https://youvenz.github.io/tags/multi-agent/Recent content in Multi-Agent on Rachid Youven ZeghlacheHugoen-usSun, 01 Feb 2026 00:00:00 +0000https://youvenz.github.io/projects/medgemma-workflow/Sun, 01 Feb 2026 00:00:00 +0000https://youvenz.github.io/projects/medgemma-workflow/<h2 id="overview">Overview</h2> <p><strong>MedFlowAssist</strong> is a multi-agent medical assistant that combines the power of <a href="https://deepmind.google/models/medgemma/">MedGemma</a>, medical speech recognition (MedASR), and <a href="https://github.com/BerriAI/litellm">LiteLLM</a> to deliver clinical-grade AI assistance across a wide range of healthcare workflows.</p> <p><a href="https://github.com/YouvenZ/MedFlowAssit#prerequisites"><img src="https://img.shields.io/badge/Python-3.11%2B-blue?logo=python&amp;logoColor=white" alt="Python 3.11+"></a> <a href="https://github.com/YouvenZ/MedFlowAssit#quick-start-step-by-step"><img src="https://img.shields.io/badge/Flask-3.0-lightgrey?logo=flask" alt="Flask"></a> <a href="https://github.com/YouvenZ/MedFlowAssit#license"><img src="https://img.shields.io/badge/License-Research%20%2F%20Educational-green" alt="License: Research"></a></p> <h2 id="key-features">Key Features</h2> <ul> <li><strong>13 clinical workflows</strong> covering documentation, triage, diagnosis support, and more</li> <li><strong>12 pre-built scenarios</strong> ready to deploy out of the box</li> <li><strong>Voice dictation</strong> via MedASR for hands-free clinical note-taking</li> <li><strong>Multimodal input</strong> — image, PDF, and CSV upload supported</li> <li><strong>Multi-agent orchestration</strong> with LangGraph-style task delegation</li> </ul> <h2 id="clinical-workflows">Clinical Workflows</h2> <p>The assistant covers end-to-end workflows including:</p>