Magical-Bear/Multi-modal-Sandtable
Multi-Sensors funsion traffic Sandtable. Micropy with ESP32 connect env sensor and publish to MQTT. Microphone get sounds translate to text, RTSP Cam with YOLO identify The Car, Fingers positions. Using LLM intent recognition and slot filling to concat text question and semantic vision data, could answering mqtt, visual and execute operations.
Stars
6
Forks
1
Language
C
License
MIT
Category
Last pushed
Oct 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Magical-Bear/Multi-modal-Sandtable"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
morettt/my-neuro
This project lets you create your own AI desktop companion with customizable characters and...
uezo/aiavatarkit
🥰 Building AI-based conversational avatars lightning fast ⚡️💬
uezo/ChatdollKit
ChatdollKit enables you to make your 3D model into a chatbot
Open-LLM-VTuber/Open-LLM-VTuber
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face...
AlphaAvatar/AlphaAvatar
A real-time interactive Omni Avatar built on LiveKit, which allows you to seamlessly integrate...