reComputer AI Lab | Edge AI Models & Tools
What is reComputer AI Lab?
reComputer AI Lab is an open platform for deploying edge-AI models on Seeed Studio reComputer hardware with a single Docker command. It brings together 100+ optimized computer-vision, LLM, and VLM models, a hardware toolchain for flashing and model conversion, step-by-step tutorials, and community projects — all tuned for reComputer devices built on NVIDIA Jetson, Rockchip RK3576/RK3588, and Raspberry Pi. Every model ships with benchmarks and a ready-to-run deployment command, so you can go from browsing to running inference at the edge in just two steps. Whether you are prototyping a vision application, running a local LLM, or shipping an industrial AI project, reComputer AI Lab lowers the barrier to real-world edge AI with reproducible, hardware-optimized workflows.
Quick Access
Jump straight to what you need
Explore Models
CV, LLM, and VLM models ready to run on reComputer.
Browse all models →Tools
reComputer-optimized toolchain, one command to use.
Browse tools →Tutorials
Step-by-step guides and hands-on tutorials for reComputer.
Browse all tutorials →Community Projects
Share your community projects built on reComputer.
View all projects →Community Projects
View all projectsSee what the community is building with reComputer
Object Detection with YOLO11 on reComputer-RK
Industrial CV solution for RK3588/RK3576: NPU-accelerated YOLO11 & MJPEG streaming.
Gun detection with Frigate NVR on R2000
Real-time AI firearm detection on reComputer R using YOLO11 and Hailo.
Deploy NVBlox with Orbbec Camera on Jetson AGX Orin
Isaac ROS NVBlox: GPU-powered real-time 3D mapping for robots.
Football Player Tracking Analysis Using reComputer RK3576
Leverage reComputer RK3576 RGA 2D hardware acceleration and VPU MPP acceleration. Run the YOLOv8n model to detect football players and achieve real-time analysis.
YOLOv8 Real-time Inference CPP Project with reComputer RK3576
A multi-source input, multi-stream output, YOLOv8 real-time inference project based on RK3576, RKNN, MPP, RGA, and ZLMediaKit.
Multi-scenario Fall Detection Based on reComputer RK3576
Fall behavior detection in multi-scenario and multi-target situations using the YOLOv8n‑pose model, with inference acceleration powered by the reComputer RK3576, and simple information feedback via a web page.
Airborne Object Detection on reComputer RK3576
VisDrone-trained YOLOv8s for aerial object detection on RK3576, supporting 11 airborne classes including pedestrian, vehicle, and cyclist.
Building a Private Home Assistant Voice Assistant on the RK3576
Build a private, local Home Assistant voice assistant on the Rockchip RK3576. The stack combines Whisper for speech recognition, Piper for speech synthesis, openWakeWord for wake-word detection, and Qwen for local conversation—all accelerated by the RK3576 NPU.
RK3576 VPU and NPU Hardware Acceleration Benchmark
Benchmark results for MPP hardware-accelerated YUV420 to MJPG/H264/H265 encoding, MJPG to YUV420 decoding, and RKNN acceleration of YOLOv8n, YOLOv8s, and YOLOv8m inference on the reComputer RK3576.