UMass-Rescue / UMass-Rescue/RescueBox
Rescuebox: UI workflow agent
Open
Nobody has claimed this yet.
complex
hackathon
- Dominant language
- Python
- Stars
- 6
- Forks
- 15
- Avg merge
- 14h 42m
- Merged PRs (30d)
- 7
Description
create a ui workflow agent for recuebox
ui-tars
scenario: given a UI prompt to find "something interesting" and media files. run rescuebox models/pipelines to extract and summarize findings
eg: here is a bunch of images , find teen with red shirt and confirm its not a fake image.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the UI-TARS project linked in the issue and the RescueBox models/pipelines that process media. Define the UI workflow, prompt handling, and expected extraction and summary outputs for the example image-search scenario; done means the agent can run that scenario and report its findings.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, computer-vision, frontend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100