The #AI Hardware Partner
Shenzhen, Austin & Nagoya
- Tweets 24,350
- Following 1,448
- Followers 78,801
- Likes 14,552
Pinned Tweet
#reBot B601-DM & B601-RS are now supported by @huggingface @LeRobotHF! 🤗
Build imitation learning workflows with Teleoperate → Record → Train → Deploy, using #LeRobot datasets and models for real-world #robotic tasks.🔗 huggingface.co/docs/lerobot/…
Check reBot GitHub repo for more hardware info: github.com/Seeed-Projects/re…
New robot added to LeRobot! 💪
Both DM and RS versions of the reBot B601 from @seeedstudio are now officially supported. The arm features a 2.5kg payload capacity and 6 degrees of freedom + gripper.
In the example below, the robot performs towel folding fully autonomously. The ACT model was trained on just 200 examples.
2
8
40
7,574
When the right component isn’t on hand, creativity gets to work. 😂
For your next batch, let Seeed Fusion handle component sourcing and PCB assembly.
Upload your BOM and Gerber files:
seeedstudio.com/fusion_pcb.h…
#SeeedFusion #PCBA
3
490
🤖📦Did you spot this little robot helping move things between booths at ROSCon 2026 in Toronto?
Meet BETL, a personal robotics project by Isaac Doubek (IG: @ rustedfriend), featuring #reSpeakerFlex as its audio input module. From hotel-room soldering to real-world action on the show floor — that's maker spirit!
🔮 More to look forward to?
BETL's shell design is taking shape, starting with a physical scale model.
More iterations, navigation, and autonomy could be on the horizon!
Excited to see what's next for BETL! 🚀
🛒reSpeaker Flex: seeedstudio.com/reSpeaker-Fl…
#SeeedStudio #reSpeaker #reSpeakerFlex #MicrophoneArray #XMOS #VoiceAI #SoundAI #EdgeAI #EmbeddedAI #EmbodiedAI #XMOS #Robot #Robotic #VoiceInterface #SmartEarforEmbodiedAI #TheAIHardwarePartner
2
8
696
A step counter you build yourself, instead of a $200 fitness band with a closed app ⌚
@pradeeplogu0 built one on @ZephyrIoT with our XIAO nRF54LM20A Sense and Round Display. No app: set goals and watch live motion data from Chrome over Bluetooth.
Check it out on @Hacksterio 👉 tinyurl.com/msn3t9am
1
4
12
1,357
Dead Wi-Fi. Frozen kiosk. Angry guest.
The fix isn't another chip.
It's deciding which answers can't disappear—FAQs, directions, machine help—and running them locally.
Define that and deployment gets predictable, support becomes billable:
seeed.cc/solutions/acoustic-…
#VoiceAI #EdgeAI
4
1,118
🚀🔥reComputer #RK3588 Module is Coming Soon!!!
⚡ Octa-core CPU: 4× Cortex-A76 + 4× Cortex-A55
🧠 6 TOPS NPU for on-device AI acceleration
💾 Up to 32GB RAM & 128GB eMMC
🔌 Rich I/O with a 260-pin SO-DIMM interface
🖥️ 8K video decoding at 60fps
From #CV to #LLM/#VLM workloads, get ready to explore new possibilities for industrial edge AI. 🤖
👀 Coming soon. Stay tuned!
🛒 reComputer RK3576 Module is IN STOCK: seeedstudio.com/reComputer-R…
#SeeedStudio #reComputerRK #Rockchip #reComputer #RK3588 #Module #VisionAI #EdgeAI #AIoT #ComputerVision #reComputerAILab #AIDeployment #TheEasierPowerfulAIComputer #TheAIHardwarePartner
1
3
44
2,463
Congrats! Glad to see the #reBot arm is also enabled with the Dream-1 API, powered by the general #WAM brain. Looking for more real-world scaling tasks & challenges that reBot can handle soon🤩
More about the $1799 reBot Arm at Seeed Studio: seeedstudio.com/reBot-Arm-B6…
Today, Dream Labs is coming out of stealth with Dream-1, a robot foundation model that controls bimanual robots it has never seen, on tasks it was never shown, in places it has never been, from $3/hour.
Dream API is live for everyone, today. 🧵
4
9
1,490
🗼 Tokyo, manga style!
Tokyo Pop: City Weather Clock by frankfan blends Japanese temples, iconic towers, and vibrant city streets with a live clock and weather updates.
Built with SenseCraft Seeedash — no code.
Explore the design 👉 sensecraft.seeed.cc/hmi/temp…
1
14
1,918
🚀 #Rockchip RK3576 + #RaspberryPi PoE+ HAT: Power Over Ethernet Meets Edge AI!
We adapted the #reComputer #RK3576 Module to the Raspberry Pi #PoE+ HAT, enabling PoE-powered operation through Ethernet while running #YOLO11 from Seeed Studio's #reComputerAILab.
One compact setup, combining simplified power delivery with on-device AI inference. No extra power adapter needed for the board when powered through a compatible PoE setup.
