memcell

Living memory for AI coding agents. Your agents recall what this project established — and what shipped in your dependencies after the model's training cutoff …

AI & ML

Install Command

npx -y memcell

Claude Desktop Config

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

memcell is a community MCP server that connects AI assistants like Claude to living memory for ai coding agents. your agents recall what this project established — and what shipped in your dependencies after the model's training cutoff …. It runs locally on your machine, keeping your data private and giving you full control over the connection. AI engineers can use it to chain models and pipelines into more powerful workflows.

About memcell

Overview

Living memory for AI coding agents. Your agents recall what this project established — and what shipped in your dependencies after the model's training cutoff — before they act, then report outcomes so confidence is earned rather than asserted. One comman

Topics

memcell, agent-memory, ai-memory, persistent-memory, memory, mcp, mcp-server, claude-code, claude, cursor, copilot, gemini-cli, codex, hooks, ai-agents, llm, context

Who Should Use memcell?

1Chain AI models and pipelines through a unified MCP interface
2Let Claude orchestrate other AI tools and models
3Integrate embeddings, image generation, or speech APIs into your workflow
4Build multi-model workflows without writing custom integration code

How to Install memcell

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
2Paste the install command above and press Enter — Node.js will download and run the server automatically.
3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.