One command, and your agent can see.
The EOT-1 runs an MCP server and a REST API on the device itself. No SDK, no cloud relay, no waiting on a vendor.
The answer lands wherever you already are.
The EOT-1 speaks MCP and REST, so your agent can put what it sees into anything with an API. That is the difference between a camera you check and a camera that tells you.
Other things to ask it.
- ❯Watch the printer and tell me the moment the print fails.
- ❯Every 30 seconds, count the people in frame and write it to Postgres.
- ❯Diff this shelf against the photo from this morning and tell me what moved.
Common questions
What do I need to install?
Nothing. The EOT-1 announces itself at eyeofthetiger.local when it joins your Wi-Fi and serves both an MCP endpoint and a REST API from the device. Add it to an MCP host with one command, or curl it. If your code can make an HTTP request, it can use the camera.
Which model runs the vision?
Whichever you point at it. Claude, OpenAI, Gemini, or a local model on your own box. The camera supplies the image and you choose where inference happens, so you can swap models without touching the hardware. You pay your provider directly and we take no cut of your tokens.
Can I sell what I build?
That is the plan. The marketplace is coming soon, with an 80/20 split in the developer favour. Sign up on the developers page for early access when the publisher programme opens.
Batch 001 is in stock and shipping now.
100 Founder Edition units. Ships worldwide. One-time payment, no subscription required, 30-day returns.