GodMode  by smol-ai

AI chat browser for accessing multiple LLMs' web apps

created 2 years ago
4,303 stars

Top 11.6% on sourcepulse

GitHubView on GitHub
Project Summary

GodMode is a dedicated AI chat browser designed for power users to simultaneously access and interact with multiple large language models (LLMs) like ChatGPT, Claude, Bard, and Perplexity. It aims to streamline the workflow of users who frequently leverage various AI services by providing a unified interface with a single keyboard shortcut for quick access and input submission across all selected models.

How It Works

The application functions as a multi-tabbed webview, where each tab hosts the web application of a different AI chat service. Users can type a single prompt that is sent to all active webviews concurrently. This "Mixture of Experts" approach allows users to benefit from the diverse outputs and specialized capabilities of different models without manual switching. The architecture prioritizes direct webapp access to ensure immediate availability of new features, such as code interpreters or multimodal inputs, often released first via web interfaces before API support.

Quick Start & Requirements

  • Installation: Download pre-compiled binaries from https://github.com/smol-ai/GodMode/releases/latest. For Macs, use arm64 for Apple Silicon or universal .dmg for Intel. For Windows, use .exe. For Linux, use .AppImage or the AUR package.
  • Prerequisites: Log in to your Google account within the application to authenticate with most services. Some services like Bing may require a refresh after login.
  • Build from Source: Requires git, npm. Clone the repo, run npm install --force, then npm run start (development) or npm run package (binaries).

Highlighted Details

  • Simultaneous input to multiple LLMs (ChatGPT, Claude 2, Perplexity, Bing, Bard, Llama2 via OobaBooga/Lepton.ai, Poe, etc.).
  • Keyboard shortcuts for quick open (Cmd+Shift+G), submission (Cmd+Enter), and toggling light/dark mode.
  • Supports webapp-specific features like Code Interpreter and multimodal inputs, bypassing API limitations.
  • Pane resizing, rearranging, and popping out individual webviews.

Maintenance & Community

The project is actively maintained by smol-ai. Contributions are welcomed, with a CONTRIBUTING.md file available. Links to community resources are not explicitly provided in the README.

Licensing & Compatibility

The repository does not explicitly state a license in the provided README text. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

Windows and Linux support are noted as needing significant work. Some authentication flows, particularly for Google Bard, are described as finicky. Light/dark mode toggling is currently broken in the rewrite. The project may be flagged as untrusted by operating systems due to a lack of code signing on some platforms.

Health Check
Last commit

1 year ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
0
Star History
68 stars in the last 90 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems), Pietro Schirano Pietro Schirano(Founder of MagicPath), and
1 more.

SillyTavern by SillyTavern

3.2%
17k
LLM frontend for power users
created 2 years ago
updated 3 days ago
Feedback? Help us improve.