[Feature]: Add CometAPI as Model Provider for Enhanced Multimodal Capabilities #1692
Description
Which destkop app does this feature request relate to?
- Select a project 👇
- Agent-TARS (cli, server, agent, tool etc.)
- UI-TARS Desktop
What problem does this feature solve?
UI-TARS Desktop currently supports various AI model providers for its multimodal GUI agent capabilities. Adding CometAPI as a model provider would give users access to 500+ different AI models and enhanced multimodal generation capabilities (text, images, video, audio), expanding the automation possibilities for both desktop and browser operations.
What does the proposed features look like?
Integrate CometAPI as a configurable model provider option in both Agent-TARS CLI and UI-TARS Desktop applications. This would allow users to:
- Configure CometAPI endpoints (base URL: https://api.cometapi.com/v1/)
- Access 500+ AI models through OpenAI-compatible APIs
- Leverage multimodal capabilities for GUI automation tasks
- Use CometAPI models for vision-language tasks in computer use scenarios
CometAPI Resources
Implementation Offer
We'd be glad to help integrate CometAPI into your project. If you're interested, we can submit a pull request that aligns with your project's coding standards and guidelines.