Back to directory

LongMemory

A local-first, self-hosted memory engine for LLM applications and agents, with durable SQLite storage, temporal and provenance tracking, and one TypeScript engine reachable from npm, a CLI, HTTP, MCP and VS Code.

LongMemory

LongMemory is a cognitive memory engine for LLM applications and autonomous agents, built around durable local-first storage in SQLite, immutable content with provenance and temporal truth, and several recall modes, including strict, historical, associative and grounded, across multiple languages. It provides governed project memory alongside skills, chat memory, an LLM wiki and a code graph.

A single TypeScript engine backs an npm library, a command-line interface, an HTTP service, an MCP server, a dashboard and a VS Code extension, so the same memory can be used in-process or as a self-hosted server reachable from a zero-dependency Python client. An optional evidence-grounded answering mode validates cited excerpts against authorized evidence and makes at most one model call, while ordinary recall requires none.

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.