Opengeni is getting ready for ProductHunt!

Hey Product Hunt! I'm Davlet from the Opengeni team.

For the past two years we've been running AI agents against real production cloud infrastructure at Cloudgeni. The model was never the hard part. Everything around it was: runs that die when a worker restarts, code that needs somewhere safe to execute, OAuth tokens for every user, tools to wire up, a human sign-off before anything risky, and a clear record of what the agent did and what it cost.

We kept rebuilding that layer, so we turned it into Opengeni.

What you get out of the box:

• Sessions that survive errors and keep working for hours or days

• Sandboxes where agents do the work (Docker, Modal, Kubernetes or your own machine)

• 30+ one-click integrations, plus any MCP server or OpenAPI spec

• Human approvals on the tools you choose

• Memory that agents build up and reuse across sessions

• Insights, tracing and an audit trail for every step, token and dollar

• Any model: OpenAI, Azure, OpenRouter, your ChatGPT, Codex or SuperGrok subscription, or any OpenAI-compatible endpoint

Two ways to run it:

• Self-host: free and open source under Apache 2.0, with Helm and Terraform for AWS, Azure and GCP

• Opengeni cloud: sign in and go. You pay model cost plus 5%, with no seat or platform fees

Work with agents in our app, or put the same sessions inside your own product with our SDK and React components.

Launch offer: the first 100 users get $100 in Opengeni cloud credit. Details come with the launch day.

We'd love your feedback, especially on what you'd build with it and what's missing. We're here all day to answer questions.