Multimodal Streamlit Apps Generative AI Tools

Streamlit applications that integrate multimodal AI capabilities (text, image, vision analysis) with APIs like Gemini, Groq, or Perplexity. Does NOT include standalone image generation, single-modality chatbots, or non-Streamlit implementations.

There are 44 multimodal streamlit apps tools tracked. The highest-rated is stavrostheocharis/auto-streamlit-studio at 32/100 with 18 stars.

Get all 44 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=generative-ai&subcategory=multimodal-streamlit-apps&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	stavrostheocharis/auto-streamlit-studio AutoStreamlit Studio is an intelligent assistant designed to streamline the...	32	Emerging	18	Python
2	dhineshaps/fetquest-genai The FET Quest Model Portfolio Project created to explore the Generative AI...	29	Experimental	1	Python
3	sitammeur/streamlit-app-builder A Streamlit-based AI assistant generates custom Streamlit app code from...	28	Experimental	7	Python
4	grandelli/dfcx-geminiprovision A Dialogflow CX implementation of a purely determistic agent (intent-based)...	25	Experimental	2	Python
5	sitammeur/PicQ PicQ: Demo for MiniCPM-o 2.6 to answer questions about images using natural language.	24	Experimental	4	Python
6	bnarasimha21/audio-vision-assistant Multimodal AI assistant combining audio and vision capabilities for accessibility	23	Experimental	1	Python
7	AdritPal08/End-To-End-Project-Using-Gemini-Gemify Create stunning content with LLM, the app that uses Google Gemini’s...	23	Experimental	2	Python
8	arjunprabhulal/function-calling-gemma3 Demo project showcasing Gemma3 function calling capabilities using Ollama....	23	Experimental	12	Python
9	mananp-2730/AI-VA Multimodal SaaS Voice Assistant for Spatial BI. Analyzes raw CSVs and...	23	Experimental	1	JavaScript
10	Pavansomisetty21/Visual-Question-Answering-using-Gemini-LLM In this we explore into visual Question Answering Using Gemini LLM and...	23	Experimental	6	Jupyter Notebook
11	Eatosin/Retina-UX-Auditor A Physics-Informed UI/UX Audit Engine. Uses Computer Vision (OpenCV...	22	Experimental	4	Python
12	TABREZ-96/Grammer_Guruji Grammar Guruji is an interactive web application powered by Streamlit,...	22	Experimental	1	Python
13	Krish-afk-bot/ai-visibility-tracker Track brand visibility inside AI-generated recommendations from LLMs like...	22	Experimental	—	Python
14	erroralex/Metadata-Viewer A JavaFX desktop application for extracting and managing AI image generation...	22	Experimental	38	Java
15	ThaiMinhLam/SymbolicResoning Participating in Explainable AI for Educational Question-Answering with...	21	Experimental	5	C
16	codingaslu/Voice-Vision-Assistant-for-Blind Voice & Vision Assistant for the Blind is an AI-powered assistant that helps...	21	Experimental	10	Python
17	abubakarsayem/Amazon-KDP-Book-Metadata-Generator-with-LLM A Streamlit web app that generates Amazon KDP book titles and descriptions...	19	Experimental	—	Python
18	Rahulchaube1/iCanSee-Ultra Open-source AI visual intelligence platform enabling object detection,...	19	Experimental	—	Python
19	AILucifer99/Gemini-GenAI-Studio An implementation of a end to end application that will automate multiple...	18	Experimental	7	Python
20	awakening-ai/OmniResponse OmniResponse: Online Multimodal Conversational Response Generation in Dyadic...	16	Experimental	12	Python
21	CarlosKhoury/Golf-Swing-Analyzer A computer vision web app that analyzes golf swings using MediaPipe and...	15	Experimental	1	Python
22	loresico/gemma3-vision-demo Multimodal Q&A demo using Google DeepMind's Gemma 3	15	Experimental	—	Python
23	bdgaskins27889/cvi-ai-assistant Generative AI for Community Violence Intervention — Trauma-Informed,...	14	Experimental	—	Python
24	abderrewakbendaoud/pokeroast 🎮 Analyze Pokemon teams with AI to expose weaknesses and improve strategies,...	14	Experimental	—	Python
25	guille123giles-cloud/ai-note-digitizer AI Note Digitizer Pro \| Aplicación de Streamlit que utiliza Google Gemini...	14	Experimental	—	Python
26	Mukku27/Inventory-Management-Using-GenAI An intelligent, LLM-powered inventory management system leveraging Google's...	13	Experimental	6	Python
27	smaranjitghose/ObjectSightAI A powerful and intuitive image analysis interface powered by Google's Gemini...	13	Experimental	2	Python
28	Shishir420-GIT/Automation-Generator This application allows users to upload an SOP based pdf, which lets them...	13	Experimental	—	Python
29	fork123aniket/Multi-Round-VLM-powered-Multimodal-Conversational-AI-Navigation-Bot Streamlit App Combining Vision, Language, and Audio AI Models	12	Experimental	3	Python
30	cunhanina/pokeroast An AI-powered "Cyber-Bullying" Dashboard that uses GenAI & Data Science to...	12	Experimental	1	Python
31	Rahilshah01/multimodal-vision-ai-chat A high-performance Multimodal AI Chatbot using Gemini 2.0 Flash to perform...	12	Experimental	1	Jupyter Notebook
32	KaiTheRedNinja/GUI-Dog A digital "guide dog" for the visually impaired	12	Experimental	4	Swift
33	Korosh-Rajaei/Marley-and-Me-pet-adoption-software Pet description generator and translator software using Dash, Flask,...	12	Experimental	—	Jupyter Notebook
34	munas-git/GenAITopicModeling-ResearchTool-2 Enhanced automated topic classification & modeling tool leveraging Google’s...	12	Experimental	1	Python
35	mariamashraf731/VisionPal-Assistive-AI An AI-powered assistive assistant for the visually impaired. Leverages Llama...	12	Experimental	1	Python
36	Mohshaikh23/Gemini-Pro-LLM-App A LLLM app using Gemini pro API	11	Experimental	—	PowerShell
37	Ahmed-Yusuf-1/Vision a React Native mobile application designed to provide users with an...	11	Experimental	—	TypeScript
38	psiba15/gemini-image-storyteller AI-powered Streamlit app that generates stories and narrated audio from...	11	Experimental	—	Python
39	JocelynVelarde/hack4her-genai-app Build your first GenAI App using MongoDB, Gemini API and Streamlit	11	Experimental	—	Python
40	sitammeur/VidiQA VidiQA: Demo for MiniCPM-V 2.6 to answer questions about videos using...	11	Experimental	2	Python
41	ankur-mali/tax-law-reasoning-generator A Python-based system for generating synthetic tax law cases to evaluate...	11	Experimental	—	Python
42	MRamya-sri/Q-A_System-and-Image_Interpretation-using-GEMINI_LLM Project demonstrates Q/A System and Image Interpretation using GEMINI LLM.	10	Experimental	1	Python
43	ArchismwanChatterjee/Hack-Hurricane-1.0 SoundSight Companion: Empowering Independence through Auditory Vision	10	Experimental	1	Python
44	ethank2222/TrinityAI Combines the three most popular LLMs on the market into one Generative AI...	10	Experimental	4	Python