Origin
Local-first Rust daemon for AI work. Git-versioned memories, distilled wiki pages, sessions for Claude Code, Cursor, Codex, and any MCP client.
What is Origin?
Origin is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to local-first rust daemon for ai work. git-versioned memories, distilled wiki pages, sessions for claude code, cursor, codex, and any mcp client.
Local-first Rust daemon for AI work. Git-versioned memories, distilled wiki pages, sessions for Claude Code, Cursor, Codex, and any MCP client.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Local-first Rust daemon for AI work. Git-versioned memories,
Use Cases
Maintainer
Works with
Installation
NPM
npx -y origin-mcpManual Installation
npx -y origin-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Origin
Origin is a local-first Rust daemon that gives AI coding agents persistent, git-versioned memory across sessions. It stores decisions, lessons, and project context as plain Markdown files under ~/.origin/ and exposes them through an MCP interface compatible with Claude Code, Cursor, Codex, Claude Desktop, and VS Code. Developers use it to prevent their AI assistant from losing context between chat sessions, enabling true continuity of thought across days and projects through capture, recall, and distill workflows.
Prerequisites
- Node.js 18 or later (for the npx-based setup command)
- An MCP client: Claude Code, Cursor, VS Code with MCP extension, Claude Desktop, or Codex
- Git installed (Origin uses git to version-control all memory files)
- No cloud account or API keys required — all data is stored locally
Run the setup command
Use npx to download and run the Origin setup script. This installs the Rust daemon binary to ~/.origin/bin/ and initializes the local data store.
npx -y origin-mcp setupRegister the MCP server with your client
After setup, register Origin as an MCP server for your preferred AI client. The tool supports Claude Code, Cursor, claude-desktop, VS Code, Codex, and Gemini.
# For Claude Code:
~/.origin/bin/origin mcp add claude-code
# For Cursor:
~/.origin/bin/origin mcp add cursor
# For Claude Desktop:
~/.origin/bin/origin mcp add claude-desktopInstall and start the daemon
Register the Origin daemon as a system service so it starts automatically and persists across reboots.
~/.origin/bin/origin installCreate and manage spaces
Spaces let you organize memories by context (e.g. a project, a client, a life area). Create a space for your current project and set it as default.
~/.origin/bin/origin space add myproject --default
~/.origin/bin/origin space listUse a different space per session
Switch between spaces at session start using the ORIGIN_SPACE environment variable, without changing your default configuration.
ORIGIN_SPACE=career claudeOrigin Examples
Client configuration
Example claude_desktop_config.json entry for Origin MCP. The npx command handles resolving the correct binary.
{
"mcpServers": {
"origin": {
"command": "npx",
"args": ["-y", "origin-mcp"]
}
}
}Prompts to try
Use these commands and prompts during your AI sessions to capture and retrieve persistent memory.
- "/brief authentication-system — load context about the auth module I'm working on."
- "/capture I decided to use JWTs with 1-hour expiry and refresh tokens stored in Redis."
- "/recall what database did we decide on for the user service?"
- "/handoff — I'm done for today, document what I accomplished and what's next."
- "/distill — synthesize a wiki page summarizing everything we know about the payment system."Troubleshooting Origin
npx -y origin-mcp setup fails or the binary is not found after setup
Ensure Node.js 18+ is installed and npx is available. After setup, the daemon binary is at ~/.origin/bin/origin. Add this directory to your PATH with: export PATH="$HOME/.origin/bin:$PATH".
MCP tools are not showing up in Claude Code or Cursor after running mcp add
Restart your MCP client after registering the server — most clients read the config file only at startup. Also confirm the daemon is running with: ~/.origin/bin/origin status.
Memories from a previous session are not being recalled
Verify you are in the correct space with: ~/.origin/bin/origin space list. If you used ORIGIN_SPACE to set a different space in a previous session, you may need to set the same variable again, or switch your default space with: ~/.origin/bin/origin space add <name> --default.
Frequently Asked Questions about Origin
What is Origin?
Origin is a Model Context Protocol (MCP) server that local-first rust daemon for ai work. git-versioned memories, distilled wiki pages, sessions for claude code, cursor, codex, and any mcp client. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Origin?
Install via npm with the command: npx -y origin-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 Origin?
Origin works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Origin free to use?
Yes, Origin is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Origin Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Origin? 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 Origin 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 Origin?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.