Like I Said Memory
Like-I-Said v2 - Advanced MCP Memory and Task Management for LLM's with AI Enhancement and React Dashboard
What is Like I Said Memory?
Like I Said Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to like-i-said v2 - advanced mcp memory and task management for llm's with ai enhancement and react dashboard
Like-I-Said v2 - Advanced MCP Memory and Task Management for LLM's with AI Enhancement and React Dashboard
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Like-I-Said v2 - Advanced MCP Memory and Task Management for
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx like-i-said-memoryConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Like I Said Memory
Like-I-Said Memory is an MCP server that gives AI assistants persistent, structured memory stored entirely on your local machine using JSON files — no external APIs or cloud storage required. It exposes tools for adding, retrieving, listing, and deleting named memories with optional tags and context metadata, so your LLM can remember facts, preferences, project notes, and tasks across separate conversations. A React dashboard provides a visual interface for browsing and managing stored memories without touching the command line.
Prerequisites
- Node.js 16 or later with npm
- Git (to clone the repository)
- An MCP client such as Claude Desktop, Cursor, or Windsurf
- Windows, macOS, or Linux — note that the install path must not contain spaces (use C:\MCP\ on Windows)
Clone the repository
Clone Like-I-Said into a directory path with no spaces. On Windows use C:\MCP\; on macOS/Linux use a path like ~/mcp/.
# Windows (Command Prompt)
mkdir C:\MCP
cd C:\MCP
git clone https://github.com/endlessblink/Like-I-Said-memory-mcp-server.git
cd Like-I-Said-memory-mcp-server
# macOS/Linux
mkdir -p ~/mcp
git clone https://github.com/endlessblink/Like-I-Said-memory-mcp-server.git ~/mcp/Like-I-Said-memory-mcp-server
cd ~/mcp/Like-I-Said-memory-mcp-serverInstall dependencies
Install Node.js dependencies for the MCP server.
npm installConfigure your MCP client
Add the server to your MCP client's configuration file, pointing to the absolute path of server.js. Adjust the path to match where you cloned the repo.
{
"mcpServers": {
"like-i-said-memory": {
"command": "node",
"args": ["/absolute/path/to/Like-I-Said-memory-mcp-server/server.js"]
}
}
}Restart your MCP client
Save the config file and fully restart Claude Desktop (or your chosen client). The memory tools should now appear in the available tool list.
Test memory storage
Ask your AI assistant to store a test memory to confirm everything is working. The memory will be saved locally as a JSON file.
Like I Said Memory Examples
Client configuration
Example Claude Desktop configuration pointing to the locally cloned Like-I-Said server on macOS.
{
"mcpServers": {
"like-i-said-memory": {
"command": "node",
"args": ["/Users/yourname/mcp/Like-I-Said-memory-mcp-server/server.js"]
}
}
}Prompts to try
These prompts let your AI assistant store and retrieve memories across conversations.
- "Remember that my preferred Python formatter is Black with line length 88."
- "What do you remember about my coding preferences?"
- "Store a note: the production database password rotates every 90 days."
- "List all memories tagged with 'project'."
- "Forget the memory called 'old_api_endpoint'."
- "What tasks have I asked you to keep track of?"Troubleshooting Like I Said Memory
The server fails to start with 'Cannot find module' or path errors.
Ensure the args path in your MCP config points to the correct absolute location of server.js and that the path contains no spaces. On Windows use double backslashes in the JSON string: C:\\MCP\\Like-I-Said-memory-mcp-server\\server.js.
Memories are not persisted between sessions.
Check that the directory where the server stores JSON files is writable. The server saves data in a local directory relative to server.js — verify no permission errors appear in the MCP client logs and that the storage directory was created after the first successful memory write.
The React dashboard does not load after opening it.
The dashboard is served locally and typically requires running a separate dev server command from the repository. Check the README for the dashboard start command (usually 'npm run dashboard' or 'npm start') and ensure port 3000 or the configured dashboard port is not blocked by another process.
Frequently Asked Questions about Like I Said Memory
What is Like I Said Memory?
Like I Said Memory is a Model Context Protocol (MCP) server that like-i-said v2 - advanced mcp memory and task management for llm's with ai enhancement and react dashboard It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Like I Said Memory?
Follow the installation instructions on the Like I Said Memory GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Like I Said Memory?
Like I Said Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Like I Said Memory free to use?
Yes, Like I Said Memory is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Like I Said Memory Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Like I Said Memory? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA 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
★ 15.4kAn 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
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (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
★ 5.4kBuild, 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.
Set Up Like I Said Memory in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Like I Said Memory?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.