Skip to main content
Glama

🧠 CRBRO β€” Persistent Neural Memory for AI

npm license MCP

CRBRO is a local MCP (Model Context Protocol) server that gives your AI assistant persistent long-term memory across sessions. It uses a biological neural architecture β€” cortex, synapses, hippocampus β€” to store, connect, and retrieve knowledge automatically.

CRBRO demo

Free and open source (MIT). All 15 tools included β€” no license, no account, no tiers.

⭐ If CRBRO gives your AI a memory worth keeping, a star on GitHub is the best way to support it.

Features

  • 🧬 Biological Architecture β€” Knowledge organized as neurons (cortex), connections (synapses), and session memory (hippocampus)

  • πŸ” Hybrid Search β€” Powered by Orama for fast BM25 + fuzzy text search

  • πŸ”₯ Heat Scores β€” Automatic relevance tracking based on frequency, recency, and connectivity

  • πŸ—ΊοΈ Global Map β€” Cluster detection and cross-domain bridge identification

  • ⛏️ Knowledge Miner β€” Optionally scans your local .md/.txt notes and feeds them into the brain

  • πŸ”’ Fully Local β€” Runs on Node.js alone: no Python, no Docker, no databases, no external services. Your memory never leaves your machine

  • πŸ’Ύ File-Based β€” All data stored as readable JSON files in ~/.crbro/ β€” inspectable, diffable, and versionable with git

  • πŸ”Œ MCP Native β€” Works with Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP-compatible client

Related MCP server: cell-mem

Quick Start

1. Initialize

npx crbro-memory init

2. Add to your MCP config

Register CRBRO at the user level, not per-project. Your brain lives in ~/.crbro/ and is shared across every folder β€” but if you register the server inside a single project, other folders won't have the tools and it will look like the memory is gone. User-level registration makes it available everywhere, which is the whole point.

Claude Code (one command, available in every folder):

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

Claude Desktop (~/AppData/Roaming/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "crbro": {
      "command": "npx",
      "args": ["-y", "crbro-memory"]
    }
  }
}

Cursor (~/.cursor/mcp.json β€” the one in your home folder, not a project's .cursor/):

{
  "mcpServers": {
    "crbro": {
      "command": "npx",
      "args": ["-y", "crbro-memory"]
    }
  }
}

3. Start using it

Your AI will now have access to 15 memory tools. Start any session with crbro_boot.

Tools

Tool

Description

crbro_boot

Boot the brain at session start β€” loads hot topics and context

crbro_status

Brain status β€” neurons, synapses, sessions count

crbro_learn

Store a fact, decision, pattern, or preference

crbro_neuron

Read a specific neuron (topic) with all its knowledge

crbro_neurons

List neurons with optional filters (domain, type, heat)

crbro_recall

Search the brain using hybrid text search

crbro_connect

Create or strengthen a connection between neurons

crbro_connections

Get all connections for a neuron

crbro_session_log

Log a session summary

crbro_sessions

List recent sessions

crbro_context

Read/update active working context

crbro_hot_topics

Get the most active topics by heat score

crbro_global_map

View the neural network β€” clusters and cross-domain bridges

crbro_maintenance

Full brain maintenance β€” archive, prune, rebuild

crbro_consolidate

End-of-session consolidation

Architecture

~/.crbro/
β”œβ”€β”€ manifest.json           ← Brain metadata
β”œβ”€β”€ cortex/                 ← One JSON per neuron (topic)
β”‚   β”œβ”€β”€ project_octochat.json
β”‚   └── tech_firebase.json
β”œβ”€β”€ synapses/               ← One JSON per connection
β”‚   └── syn_octochat__firebase.json
β”œβ”€β”€ hippocampus/            ← One JSON per session
β”‚   └── session_2026-05-06.json
β”œβ”€β”€ prefrontal/             ← Working memory
β”‚   β”œβ”€β”€ active_context.json
β”‚   β”œβ”€β”€ hot_topics.json
β”‚   └── global_map.json
β”œβ”€β”€ archives/               ← Cold neurons
└── .search/                ← Orama search index
    └── orama.index.json

Heat Score Algorithm

Each neuron has a heat score (0.0 - 1.0) calculated from:

  • Frequency (35%) β€” How often the neuron is accessed

  • Recency (40%) β€” When it was last accessed (today = 1.0, >3 months = 0.05)

  • Connectivity (25%) β€” How many synapses connect to it

Knowledge Miner

The miner is an optional, fully local helper that scans a directory for .md and .txt files (notes, docs, journals) and extracts knowledge into the brain β€” so CRBRO can learn from what you already wrote, not just from conversations. It never touches the network and never leaves your machine.

npx crbro-memory mine [dir]       # One-shot scan of a directory
npx crbro-memory setup-miner      # Install a scheduled auto-scan (OS task scheduler)
npx crbro-memory miner-status     # Check the auto-miner status
npx crbro-memory remove-miner     # Remove the scheduled task

Naming note: "miner" here means knowledge mining β€” extracting facts from your own text files. Nothing to do with cryptocurrency.

CLI Commands

npx crbro-memory          # Start MCP server (stdio)
npx crbro-memory init     # Initialize brain + detect IDEs
npx crbro-memory status   # Show brain status
npx crbro-memory --help   # Help

License

MIT β€” see LICENSE. Built by Octonove.

Install Server
A
license - permissive license
A
quality
B
maintenance

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Octonove/crbro-memory'

If you have feedback or need assistance with the MCP directory API, please join our Discord server