# Anda DB

A modular Rust library for building durable AI agent memory systems, combining B-Tree, BM25 full-text and HNSW vector indexes in one embedded, schema-aware document database.

Anda DB is a modular Rust workspace for building durable memory systems for AI agents. At its core is an embedded, schema-aware document database with three retrieval modes built in: B-Tree indexes for exact match and range filters, BM25 indexes for full-text search, and HNSW indexes for vector similarity search.

On top of that core, the workspace adds a portable persistence layer backed by object storage, a declarative knowledge protocol called KIP, and a reference runtime that turns the database into a persistent knowledge graph for AI agents. It targets applications that need more than a plain key-value store but less than a full external database service, such as long-term agent memory, embedded hybrid retrieval inside Rust services, knowledge-graph workloads, and deployments that must run locally during development and against cloud object storage in production, including regulated environments that keep storage inside their own network.

It requires Rust 1.95 or newer and is MIT licensed.

Website: https://github.com/ldclabs/anda-db