MCPgee
MCPgee
MCPgeeMCPgee

Ombre Brain

v1.0.0•Knowledge & Memory•stable

For Claude.

ai-agentchatgptclaudeemotional-intelligencegemini
Share:
99
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Ombre Brain?

Ombre Brain is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to for claude.

For Claude.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • For Claude.

Use Cases

Add long-term memory and emotional intelligence to AI agents. Store and recall conversations across multiple AI assistants.
P0lar1zzZ

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx ombre-brain

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Ombre Brain

Ombre Brain is an MCP server that provides AI assistants with long-term emotional memory using a psychologically-grounded model based on Russell's valence-arousal coordinates and Ebbinghaus memory decay. It stores memories as Markdown files with YAML frontmatter (compatible with Obsidian), automatically compresses older memories, surfaces emotionally intense unresolved items at conversation start, and supports multiple AI platforms including Claude, ChatGPT, and Gemini. This is ideal for anyone who wants their AI assistant to remember past conversations with human-like emotional context and forgetting curves.

Prerequisites

  • Python 3.10+ installed
  • Git to clone the repository
  • An API key for a DeepSeek-compatible or OpenAI-compatible LLM (used for memory compression)
  • An MCP-compatible client such as Claude Desktop
  • Optional: Obsidian for viewing memory files in a vault
1

Clone the repository and create a virtual environment

Clone Ombre Brain from GitHub and set up an isolated Python environment to avoid dependency conflicts.

git clone https://github.com/P0lar1zzZ/Ombre-Brain.git
cd Ombre-Brain
python -m venv .venv
source .venv/bin/activate
2

Install dependencies and copy config

Install required Python packages and create your local configuration file from the provided example.

pip install -r requirements.txt
cp config.example.yaml config.yaml
3

Edit config.yaml to set your API credentials

Open config.yaml and set your LLM API key and endpoint. The default uses DeepSeek, but any OpenAI-compatible API works. Configure the buckets_dir path where memory files will be stored.

4

Configure Claude Desktop to launch the server

Add Ombre Brain to your Claude Desktop MCP config, pointing to the server.py file in your cloned repository and setting your OMBRE_API_KEY.

5

Restart Claude Desktop and test memory tools

After restarting the client, the five memory tools (breath, hold, grow, trace, pulse) will be available. Use 'hold' to store a memory and 'breath' to surface existing ones.

Ombre Brain Examples

Client configuration

Claude Desktop config pointing to the locally cloned Ombre Brain server.py.

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

Prompts to try

Example prompts that exercise Ombre Brain's memory storage and retrieval tools.

- "Remember that I felt anxious about the product launch today — it went poorly but I learned a lot"
- "What unresolved thoughts or memories do you have from our previous conversations?"
- "Write a diary entry about what happened today and store it in memory"
- "Mark the memory about the job interview as resolved"
- "Show me the current status of the memory system — how many buckets are active?"

Troubleshooting Ombre Brain

LLM API calls fail during memory compression

Verify OMBRE_API_KEY is set correctly and that OMBRE_BASE_URL points to your API endpoint. The system degrades gracefully to local keyword analysis if the LLM is unavailable, so basic memory functions still work.

Memories are not persisting between sessions

Check that OMBRE_BUCKETS_DIR (or buckets_dir in config.yaml) points to a writable directory with sufficient disk space. If deploying remotely (Render/Zeabur), ensure the plan includes persistent disk storage.

Server fails to start with import errors

Ensure you activated the virtual environment (source .venv/bin/activate) before installing requirements. Run 'pip install -r requirements.txt' again inside the activated venv, then verify all packages installed successfully.

Frequently Asked Questions about Ombre Brain

What is Ombre Brain?

Ombre Brain is a Model Context Protocol (MCP) server that for claude. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Ombre Brain?

Follow the installation instructions on the Ombre Brain GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Ombre Brain?

Ombre Brain works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Ombre Brain free to use?

Yes, Ombre Brain is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Ombre Brain Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Ombre Brain? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "ombre-brain": { "command": "npx", "args": ["-y", "ombre-brain"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Ombre Brain?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides