MCPgee
MCPgee
MCPgeeMCPgee

Ori Mnemos

v0.3.0•Knowledge & Memory•stable

Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

agent-memoryai-agentai-agentsai-memoryknowledge-graph
Share:
305
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Ori Mnemos?

Ori Mnemos is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to local-first persistent agentic memory powered by recursive memory harness (rmh). open source must win.

Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

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

Features

  • Local-first persistent agentic memory powered by Recursive M

Use Cases

Local-first agentic memory
Recursive Memory Harness (RMH)
Persistent knowledge storage
aayoawoyemi

Maintainer

LicenseApache-2.0
Languagetypescript
Versionv0.3.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

NPM

npx -y ori-memory

Manual Installation

npx -y ori-memory

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 Ori Mnemos

Ori Mnemos is a local-first persistent memory system for AI agents, powered by the Recursive Memory Harness (RMH). It provides 16 MCP tools for storing, retrieving, and managing agent memories organized across five namespaces — identity, knowledge, operations, inbox, and templates — all stored as plain markdown files on disk with SQLite indexing. Unlike cloud-based memory solutions, Ori runs entirely on your machine with no external dependencies, making it portable, git-friendly, and private by design.

Prerequisites

  • Node.js with npm installed
  • Git installed (the vault uses git for version control)
  • An MCP-compatible AI client such as Claude for Desktop, Cursor, or Claude Code
  • Optional: an LLM API key if you want AI-assisted memory processing (the server also works with heuristics only)
1

Install ori-memory globally

Install the ori-memory package from npm globally so the 'ori' CLI is available on your PATH.

npm install -g ori-memory
2

Initialize a memory vault

Create a new memory vault (a directory of markdown files) using the ori init command. You can name it anything; 'brain' is the convention used in the docs.

ori init my-agent
cd my-agent
3

Configure your MCP client

Use the built-in bridge command to automatically configure your AI client, or add the server manually to your claude_desktop_config.json.

# Auto-configure Claude Code:
ori bridge claude-code --vault ~/brain

# Or auto-configure Claude Desktop:
ori bridge generic --vault ~/brain
4

Add the server to claude_desktop_config.json manually (alternative)

If you prefer manual configuration, add this entry to your Claude Desktop config, replacing the vault path with your actual vault directory.

{
  "mcpServers": {
    "ori": {
      "command": "ori",
      "args": ["serve", "--mcp", "--vault", "/path/to/your/brain"],
      "env": {
        "ORI_VAULT": "/path/to/your/brain"
      }
    }
  }
}
5

Verify the vault and build the index

Check vault health and build the initial embedding index for intelligent retrieval.

ori status
ori health
ori index build

Ori Mnemos Examples

Client configuration

Complete claude_desktop_config.json entry for Ori Mnemos pointing to a vault at ~/brain.

{
  "mcpServers": {
    "ori": {
      "command": "ori",
      "args": ["serve", "--mcp", "--vault", "/Users/yourname/brain"],
      "env": {
        "ORI_VAULT": "/Users/yourname/brain"
      }
    }
  }
}

Prompts to try

Use these prompts with your AI client once Ori Mnemos is connected to test memory storage and retrieval.

- "Remember that my preferred coding language is TypeScript and I work at Acme Corp"
- "What do you know about my preferences and background?"
- "Store a note: the API endpoint for staging is https://api-staging.example.com"
- "Search your memory for anything related to the authentication project"
- "Give me a session briefing — what context do you have about me and my current projects?"
- "Prune any stale or outdated notes from memory"

Troubleshooting Ori Mnemos

The 'ori' command is not found after npm install

Ensure npm's global bin directory is on your PATH. Run 'npm config get prefix' to find the prefix directory, then add '<prefix>/bin' to your PATH in ~/.bashrc or ~/.zshrc. Alternatively use 'npx -y ori-memory serve --mcp --vault ~/brain' in the MCP config command instead of 'ori'.

Memory retrieval returns irrelevant results

Build or rebuild the embedding index by running 'ori index build' from the terminal. The index may be stale if you added notes directly to the markdown files without going through the MCP tools. Run 'ori health' to check index status.

The vault grows large and git operations become slow

Run 'ori prune' (or use the ori_prune MCP tool) to identify and remove stale content. For very large vaults, consider adding a .gitignore entry for the SQLite index files (.ori/index.db) and committing only the markdown files to keep the git history clean.

Frequently Asked Questions about Ori Mnemos

What is Ori Mnemos?

Ori Mnemos is a Model Context Protocol (MCP) server that local-first persistent agentic memory powered by recursive memory harness (rmh). open source must win. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Ori Mnemos?

Install via npm with the command: npx -y ori-memory. 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 Ori Mnemos?

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

Is Ori Mnemos free to use?

Yes, Ori Mnemos is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Ori Mnemos Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Ori Mnemos? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A 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

★ 15.4k

An 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

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (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

★ 5.4k

Build, 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.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "ori-mnemos": { "command": "npx", "args": ["-y", "ori-memory"] } } }

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

Read the full setup guide →

Ready to use Ori Mnemos?

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
Explore All ServersRead Our Guides