Back to directory

Marrow

An MCP server that gives AI coding agents memory that survives between sessions, through persistent task tracking, versioned docs and semantic code search over a tree-sitter-based index.

Marrow

A background daemon watches source files in real time, extracts structural skeletons with language-aware grammars, generates vector embeddings, and keeps a semantic index in sync, so agents can navigate code by meaning instead of by filename.

It exposes 23 structured MCP tools and a REST API, letting a heavier model handle architectural work and save state that a lighter local model can pick up later through a session-context call and a semantic task backlog, supporting handoff between different agents.

It is composed of three Python packages, a FastAPI/FastMCP server, a background worker, and a shared schema, storing vectors and metadata in LanceDB and tasks and artifacts as Markdown.

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.