hailo-ai/tappas
High-performance, optimized pre-trained template AI application pipelines for systems using Hailo devices
This provides optimized building blocks and pre-trained AI models for video processing. It takes live video feeds or recorded footage and outputs enhanced video with AI-driven insights like object detection, specifically designed for systems equipped with Hailo-8 or Hailo-10H AI accelerator devices. It is for engineers and developers creating high-performance, edge-based video analytics applications.
180 stars.
Use this if you are developing video analytics solutions on Hailo AI accelerator hardware and need to rapidly deploy high-performance, AI-powered video processing pipelines.
Not ideal if you are not using Hailo-8 or Hailo-10H devices, or if you require a general-purpose AI development framework not focused on video.
Stars
180
Forks
77
Language
C++
License
LGPL-2.1
Category
Last pushed
Jan 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hailo-ai/tappas"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
roboflow/inference
Turn any computer or edge device into a command center for your computer vision projects.
roboflow/roboflow-python
The official Roboflow Python package. Manage your datasets, models, and deployments. Roboflow...
dusty-nv/jetson-inference
Hello AI World guide to deploying deep-learning inference networks and deep vision primitives...
Apra-Labs/ApraPipes
A pipeline framework for developing video and image processing application. Supports multiple...
open-edge-platform/geti
Build computer vision models in a fraction of the time and with less data.