At Hyperparam we run agents three ways: coding agents (Claude Code and Codex), a software factory that picks up issues and PRs on its own, and agents that run with no one watching. None of them tells you when something quietly goes wrong, because the models are so good at working around issues. In the first half of September those workers tried to run python3 on a container that doesn't have python3 1044 times, and none of us noticed, because the agents found workarounds and the pull requests looked fine in the morning. We only found out because someone asked.
That's why we built HypAware, launching here on Thursday. We built it because wanted better visibility into our own AI logs. It reads every session from every agent, finds what's broken, proposes the fix, and checks on the next pass whether it held.
What kinds of agents are you running, and how do you find out when one of them goes wrong?
Hi Product Hunt, I'm Kenny, founder of Hyperparam.
HypAware is for developers and small teams who run coding agents like Claude Code, Codex, and Cursor every day. The problem is that the more autonomous agents become, the less we know what they are doing.
We found that out on our own fleet. Our overnight agents ran python3 on a container that doesn't have it 1,044 times in two weeks, and nobody noticed, because the agents worked around it and the pull requests looked fine.
HypAware records every agent session into one history you can search, query, or just ask your agent about. It reads those sessions and proposes specific fixes, like a line in your CLAUDE.md or a new skill, with links to the sessions that show the problem. Later it checks whether the fix stuck.
Recording, search, and reports are free and open source, and stay on your machine. HypAware Cloud brings a team's sessions together in one hosted workspace.
I've found it very useful for developing our own AI systems. Check it out.