MCPgee
MCPgee
MCPgeeMCPgee

RoamPal

v1.0.0•Knowledge & Memory•stable

🐍 🏠 - Outcome-based persistent memory for AI coding tools. Memories that help get promoted, memo

agent-memoryai-assistantai-codingai-coding-assistantai-memory
Share:
46
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is RoamPal?

RoamPal is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🐍 🏠 - outcome-based persistent memory for ai coding tools. memories that help get promoted, memo

🐍 🏠 - Outcome-based persistent memory for AI coding tools. Memories that help get promoted, memo

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

Features

  • MCP protocol support

Use Cases

Persistent memory for AI coding
Outcome-based agent learning
roampal-ai

Maintainer

LicenseApache 2.0
Languagepython
Versionv1.0.0
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx roampal-core

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 RoamPal

RoamPal Core is a persistent, outcome-based memory system for AI coding assistants that stores and retrieves knowledge using ChromaDB and ONNX Runtime for local vector search. It provides MCP tools for adding, searching, updating, and scoring memories so that AI agents like Claude Code and Opencode can remember project context, coding preferences, past decisions, and outcomes across sessions. Unlike simple note-taking, RoamPal tracks which memories led to positive outcomes, enabling the agent to prioritize useful patterns over time.

Prerequisites

  • Python 3.10+ installed
  • CPU with AVX2 support (Intel Haswell 2013+ or AMD Excavator 2015+)
  • ~800 MB RAM and ~500 MB free disk space for the local vector model
  • pip available for package installation
  • Claude Code, Opencode, or another MCP-compatible client
1

Install RoamPal

Install the roampal package from PyPI using pip.

pip install roampal
2

Initialize RoamPal

Run roampal init to auto-detect your installed AI coding tools and configure the MCP server integration automatically.

roampal init
3

Start the RoamPal server

Start the background memory server. It must be running for your MCP client to connect and use memory tools.

roampal start
4

Set a project profile (optional)

Use profiles to keep memories separate across projects. Set the ROAMPAL_PROFILE environment variable or use the profile command.

roampal profile create my-project
roampal profile use my-project
5

Verify server status

Check that the server is running and review memory statistics.

roampal status
roampal stats

RoamPal Examples

Client configuration

Claude Code project-level configuration (.claude.json) to set a project-specific memory profile for RoamPal.

{
  "mcpServers": {
    "roampal": {
      "command": "roampal",
      "args": ["start", "--foreground"]
    }
  },
  "env": {
    "ROAMPAL_PROFILE": "my-project"
  }
}

Prompts to try

Example prompts to exercise RoamPal's memory tools through your AI coding assistant.

- "Remember that we decided to use PostgreSQL instead of SQLite for this project"
- "Search my memory for anything related to our authentication approach"
- "Update the memory about our API design to reflect the new versioning scheme"
- "Score the memory about the caching strategy — it worked well in production"

Troubleshooting RoamPal

roampal init fails with AVX2 not supported error

RoamPal uses ONNX Runtime for local embedding inference, which requires AVX2 CPU instructions. Check your CPU with: python -c "import cpuinfo; print(cpuinfo.get_cpu_info()['flags'])". If AVX2 is not listed, RoamPal cannot run on this machine — consider using a newer host.

search_memory returns no results for queries that should match

Memories are stored per profile. Run roampal stats to confirm the active profile has stored memories. If using multiple profiles, ensure ROAMPAL_PROFILE matches the profile where the memories were added.

MCP client cannot connect to the RoamPal server

The roampal server must be running before the MCP client starts. Run roampal start and then roampal status to confirm it is up. If using roampal start in the background, check roampal status output for port and socket details and ensure no firewall rules block the connection.

Frequently Asked Questions about RoamPal

What is RoamPal?

RoamPal is a Model Context Protocol (MCP) server that 🐍 🏠 - outcome-based persistent memory for ai coding tools. memories that help get promoted, memo It connects AI assistants to external tools and data sources through a standardized interface.

How do I install RoamPal?

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

Which AI clients work with RoamPal?

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

Is RoamPal free to use?

Yes, RoamPal 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

RoamPal Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to RoamPal? 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": { "roampal-core": { "command": "npx", "args": ["-y", "roampal-core"] } } }

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

Read the full setup guide →

Ready to use RoamPal?

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