rad-agent

by eth-medical-ai-lab · Agent Tool · ★ 24

About rad-agent

RadAgent Transparent and reliable chest CT report generation through tool-using, stepwise reasoning Overview RadAgent is a tool-using AI agent for chest CT report generation that produces reports through a stepwise, interpretable process. Each generated report is accompanied by a fully inspectable trace of intermediate decisions and tool interactions, allowing clinicians and researchers to examine how the reported findings are derived. Beyond transparency, RadAgent improves chest CT report generation over its 3D VLM backbone counterpart, CT-Chat, across several dimensions.

Quick Facts

Stars24
Forks1
LanguageJupyter Notebook
CategoryAgent Tool
Quality Score66.3648408077246/100
Last Updated2026-06-03
Created2026-04-17
Est. Tokens~167k

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Jupyter Notebook Agent Tools

Frequently Asked Questions

What is rad-agent?

rad-agent is RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography. It is categorized as a Agent Tool with 24 GitHub stars.

What programming language is rad-agent written in?

rad-agent is primarily written in Jupyter Notebook.

How do I install or use rad-agent?

You can find installation instructions and usage details in the rad-agent GitHub repository at github.com/eth-medical-ai-lab/rad-agent. The project has 24 stars and 1 forks, indicating an active community.

View on GitHub → Browse Agent Tool tools