Back to directory

MenteDB

A purpose-built Rust database engine for AI agent memory, combining a write-ahead log, HNSW vector search, and a knowledge graph instead of wrapping an existing database.

MenteDB

MenteDB is a storage engine written from scratch in Rust for AI agent memory, rather than a layer built on top of an existing database. It combines a write-ahead log, HNSW vector indexing, and knowledge graphs, and performs what it calls speculative context pre-assembly to prepare context ahead of a request.

It can run as a managed cloud service reached with an API key, or self-hosted with a single binary or Docker image that includes built-in nightly maintenance. Client libraries are available for Python, Node, and Rust, plus integration packages for LangChain and CrewAI, and a command-line client runs its query language against a local data directory or a running server.

It is under active development as a beta, so APIs may change between minor versions, and it is Apache-2.0 licensed.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.