Hebbian Mind Enterprise

Hebbian Mind Enterprise

Memory that learns. Connections that fade.

An MCP server that builds knowledge graphs through use. Concepts connect when they activate together. Unused connections decay. The more you use it, the smarter it gets.

What It Does

• Associative Memory - Save content. Query content. Related concepts surface automatically.
• Hebbian Learning - Edges strengthen through co-activation. No manual linking required.
• Concept Nodes - 100+ pre-defined enterprise concepts across Systems, Security, Data, Operations, and more.
• MCP Native - Works with Claude Desktop, Claude Code, any MCP-compatible client.

Installation

Three paths. Pick what fits.

Windows (Native)

# Clone the repo
git clone https://github.com/cipscorps/hebbian-mind-enterprise.git
cd hebbian-mind-enterprise

# Install with pip
pip install -e .

# Verify
python -m hebbian_mind.server

The server runs on stdio. Press Ctrl+C to stop.

Linux / macOS (Native)

# Clone the repo
git clone https://github.com/cipscorps/hebbian-mind-enterprise.git
cd hebbian-mind-enterprise

# Install with pip (use a virtual environment if you prefer)
pip install -e .

# Verify
python -m hebbian_mind.server

Linux gets automatic RAM disk support via /dev/shm when enabled.

Docker (Teams / Enterprise)

# Clone the repo
git clone https://github.com/cipscorps/hebbian-mind-enterprise.git
cd hebbian-mind-enterprise

# Copy environment template
cp .env.example .env

# Build and start
docker-compose up -d

# View logs
docker-compose logs -f hebbian-mind

For RAM disk optimization:

docker-compose --profile ramdisk up -d

Claude Desktop Integration

Add to your claude_desktop_config.json:

Native Install:

{
  "mcpServers": {
    "hebbian-mind": {
      "command": "python",
      "args": ["-m", "hebbian_mind.server"]
    }
  }
}

Docker Install:

{
  "mcpServers": {
    "hebbian-mind": {
      "command": "docker",
      "args": ["exec", "-i", "hebbian-mind", "python", "-m", "hebbian_mind.server"]
    }
  }
}

Restart Claude Desktop. The tools appear automatically.

Configuration

Environment variables control behavior. Set them before running, or use .env with Docker.

Core Settings

Hebbian Learning

Optional Integrations

MCP Tools

Eight tools. All available through any MCP client.

save_to_mind

Store content with automatic concept activation and edge strengthening.

{
  "content": "Microservices architecture enables independent deployment",
  "summary": "Optional summary",
  "source": "ARCHITECTURE_DOCS",
  "importance": 0.8
}

Activates matching concept nodes. Strengthens edges between co-activated concepts.

query_mind

Query memories by concept nodes.

{
  "nodes": ["architecture", "deployment"],
  "limit": 20
}

Returns memories that activated those concepts.

analyze_content

Preview which concepts would activate without saving.

{
  "content": "API authentication using JWT tokens",
  "threshold": 0.3
}

get_related_nodes

Get concepts connected via Hebbian edges.

{
  "node": "security",
  "min_weight": 0.1
}

Returns the neighborhood graph - concepts that have fired together with "security".

list_nodes

List all concept nodes, optionally filtered.

{
  "category": "Security"
}

mind_status

Server health and statistics.

{}

Returns node count, edge count, memory count, strongest connections, dual-write status.

faiss_search

Semantic search via external FAISS tether (if enabled).

{
  "query": "authentication patterns",
  "top_k": 10
}

faiss_status

Check FAISS tether connection status.

Temporal Decay

Memories and edges both decay over time unless reinforced.

Memory decay: Same formula as CASCADE and PyTorch Memory. Memories lose effective importance over time. Accessed memories reset their clock. Immortal memories (importance >= 0.9) never decay.

Edge decay: Connections between concepts weaken if not co-activated. This is the inverse of Hebbian learning -- "neurons that stop firing together, stop wiring together." Edges decay toward a minimum weight (0.1), never to zero, preserving the structure of learned associations.

Decay Configuration

Decayed memories are hidden from query_mind by default. Pass include_decayed: true to retrieve them.

Architecture

Dual-Write Pattern

• Write: RAM first (speed) -> Disk second (persistence)
• Read: RAM (instant) with disk fallback
• Startup: Copies disk to RAM if RAM is empty

RAM disk is optional. Without it, reads and writes go directly to SQLite on disk.

Concept Nodes

100+ pre-defined nodes across categories:

• Systems & Architecture - service, api, component, integration
• Security - authentication, authorization, encryption, access
• Data & Memory - database, cache, persistence, schema
• Logic & Reasoning - pattern, rule, validation, analysis
• Operations - workflow, pipeline, monitoring, health
• Quality - performance, reliability, scalability, test

Nodes have keywords and prototype phrases. Content activates nodes when keywords match.

Hebbian Learning

When concepts co-activate (appear in the same saved content):

1. Edge created if none exists (weight: 0.15)
2. Edge strengthened if exists: weight += factor / (1 + current_weight)
3. Weight capped at MAX_EDGE_WEIGHT

"Neurons that fire together, wire together."

Troubleshooting

Server won't start

Check Python version (requires 3.10+):

python --version

Verify MCP SDK installed:

pip install mcp

No activations on save

Content must match node keywords above threshold. Lower the threshold:

export HEBBIAN_MIND_THRESHOLD=0.2

Or check what would activate:

{"tool": "analyze_content", "content": "your text here"}

Docker container won't connect

Ensure container is running:

docker ps | grep hebbian-mind

Check logs:

docker-compose logs hebbian-mind

High memory with RAM disk

Check node/edge counts via mind_status. Consider increasing HEBBIAN_MIND_THRESHOLD to activate fewer nodes, or lower HEBBIAN_MIND_MAX_WEIGHT to limit edge growth.

Performance

Testing

# Install dev dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Run with coverage
pytest --cov=hebbian_mind

Support

• Documentation: cipscorps.io/docs/hebbian-mind
• Email: [email protected]
• Issues: Private repo issue tracker

Enterprise support plans available.

License

Proprietary software. See LICENSE for terms.

• Individual: Single developer, unlimited projects
• Team: Up to 10 developers, single organization
• Enterprise: Unlimited developers, single organization

Redistribution prohibited.

Memory that learns. Concepts that connect. The more you use it, the smarter it gets.