Shodh Cognitive Memory
🦀 🏠 - Cognitive memory for AI agents with Hebbian learning, 3-tier architecture, and knowledge graphs. Single ~15MB binary, runs offline on edge devices.
What is Shodh Cognitive Memory?
Shodh Cognitive Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🦀 🏠 - cognitive memory for ai agents with hebbian learning, 3-tier architecture, and knowledge graphs. single ~15mb binary, runs offline on edge devices.
🦀 🏠 - Cognitive memory for AI agents with Hebbian learning, 3-tier architecture, and knowledge graphs. Single ~15MB binary, runs offline on edge devices.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🦀 🏠 - Cognitive memory for AI agents with Hebbian learning,
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @shodh/memory-mcpManual Installation
npx -y @shodh/memory-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Shodh Cognitive Memory
Shodh Memory is a cognitive memory engine for AI agents implemented in Rust and distributed as a single ~15 MB binary that runs fully offline on edge devices, laptops, or robotics hardware. It implements neuroscience-inspired Hebbian learning — frequently accessed memories strengthen over time while unused ones fade — organised in a 3-tier architecture (working, episodic, semantic) with knowledge-graph relationships and spreading activation. The MCP server exposes 37 tools covering memory storage and retrieval, GTD-style task management, project tracking, reminders, and system diagnostics, giving any MCP client persistent, evolving long-term memory without cloud dependencies.
Prerequisites
- Node.js 16+ (for npx installation method) or Docker for containerised deployment
- No external API keys required for local use — the binary generates its own keys on first run
- Claude Desktop, Claude Code, or another MCP-compatible client
- For remote/production deployments: SHODH_API_KEYS environment variable with comma-separated API keys
Add to Claude Code via the MCP CLI
The fastest way to get started in Claude Code is to add shodh-memory as an MCP server with a single command.
claude mcp add shodh-memory -- npx -y @shodh/memory-mcpSet up automatic memory hooks
Install the session lifecycle hooks so Claude Code automatically saves and recalls memories at the start and end of each session.
npx @shodh/memory-mcp setup-hooksAlternatively, run the shodh binary directly
Download and initialise the standalone Shodh binary for direct use without npx.
shodh init # First-time setup — generates local API keys
shodh server # Start memory server on port 3030
shodh tui # Launch terminal dashboardOr deploy with Docker
For persistent server deployments, use the Docker image with a named volume for data persistence.
docker run -d -p 3030:3030 -v shodh-data:/data varunshodh/shodh-memoryConfigure environment for production deployments
For multi-user or remote deployments, set environment variables to control the API keys, memory storage path, and concurrency limits.
SHODH_ENV=production
SHODH_API_KEYS=key1,key2,key3
SHODH_HOST=127.0.0.1
SHODH_PORT=3030
SHODH_MEMORY_PATH=/var/lib/shodh
SHODH_MAX_CONCURRENT=200Shodh Cognitive Memory Examples
Client configuration
claude_desktop_config.json entry for Shodh Memory using the npm package.
{
"mcpServers": {
"shodh-memory": {
"command": "npx",
"args": ["-y", "@shodh/memory-mcp"]
}
}
}Prompts to try
Example prompts demonstrating Shodh Memory's 37 MCP tools for persistent AI memory.
- "Remember that the project deadline is June 30 and the client is Acme Corp."
- "What do you recall about the database schema we discussed last week?"
- "Add a todo: review pull request #42 by end of day."
- "List all my open projects and their statuses."
- "Set a reminder for tomorrow at 9am to send the weekly report."
- "Show me a summary of all memories related to the authentication module."Troubleshooting Shodh Cognitive Memory
npx @shodh/memory-mcp fails with permissions or download errors
Ensure Node.js 16+ is installed and npx is available. Run 'npx -y @shodh/memory-mcp' manually in a terminal to see the full error output. If behind a proxy, set the HTTP_PROXY environment variable.
Memories are not persisting between Claude sessions
Run 'npx @shodh/memory-mcp setup-hooks' to install the session lifecycle hooks. Without hooks, the agent must manually call the 'remember' tool — hooks automate saving at session end.
Remote deployment returns 401 errors when calling MCP tools
Set SHODH_API_KEYS to a comma-separated list of valid keys and pass the key in the X-API-Key HTTP header on each request. Local single-user deployments do not require this.
Frequently Asked Questions about Shodh Cognitive Memory
What is Shodh Cognitive Memory?
Shodh Cognitive Memory is a Model Context Protocol (MCP) server that 🦀 🏠 - cognitive memory for ai agents with hebbian learning, 3-tier architecture, and knowledge graphs. single ~15mb binary, runs offline on edge devices. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Shodh Cognitive Memory?
Install via npm with the command: npx -y @shodh/memory-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Shodh Cognitive Memory?
Shodh Cognitive Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Shodh Cognitive Memory free to use?
Yes, Shodh Cognitive Memory is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Shodh Cognitive Memory Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Shodh Cognitive 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 Shodh Cognitive 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 Shodh Cognitive Memory?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.