Marrow · aryawidjaja — Claude Code MCP server: shared memory for coding agents
Marrow is a Claude Code MCP server that gives parallel coding agents one shared memory: a question comes back as matched notes drawn from the whole store, instead of an index file loaded into every session.
AGPL-3.0 ★ 5 updated 2026-08-12
Open on GitHubWhat Marrow does
Marrow answers an agent's question with a ranked set of notes and the notes linked to them, searched across everything the project has accumulated. Each memory is a markdown file under .marrow/, open and deletable by hand. The hive lets an agent in one repo recall what another repo knows; machines and teammates stay in sync through a relay you host or through Spinal Cloud.
With several sessions live, a file one of them is editing gets claimed so the rest leave it alone. Everything the agents do lands in one log that is append-only and chained by hashes.
On Claude Code the route is a plugin: /plugin marketplace add aryawidjaja/marrow, then /plugin install marrow@marrow, then the binary from brew install aryawidjaja/marrow/marrow (Windows: irm marrow.works/install.ps1 | iex) and a restart. Other clients take marrow setup, where --global wires every repo at once. Hooks call for jq. In the project's own benchmark, 1000 facts cost 2.1× less context per turn and $0.50 a task against $0.90; under roughly a hundred facts the built-in Claude Code memory wins at 0.87×.
What it helps with
- share one project memory between parallel agents
- keep two live sessions off the same file
- carry project facts across repos and machines
- audit agent actions from one log
- hold context per turn flat on a large codebase
Example prompts for the agent
- Store in memory that ids here sort, so
uuid4is wrong for them. - What do earlier sessions know about the schema in
api? - Run
/marrow-saveso this session's context survives.
How to install Marrow
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Marrow
How do I install Marrow in Claude Code?
Add the marketplace with /plugin marketplace add aryawidjaja/marrow, then install the plugin: /plugin install marrow@marrow. After that pull the binary with brew install aryawidjaja/marrow/marrow (on Windows irm marrow.works/install.ps1 | iex) and restart the agent.
What does Marrow do?
It keeps one project memory for several coding agents and returns the relevant notes on request. A file a session is editing is claimed so other agents skip it, and agent actions go into an append-only log.
What does Marrow need to run?
The binary from brew or the Windows install script, plus jq for the hooks. Syncing between machines needs a relay you run or Spinal Cloud.
Similar MCP servers
All MCP servers for Agent setup: memory, context, orchestration →Marrow by other authors comes first.