Kepler is a desktop app for the people who keep systems alive: SREs, platform engineers, on-call operators. It looks like a chat window. It behaves like a careful colleague with a terminal, a browser, an editor, and a long memory of your infrastructure. Ask it what is wrong with a live system and it runs read-only commands, reads the dashboards you already have open, recalls what happened last time, and comes back with a diagnosis and a suggested fix. By default it suggests. You decide what runs.
Everything Kepler packs
Ask it what is going on
It runs the commands, reads the logs and opens the dashboards, then shows you exactly what it ran before it tells you what it thinks.
It remembers
Your services, how they connect, what broke last month and how you fixed it. Every session makes the next one shorter.
It keeps watch
Point it at a deploy, a certificate or a pod count. When something changes it looks into it and tells you what it found, at your desk or on your phone.
It asks before it acts
Kepler suggests, you run the command. Give it more room per conversation if you want. Delete, scale and restart stay off the table, always.
Open a war room
Put several agents on one incident, each working its own angle, all reporting back to you in one place.
Stays on your machine
Your history, your memory and your credentials never leave your laptop. Use our hosted models or bring your own keys.
I have spent most of my working life keeping other people's systems alive. Coding agents got a perfect world model for free. The rest of us got dashboards at 3am. Kepler is my attempt at the other half: an agent that learns your infrastructure the way a good colleague does, and asks before it touches anything.
Fifty operators used the closed beta and shaped what it is today.