DevMind

v1.0.0Knowledge & Memorystable

DevMind MCP provides **persistent memory capabilities** for AI assistants through the Model Context Protocol (MCP). It enables AI to remember context across conversations, automatically track development activities, and retrieve relevant information

ai-memorycontext-recordingdeveloper-toolsmcpmemory-management
Share:
18
Stars
0
Downloads
0
Weekly
0/5

What is DevMind?

DevMind is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to devmind mcp provides **persistent memory capabilities** for ai assistants through the model context protocol (mcp). it enables ai to remember context across conversations, automatically track developm...

DevMind MCP provides **persistent memory capabilities** for AI assistants through the Model Context Protocol (MCP). It enables AI to remember context across conversations, automatically track development activities, and retrieve relevant information

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

Features

  • DevMind MCP provides **persistent memory capabilities** for

Use Cases

Maintain persistent memory of development activities and context. Automatically track project activities and development progress. Retrieve relevant information from past sessions and interactions.
JochenYang

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedDec 17, 2025
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx devmind-mcp

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 DevMind

DevMind MCP provides persistent memory capabilities for AI coding assistants through the Model Context Protocol, using a local SQLite database with optional vector embeddings to store and retrieve development context across sessions. It exposes 15 tools for creating sessions, recording implementation notes, performing semantic search over past decisions, indexing codebases, and exporting memory graphs. Developers use it to ensure their AI assistant remembers architectural decisions, past bug fixes, and implementation patterns from previous conversations without needing to re-explain context every time.

Prerequisites

  • Node.js 18+ installed for running via npx
  • An MCP-compatible client such as Claude Desktop, Cursor, or Claude Code CLI
  • Optional: a .devmind.json config file in your project root for per-project memory settings
  • SQLite available on your system (bundled with Node.js on most platforms)
1

Install DevMind MCP via npx or globally

The simplest way to run DevMind is via npx which pulls the latest version automatically. You can also install it globally with npm.

# Run directly (recommended):
npx -y devmind-mcp@latest

# Or install globally:
npm install -g devmind-mcp
2

Add via Claude Code CLI (optional shortcut)

If you use Claude Code CLI, you can register DevMind MCP as a project-level server with a single command.

claude add mcp npx -y devmind-mcp@latest
3

Create a project configuration file (optional)

Create a .devmind.json file in your project root to customize the memory database path, quality threshold, auto-save interval, and file patterns to index.

{
  "database_path": "~/.devmind/memory.db",
  "quality_threshold": 0.3,
  "auto_save_interval": 30000,
  "embedding_model": "local",
  "ignored_patterns": ["node_modules/**", "dist/**"],
  "included_extensions": [".ts", ".js", ".py", ".go"]
}
4

Add the server to your MCP client configuration

Register DevMind in your claude_desktop_config.json so the client launches it automatically on startup.

{
  "mcpServers": {
    "devmind": {
      "command": "npx",
      "args": ["-y", "devmind-mcp@latest"]
    }
  }
}
5

Restart your client and start a session

Restart your MCP client. Ask the AI to create a new DevMind session for your current project, then start recording implementation context as you work.

DevMind Examples

Client configuration

Example claude_desktop_config.json entry for DevMind MCP Server.

{
  "mcpServers": {
    "devmind": {
      "command": "npx",
      "args": ["-y", "devmind-mcp@latest"]
    }
  }
}

Prompts to try

Example prompts for using DevMind's persistent memory capabilities with your AI assistant.

- "Create a new DevMind session for the auth-refactor project"
- "Record that I implemented JWT authentication with refresh tokens using the jose library"
- "Search my memory for how I handled rate limiting in previous projects"
- "Index the codebase at ./src so you can reference the existing code patterns"
- "Export my memory graph for this project so I can review all recorded decisions"

Troubleshooting DevMind

Memory is not persisting between AI sessions

Verify the database_path in .devmind.json is writable and that the directory exists. By default, DevMind stores data at ~/.devmind/memory.db — create the directory manually if it does not exist: 'mkdir -p ~/.devmind'.

Semantic search returns no results even after recording context

The default embedding_model is set to 'local' which may have limited capability. Ensure your .devmind.json quality_threshold is not too high (default 0.3 is recommended). Check the auto_save_interval has elapsed so context was actually persisted.

Codebase indexing fails or times out on large projects

Add large generated directories (node_modules, dist, .git, build) to the ignored_patterns list in .devmind.json before running the codebase index tool. Use force_reindex: false on subsequent runs to skip already-indexed files.

Frequently Asked Questions about DevMind

What is DevMind?

DevMind is a Model Context Protocol (MCP) server that devmind mcp provides **persistent memory capabilities** for ai assistants through the model context protocol (mcp). it enables ai to remember context across conversations, automatically track development activities, and retrieve relevant information It connects AI assistants to external tools and data sources through a standardized interface.

How do I install DevMind?

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

Which AI clients work with DevMind?

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

Is DevMind free to use?

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

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.

Quick Config Preview

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

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

Read the full setup guide →

Ready to use DevMind?

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