moling  by gojue

Local office AI assistant for computer/browser use via MCP server

Created 6 months ago
310 stars

Top 86.7% on SourcePulse

GitHubView on GitHub
Project Summary

MoLing is a dependency-free, locally deployed office AI assistant that enables system interaction for tasks like file manipulation and command execution. It targets users seeking to automate desktop tasks and integrate AI capabilities without complex environment setups, offering a streamlined approach to office automation.

How It Works

MoLing acts as a server implementing the MCP protocol, allowing AI clients to interact with the host operating system. It leverages OS APIs for file system operations and can execute system commands. Browser control is achieved via chromedp, requiring a Chrome installation. This approach bypasses traditional language-specific dependencies (Node.js, Python), simplifying deployment and avoiding environment conflicts.

Quick Start & Requirements

  • Install: Via shell script (Linux/macOS) or PowerShell (Windows, untested). Direct download from releases or build from source (requires Golang toolchain) are also options.
  • Prerequisites: Chrome browser required for browser control. On Windows, Chrome's path must be in system environment variables.
  • Configuration: A configuration file is generated at ~/.moling/config/config.json. The moling client --install command can automatically configure supported MCP clients.
  • Docs: MoLing MCP Server English

Highlighted Details

  • Dependency-free, cross-platform (Windows, Linux, macOS) operation.
  • Supports file system operations (read, write, merge, statistics, aggregation).
  • Enables direct system command execution.
  • Browser control via chromedp.
  • Compatible with MCP clients like Claude, Cline, and Cherry Studio.

Maintenance & Community

The project is hosted on GitHub. No specific community channels (Discord/Slack) or notable contributors are mentioned in the README.

Licensing & Compatibility

  • License: Apache License 2.0.
  • Compatibility: Permissive license allows for commercial use and integration with closed-source applications.

Limitations & Caveats

The project has only been tested on macOS; functionality on other operating systems, particularly Windows, is not guaranteed and may have issues. Command-line operations are noted as potentially dangerous.

Health Check
Last Commit

3 months ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
0
Star History
2 stars in the last 30 days

Explore Similar Projects

Starred by Luis Capelo Luis Capelo(Cofounder of Lightning AI), Addy Osmani Addy Osmani(Head of Chrome Developer Experience at Google), and
23 more.

goose by block

0.8%
20k
Open-source AI agent for automating complex engineering tasks
Created 1 year ago
Updated 23 hours ago
Feedback? Help us improve.