Winsen Labs · An AI lab

We reimagine and rebuild the systems teams work with.

Winsen Labs is a small AI lab that ships. We build the tools we wished existed, we use them ourselves every day, and we help companies put AI to work. Properly. When you work with us, you get the team that builds this stuff for a living.

Who we are

A small lab that builds what it believes in, then uses it every day.

We started Winsen Labs because most of the tools we used at work felt older than the people using them. So we built a place where the people imagining better systems and the people shipping them are the same people. Where a hard question is allowed to take a year if it needs one. We're small, we move slowly when slow is the right speed, and we answer the email ourselves.

How we help

We help a handful of teams each year make the leap to AI. Then we hand them the keys.

Each year we take on a few engagements with teams whose problems genuinely excite us. The kind where research is part of the answer, not an afterthought. We sit alongside your team, we ship something real, and we leave you owning every piece of it. And we're not advisers reading about AI from the outside: the brains, the agents, and the runtime we deploy for you are the same ones we build and run ourselves. No pitch deck. No black box. Just the work, done properly.

01

Build an internal company brain to help you integrate AI into your actual processes.

A private brain over your mail, calendar, tasks, docs, and data. Searchable, ask-able, and quietly compounding the longer you use it. The first step to weaving AI into how you actually work. Yours when we're done.

02

Put agents into production. Keep them alive.

From a sketch on a whiteboard to an agent that lives in production and earns its keep. We design it, wire it into your stack, put guardrails where they matter, and stay until your team has every answer.

03

Solve the hard graph problem.

Customers and products. Supply chains. Internal knowledge graphs. If your hardest problem looks like a network, we've spent years on exactly that shape of problem, and we ship something you can actually run.

04

Run your agent runtime for you.

Don't want to run the runtime, the monitoring, and the model layer yourself? We host it on Platos, manage observability and routing, keep models and tools current, and let your team focus on what the agents do, not how they stay alive.

What we do

We build the tools we wished existed. Then we ship them.

A workspace with a company brain and AI employees that do real work. An open-source runtime that keeps agents alive in production. A project hub built for shipping software with AI coding agents. We use all three ourselves, every day, and we keep everything open where we can. This is the body of work behind every engagement.

Product · Open source02

Platos

The open-source agent runtime.

Build, ship, and operate AI agents on infrastructure you own. Model-agnostic, monitored by default, self-hostable in one docker compose up. No seat license. No lock-in. No drama.

Product · Open source03

Rocketman

Idea to production, managed in the repo.

A project hub that lives in your codebase as one beautiful offline file, plus a Claude skill stack that walks an idea from spec to shipped. Project management, rebuilt for the age of AI coding agents.

Winsen Academy · Coming up

We also teach this.

Winsen Academy is our school for the AI-native way of working. Not prompt tips. A new way to think, build, and get things done with AI at your side, taught by the people doing the research, shipping the products, and sitting inside real companies. The first courses are in the works.