RepoRadar
Leave a Tip
Item detail

Lyellr88/MARM-Systems

MARM is an Apache-2.0 local-first persistent multi-agent memory layer for MCP clients — a Docker / pip-installable service that gives any MCP-compatible agent persistent memory, cross-agent context sharing, write queues, swarm-ready presets, and compaction for clean recall. 305 stars, ships on PyPI as `marm-mcp-server`, on Docker Hub as `lyellr88/marm-mcp-server`, listed in the official MCP Regist

Open source →Back to radar
Score7.5
Popularity65.0
Risknone
TierSilver
Score breakdown
Usefulness8.0
Novelty7.0
Momentum7.0
Maturity6.8
Open-source/build8.4
Evidence7.2
Workflow potential9.0
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for anyone building a multi-agent system that needs shared, persistent memory between Claude Code, Cursor, Windsurf, and any other MCP-compatible client. `pip install marm-mcp-server` (or `docker pull lyellr88/marm-mcp-server`), point the MCP client at the local endpoint, and the agent gains memory that survives across sessions and across clients.

Who should use it

developers building multi-agent systems on Claude Code / Cursor / Windsurf that need shared, persistent memoryagent teams that want one memory store fronting multiple MCP clients without per-client integrationsplatform engineers who want a Docker-deployable memory layer they can run in their own infraswarm-style agent workflows that need write-queue coordination so agents don't trample each otheranyone tired of pasting the same context into every fresh agent session

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

No inherent user-impacting risk is flagged from the captured evidence.

Evidence links

Closest alternatives / related signals

mcpmemory-layerpersistent-memorymulti-agentswarmlocal-firstdockerpypi