moly  by moxin-org

Rust desktop app for local/cloud LLM access and AI agent integration

created 1 year ago
309 stars

Top 88.0% on sourcepulse

GitHubView on GitHub
Project Summary

Moly is a desktop and cloud AI LLM GUI client built in pure Rust, targeting developers and power users who want a unified interface for various AI providers, including local LLMs via its Moly Server and AI agents via the MoFa framework. It offers a cross-platform experience with pre-built releases for macOS, Linux, and Windows, simplifying local LLM interaction and AI agent integration.

How It Works

Moly leverages the Makepad UI toolkit for its cross-platform graphical interface and Project Robius for application development. It supports OpenAI-compatible APIs and integrates with Moly Server, a local LLM runner, and MoFa, a framework for building AI agents exposed via Dora servers. This architecture allows for flexible integration of diverse AI backends within a single, native application.

Quick Start & Requirements

  • Install: Download pre-built releases or build from source using cargo run --release.
  • Prerequisites: Rust 1.79+ required for packaging. Linux requires openssl, clang, binfmt, Xcursor/X11, asound/pulse. macOS and Windows may require specific build tools. Moly Server requires downloading an executable or compiling from source. MoFa integration requires Python 3.10+, Dora, and specific Python libraries.
  • Resources: Building from source requires a Rust toolchain. Running local LLMs depends on model size and hardware.
  • Docs: MolyKit documentation, Moly Server instructions, MoFa, Dora installation.

Highlighted Details

  • Pure Rust implementation for cross-platform compatibility.
  • Supports OpenAI-compatible APIs, local LLMs via Moly Server, and AI agents via MoFa.
  • Packaging support for .app, .dmg, .deb, AppImage, and .exe installers.
  • Extensible provider system via supported_providers.json.

Maintenance & Community

The project is in early development. Community interaction channels are not explicitly listed in the README.

Licensing & Compatibility

The project appears to be licensed under the MIT License. Compatibility for commercial use is generally permissive under MIT.

Limitations & Caveats

Moly is in early development, with potential for bugs and unexpected behavior. The pacman package for Linux has not yet been tested. Specific macOS packaging steps require granting "App Management" permissions.

Health Check
Last commit

2 days ago

Responsiveness

Inactive

Pull Requests (30d)
11
Issues (30d)
1
Star History
73 stars in the last 90 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems), Shawn Wang Shawn Wang(Editor of Latent Space), and
8 more.

llm by rustformers

0.0%
6k
Rust ecosystem for LLM Rust inference (unmaintained)
created 2 years ago
updated 1 year ago
Feedback? Help us improve.