vectors, graphs, and temporal search.

52
/ 100
Established

Built in Rust with HNSW indexing (via USearch) for sub-millisecond vector search, CortexaDB combines semantic, graph-based, and temporal retrieval in a single fluent query API—enabling hybrid search across multiple dimensions without server overhead. The architecture uses WAL-backed storage for hard durability while supporting batch ingestion at 5,000+ chunks/second, making it purpose-built for stateful AI agent workflows that require persistent memory beyond context windows. Python and Rust bindings integrate seamlessly with embedding providers like OpenAI for end-to-end semantic memory management.

27 stars and 1,122 monthly downloads. Available on PyPI.

No Dependents
Maintenance 13 / 25
Adoption 14 / 25
Maturity 18 / 25
Community 7 / 25

How are scores calculated?

Stars

27

Forks

2

Language

Rust

License

Apache-2.0

Last pushed

Mar 12, 2026

Monthly downloads

1,122

Commits (30d)

0

Get this data via API

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

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