Why this page exists
Most of what we build belongs to the people who paid for it, and lives behind their logo rather than ours. Labs is the part we can show you directly: tools and experiments we run on our own site, published so you can poke at them rather than take our word for it.
We only list something once it is real and reachable. If it is an idea we are still arguing about, it is not here yet.
What is running
An agent-readable website
LiveThis site answers to software as well as it answers to people.
Most company websites are written for a person with a browser. An agent asked to find a studio, read its work and judge whether it fits has to scrape HTML meant for human eyes, and usually gets it wrong. We rebuilt this site so it does not have to.
Every page here answers in Markdown as well as HTML: send an Accept header, or put .md on the end of any path. The case studies are a read-only JSON API with a published OpenAPI schema. The same data is an MCP server, so an assistant can call it directly rather than parsing a page. Nothing needs a key, and the discovery files that tell an agent all of this exists sit where the specs say they should.
It is also the honest demo of how we work. Everything above is running on the page you are reading, and you can check any of it in a terminal in about ten seconds.
Working with us on one
If something here is close to a problem you have, the fastest route is a call: book 15 minutes, or write to remotevansh@gmail.com. For the client work instead, the case studies are on the home page.