🔌 PoE-powered operation
👁️ YOLO11 object detection
⚡ Edge AI on RK3576
🛠️ Explore more AI models and demos in reComputer AI Lab: sensecraft.seeed.cc/ai-lab/e…
🛒 reComputer RK3576 Module is IN STOCK: seeedstudio.com/reComputer-R…
5
29
2,899
An AI that uses a real iPhone, with a $7 board as its eyes and hands 📱
Henry Yuan's ESP32 iPhone Agent runs on our XIAO ESP32S3: the phone mirrors its screen to the board, and the board taps back as a USB mouse. No jailbreak.
Check it out on @github 👉 tinyurl.com/53vwy369
7
3
27
2,504
🚀 CodeCraft now supports Sticky!
Want to build your own Sticky app? Just describe what you want:
💬 Describe → 🤖 Generate → ☁️ Compile → ⚡ Flash → ✨ Run
Try a Sudoku game, habit tracker, decision maker — or build something in 5 minutes.
One prompt, a working Sticky.
🎁 Try for free: codecraft.seeed.cc/?utm_sour…
#CodeCraft #Sticky #SeeedStudio #VibeCoding #HardwareDevelopment #Maker
2
6
1,549
🔥 reComputer Robotics J601: Multiple Sensors, Concurrent AI, One Edge Platform
6 camera feeds. LiDAR point clouds. Multiple AI workloads. Just 47% GPU utilization. Powered by @nvidia Jetson AGX Thor, our #reComputer Robotics J601 series delivers the performance to bring multiple perception workloads together on one edge platform.
📡 Sensor inputs: 6 cameras + LiDAR point clouds
👀 See the full pipeline in action:
🔹 Object detection across 6 camera feeds | YOLO26n, TensorRT FP16
🔹 Road and lane segmentation | YOLOP,TensorRT FP16
🔹 Geometric fusion and local mapping | CUDA, calibration/pose alignment
Camera views, bird’s-eye views, and 3D point clouds reveal how the pipeline builds a shared spatial view.
⚙️ Built for sensor-rich systems:
• 4 × 10GbE RJ45 ports for sensor connectivity and expansion
• Live network and compute monitoring
⚡ One sampled snapshot:
• Object detection: 4.4 ms
• Road segmentation: 26.2 ms
• GPU: 47% | CPU: 12% | RAM: 13%
🎥 Watch the demo below.
Explore the reComputer Robotics J601👉wiki.seeedstudio.com/jetson/…
Performance varies with scene and configuration.
#Robotics #EdgeAI #NVIDIAJetson #SensorFusion
2
14
2,670
🔗 Check out the product page: seeedstudio.com/reComputer-J…
513
Detect multiple barcodes with reCamera Pro
Building a parcel-scanning station? Several labels may enter the camera’s field of view together. How would you approach reading them?
Start with this 20-second reCamera Pro demo, then follow our Wiki to build your own QR code and barcode recognition application！
#reCameraPro #BarcodeRecognition #theGotoAIcameraforYOLOattheedge #Seeed #SeeedStudio #HowToBuildAnAICamera #EdgeAI
1
3
15
2,112
Wiki:wiki.seeedstudio.com/recamer…
reCamera Pro: seeedstudio.com/reCamera-Pro…
2
452
🐱 A new cat fact for your desk.
Cat Facts by Meilily uses the Cat Facts API to bring quick feline trivia to your ePaper display in a simple, playful layout.
Built with SenseCraft Seeedash — no code.
Explore the design 👉 sensecraft.seeed.cc/hmi/temp…
3
5
18
1,918
🛠️ Tap, press, listen—make L2 Pro yours!
Powered by ESP32-S3, Wio Tracker L2 Pro combines a touchscreen, speaker, buttons, LEDs & MicroSD support for flexible interaction and customization.
💬 What would you build first?
🐦 Grab yours now—early bird 15% off!
👉 seeedstudio.com/Wio-Tracker-…
#SeeedStudio #theAIHardwarePartner #theIndieCommunicationSystem #Meshtastic #ESP32
2
5
48
3,965
A robot with four cameras still can't see properly — unless it knows where every pixel is.
Module 2 of our Mobile Robot Full-stack Development course. Module 1 built the robot brain — #Jetson, #JetPack, #ROS2. Module 2 gives it eyes: hardware sync → #CameraCalibration → metric #BEV, with a valid-mask check on every pixel.
Two things people get wrong:
• Skipping hardware sync, then wondering why extrinsics never converge
• Treating the BEV as a preview, not a metric image in a defined frame
📖Read the full article:
seeedstudio.com/blog/2026/10…
⭐ Learn more about the course:
github.com/Seeed-Projects/mo…
ALT A mobile robot chassis on an orange-and-black frame sits in a dark industrial workspace lit with green accent lighting. Branding and the title "Mobile Robot Full-stack Development in Practice" occupy the left half. A card in the lower left marks this as Module 2: Fundamentals of Vision Systems — GMSL2 Multi-Camera, Calibration and BEV Surround View — and points to the article. A robot-related slogan sits upper right.
Made with AI
2
5
15
1,955
The J501 + GMSL2 eight-channel board used in Module 2:
👉 seeedstudio.com/reComputer-R…
Module 2 code and configs:
👉 github.com/Seeed-Projects/mo…
1
531