Skip to main content
MCP server CX Codex

crbro-memory — Claude Code MCP server: long-term agent memory

A local MCP server that keeps an agent's knowledge across sessions: facts, decisions, errors and session summaries stored as files.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add crbro-memory -- npx -y crbro-memory
Open on GitHub

What crbro-memory does

CRBRO splits knowledge into neurons (cortex), links between them (synapses) and session memory (hippocampus). Search runs over individual facts through Orama, so a topic holding hundreds of entries stays as findable as a small one. Every hit returns the matching line, the date it was written and a confidence label.

You can read memory in slices. crbro_inspect view=neuron gives an index of facts, decisions, patterns and errors with an id, a date and a preview, while entries=[ids] pulls only those. Facts carry a shelf life — volatile, normal, durable or permanent, set through CRBRO_SHELF_DAYS; expired claims move to possibly_stale with a source-check warning. Repeating a fact does not verify it: only crbro_revise status=verified restarts a check.

npx crbro-memory init installs a local embedding model, multilingual-e5-small in int8, and fuses it with keyword search. That costs roughly 500 MB on disk once per machine and about 0.5 GB of RAM while a server runs. init --no-semantic skips the install, and CRBRO_SEMANTIC=0 turns semantics off later. Node.js is required, since the server starts through npx.

What it helps with

  • keep decisions and agreements alive between agent sessions
  • find one fact in a topic that already holds hundreds
  • separate stale claims from current ones
  • read only the entries you need instead of a whole neuron
  • record whether a claim came from a source or from the user

Example prompts for the agent

  • Save to memory that we moved hosting to Hetzner
  • Search memory for everything about deploys from the last two weeks
  • Show the project neuron index and read only the migration entries

How to install crbro-memory

Platform CLI

claude mcp add crbro-memory -- npx -y crbro-memory

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 crbro-memory

How do I install crbro-memory in Claude Code?

One command: claude mcp add crbro-memory -- npx -y crbro-memory. The server then starts through npx on each run.

What does crbro-memory do?

It gives an agent file-based long-term memory: facts, decisions, patterns, errors and session summaries are saved and found by search in later sessions. Everything stays local.

Do I need the semantic model for crbro-memory?

No. npx crbro-memory init installs multilingual-e5-small and fuses it with keyword search, but init --no-semantic skips the install and CRBRO_SEMANTIC=0 disables semantics afterwards.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor