ldclabs/anda-db

Developer-first database

A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.

Persistent memory & RAG engine for AI agents — SQLite + FTS5 + embeddings, multi-stage recall, sleep maintenance, multi-host hooks

Vector memory that gets smarter every time your agent uses it.

Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Apache-2.0, ships as library / MCP server / HTTP cluster.

RuVector provides High Performance, Real-Time decisions and agent memory , Self-Learning Ai, Vector GNN DB built in Rust.

Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). Apache-2.0.

The cognitive database. A new class of data storage. Not a vector store, not a graph DB, not a RAG wrapper. Ebbinghaus decay, Hebbian learning, and Bayesian confidence are engine-native primitives. Memories evolve on their own. MCP-native. Single binary.

Local-first AI agent memory with a knowledge graph, ontology constraints, and traceable reasoning—all in one SQLite file.