Ombre-Brain

Overview

Ombre Brain provides Claude with persistent emotional memory across conversations. It implements a sophisticated memory system using Russell's circumplex model to tag memories with valence and arousal coordinates. Memories are stored as Obsidian-compatible Markdown files with forgetting curves that naturally decay over time, while emotionally intense memories decay slower. The system includes five MCP tools: breath for memory surfacing/searching, hold for storing memories with auto-tagging, grow for diary digest and splitting, trace for modification/deletion, and pulse for system status. It gracefully degrades to local keyword analysis when APIs are unavailable.

Try asking AI

After installing, here are 3 things you can ask your AI assistant:

• breath

  Surface or search memories

  Try:Show me unresolved memoriesTry:Search for memories about our last conversation
• hold

  Store a single memory with auto-tagging

  Try:Remember that we talked about my vacation plansTry:Store this important detail about my project
• grow

  Diary digest, auto-split into multiple buckets

  Try:Archive our conversation from todayTry:Process this long chat into memories
• trace

  Modify metadata, mark resolved, delete

  Try:Mark this memory as resolvedTry:Update the importance of this memoryTry:Delete this old memory
• pulse

  System status + all memory buckets listing

  Try:Show me system statusTry:List all my memory bucketsTry:What's the current state of my memory system

Comparable tools

Installation

git clone https://github.com/P0lar1zzZ/Ombre-Brain.git
cd Ombre-Brain
python -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate
pip install -r requirements.txt
cp config.example.yaml config.yaml

{
  "mcpServers": {
    "ombre-brain": {
      "command": "python",
      "args": ["/path/to/Ombre-Brain/server.py"],
      "env": {
        "OMBRE_API_KEY": "your-api-key"
      }
    }
  }
}

Compare Ombre-Brain with