Private
Keep user data local and under your control
Build intelligent ideas with our platform for local AI
Our products are...
Fast
Accelerate AI locally, inference times down to 2 ms
Efficient
Low power demand to allow embedded applications
Offline
Deploy in the field where connectivity is limited
Our products
See all productsDev Board
A single-board computer with a removable system-on-module (SoM) featuring the Edge TPU.
- Supported OS: Mendel Linux (derivative of Debian)
- Supported Framework: TensorFlow Lite
- Languages: Python and C++
- Works with AutoML Vision Edge
- Datasheet
USB Accelerator
A USB accessory featuring the Edge TPU that brings ML inferencing to existing systems.
- Supported host OS: Debian Linux
- Compatible with Raspberry Pi boards
- Supported Framework: TensorFlow Lite
- Works with AutoML Vision Edge
- Datasheet
Camera
5-megapixel camera module that's compatible with the Coral Dev Board.
- Omnivision Sensor
- Autofocus
- Auto exposure control
- 25 mm x 25 mm
- Datasheet
Want to learn more about the Edge TPU? Check out the FAQ
Flexible enough for startups and large‑scale enterprises
Prototype
Imagine what’s possible with local AI, then move right into proof-of-concept. Our products make it easy to take your idea from sketch pad to workbench.
Scale
Our products are designed to grow with you, integrating seamlessly into production processes at any scale.
Deploy
Robust modular components bring reliable AI to more applications than you ever dreamed possible.
News & announcements
See more
May 29, 2019
May 2019 Updates
An offline compiler, new project tutorials, and MDT updates are now available.
Read moreThe Coral Dev Board Takes Google’s AI to the Edge
IEEE Spectrum
April 19, 2019
"There’s a steady drumbeat about how deep learning is going to touch nearly every area of technology, not least from us here at IEEE Spectrum. So, like a lot of folks, I’ve been interested in getting my hands dirty and learning some of the tools and techniques."
Read at IEEE Spectrum
March 6, 2019
Google unveils new tools to bolster AI hardware development
Both dev board and accelerator are powered by Google’s Edge TPU chips, which are ASIC processors no bigger than your fingernail
Read at The Verge