Autonomous coding agents in a cloud devbox you can watch, steer, and verify, running Claude Code, Codex, or OpenCode on your own subscription.
Replies
Best
Maker
📌
Hey Product Hunt! Solo founder here 👋
Since Claude Code and Codex came out I've been obsessed. It's hard not to be when you're getting a 20x discount on inference. But the day-to-day drove me a little crazy: walking around with my laptop lid open on a phone hotspot, babysitting command approvals so nothing nukes my root directory, and running out of RAM with multiple agents spinning up dev servers at once.
The existing cloud agents didn't do it for me. Slow VM setup made them feel like they were meant for fire and forget only, I missed plan mode, and the whole VM was a black box. The only way to verify anything was checking out the branch and testing it myself.
So I built Aether:
Agents start on any repo in <5 seconds, deps installed, dev servers running, and responses come back in under a second, so it feels local
Every workspace is a full Devbox: terminal, editor, port previews, and Docker support. Watch it work, steer, or take over
My personal favorite feature: turn on PR review + PR-comment responses and you get a loop where a writer agent and a reviewer agent go back and forth until the reviewer is satisfied. Real example on our public demo repo: https://github.com/Aether-Runtim... (bugs seeded on purpose, disclosed in the readme)
PRs with visual changes ship with a Playwright video and screenshots
Start tasks from Linear, Slack, Sentry alerts (with full Sentry MCP access), the API, or scheduled automations
Your inference runs on your own subscription, so you keep the subsidy. Aether only charges for compute. Free tier, paid from $30/mo.
Fun fact: the launch video was made entirely by Claude Fable writing Python scripts.
Would really appreciate any feedback!
Report
the fact that you can actually watch the agent work and step in when it goes off track is such a thoughtful design choice, makes it feel way more like collaborating than just hitting run
Report
finally got a chance to test this out and being able to watch the agent work in real time and step in when it goes sideways is genuinely useful, the verification step catches stuff i'd normally have to debug later.
Replies
the fact that you can actually watch the agent work and step in when it goes off track is such a thoughtful design choice, makes it feel way more like collaborating than just hitting run
finally got a chance to test this out and being able to watch the agent work in real time and step in when it goes sideways is genuinely useful, the verification step catches stuff i'd normally have to debug later.