Home
Softono
OpenCometAI

OpenCometAI

Open source MIT JavaScript
30
Stars
7
Forks
0
Issues
3
Watchers
1 month
Last Commit

About OpenCometAI

Open Comet is an autonomous AI agent integrated into your Chrome browser. It enables safe, transparent, and multi-modal web automation—allowing AI models to browse, research, and interact with the web just like a human.

Platforms

Web Self-hosted

Languages

JavaScript

Open Comet Logo

Open Comet

The autonomous AI browser agent for deep research & tasks.

Version JavaScript Chrome Extension License

OpenAI Anthropic Gemini Mistral AI Ollama


Open Comet is an autonomous AI agent that lives in your browser's side panel. It operates on a "Zero-Data" architecture, ensuring your privacy by keeping history local while providing high-fidelity execution for research, browsing, and multi-step automation.

🚀 Key Features

  • Autonomous Browsing: Executes complex, multi-step workflows across any website.
  • Deep Research Engine: STORM-inspired loops to synthesize information from multiple sources and tabs.
  • High-Fidelity Execution: Uses pixel-perfect DOM grounding and visual analysis for reliable interaction.
  • "Zero-Data" Privacy: No history or sensitive data is stored on external servers—everything stays on your device.
  • Advanced Skills System: Create, reuse, and share specialized automation workflows (Skills).
  • Flexible Model Support: Works with Cloud (OpenAI, Anthropic, Gemini, Mistral) and Local (Ollama) models.
  • Modern UI: A compact, Apple-inspired capsule overlay with glassmorphism for a native, premium feel.

✨ What's New in v1.1

  • Refined Branding: Official Open Comet logo and branding across the extension.
  • Mistral-Optimized Engine: Automated prompt downsizing and aggressive screenshot compression.
  • Enhanced Token & Cost Tracking: Native settings dashboard for real-time monitoring of costs and token usage.
  • Improved Task Resilience: Better search-box detection and stale-UID fallbacks for higher success rates.
  • Session Continuity: Seamlessly resumes tasks within the same tab group and chat session.

🛠️ Installation & Setup

  1. Get the Source:
    • Download: Get the Open Comet v1.1.0 release and unzip it.
    • Clone: Alternatively, run git clone https://github.com/princechouhan19/OpenCometAI.git
  2. Install the Extension:
    • Open Chrome and go to chrome://extensions.
    • Enable Developer Mode (top-right toggle).
    • Click Load unpacked and select the root directory (unzipped folder or cloned repo).
    • Pin Open Comet from your extensions menu.
  3. Account & License:
    • Create an account on opencomet.onrender.com/profile.
    • Generate a License Key from your dashboard.
    • In the Open Comet extension, login with your credentials and add your License Key.
  4. Configuration:
    • Open the side panel, go to Settings, and select your Provider and Model.
    • Add your API Key for the chosen provider.
  5. Run Your First Task: Type a command in the input box and watch the agent work!

🗺️ Roadmap

  • [ ] Multi-Agent Collaboration: Parallel sub-agents for faster complex research.
  • [ ] Skill Marketplace: Discover and share community-built skills.
  • [ ] Advanced Vision Integration: Native support for the latest vision-capable models.
  • [ ] Enhanced Local Reasoning: Optimized performance for 8B-70B local models via Ollama.

🤝 Contributing

We welcome contributions from the community! Whether you're fixing a bug, adding a new skill, or improving the documentation, please check out our Contributing Guide to get started.

📜 License

Open Comet is open-source software licensed under the MIT License.

📈 Star History

Star History Chart

Built with ❤️ for the next generation of autonomous browsing.