How do I run the Memory Context Manager_v2 UI?
Clone the repository, run `yarn install`, then `yarn rw dev`, and open `http://localhost:8910` in your browser.
@Big0290
Basic information
๐ง Deep Project Analysis: Memory Context Manager v2
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"memory-context-manager-v2": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"memory-context-manager-v2:latest",
"python",
"main.py"
],
"env": {
"MCP_LOG_LEVEL": "INFO",
"OLLAMA_BASE_URL": "http://host.docker.internal:11434"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Memory Context Manager_v2 is an MCP server featuring a Continuous Self-Evolution System that enables autonomous learning, performance improvement, and intelligent adaptation. It includes an Evolution Engine for background optimization and is monitored via a dedicated web UI built with RedwoodJS and Chakra UI.
To use Memory Context Manager_v2, run its MCP server instance and then access its web UI by cloning the UI repository, installing dependencies with yarn install, starting the development server with yarn rw dev, and navigating to http://localhost:8910. The UI provides real-time monitoring, evolution tracking, and system control.
Clone the repository, run `yarn install`, then `yarn rw dev`, and open `http://localhost:8910` in your browser.
Node.js 18+, Yarn package manager, and a running instance of the Memory Context Manager v2 MCP server.
The README does not specify data storage details; it only describes real-time monitoring and RESTful communication with the MCP server.
The UI communicates with the MCP server via RESTful API endpoints, as stated in the architecture section.
The README does not mention authentication; it only describes a dashboard interface without user management features.

Ask your Takibi Base collections anything; get answers with cited passages and a support score.

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,
Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.
Comments