Hey PH 👋 I'm Davlet, a builder who spent two years on the boring but crucial part of AI agents

Hey everyone! I'm Davlet.

I'm a builder at heart, the kind of person who'd rather be in a terminal than a slide deck. A while back I started building AI agents for cloud infrastructure: agents that work on real cloud accounts, real Terraform, real production systems.

The agents themselves turned out to be the easy part. The hard part was everything underneath: keeping them running for hours or days without falling over, recovering when a worker dies mid-task, asking a human before doing anything risky, and showing exactly what an agent did, step by step, down to the token and the dollar.

So we kept fixing the foundation.

That took about two years, and it became Opengeni: an open-source platform for running agents you can actually trust in production. It's model-agnostic and self-hostable, and it comes with sandboxes, approvals and full visibility out of the box.

If you want to use agents without spending two years building all that plumbing yourself, that's exactly why it exists.

We're launching on Product Hunt today! Would love for you to check it out, kick the tires, and tell me what breaks 🙂

👉 https://www.producthunt.com/products/opengeni?launch=opengeni

Happy to answer anything about agents, infra, or what two years of "just one more fix to the foundation" looks like.