A multimodal AI agent powered by Gemini 2.5 that uses voice and vision to autonomously navigate the web for visually impaired users.
-
Updated
Mar 23, 2026 - Python
#
geminiliveagentchallenge
Here are 4 public repositories matching this topic...
Real-time multimodal AI co-pilot. Gemini 3.0 + Google Cloud Run + Firestore. Sees your screen, answers your questions.
-
Updated
Jul 26, 2026 - Python
Friday is a hands-free AI assistant that listens to your voice and autonomously controls your web browser to complete tasks. Say "Hey Friday" or press the mic button, give a command in plain English, and Friday handles the rest - navigating, clicking, and interacting with websites on your behalf.
python automation gemini speech-recognition tkinter voice-control browser-automation ai-agent hands-free llm browser-use geminiliveagentchallenge
-
Updated
Mar 16, 2026 - Python
A vision-first autonomous web agent powered by Gemini 3 Flash, navigating complex UIs through pixel-based reasoning and functional Yield-Logic.
-
Updated
Mar 15, 2026 - Python
Improve this page
Add a description, image, and links to the geminiliveagentchallenge topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the geminiliveagentchallenge topic, visit your repo's landing page and select "manage topics."