Show HN: AgentBouncr – Governance layer for AI agents
github.com
github.com
One thing I'd think about: how does this map to the documentation requirement? Under Annex IV, you need to document exactly what oversight mechanisms exist, how they work, and under what conditions they activate. The governance layer generates the evidence, but someone still needs to turn it into the structured documentation format that regulators expect.
This is the gap I see across most of the compliance tooling, runtime enforcement tools (like this) and documentation tools (Holistic AI, Annexa, ComplyAct) solve different halves of the problem. The teams that will have the smoothest conformity assessments are the ones connecting both.
I've been running ~2,400 multi-agent dispatches and came at this from the opposite direction: I started with staging gates (propose → human review → execute) as the runtime layer, then realized I also needed a forensic layer for when things slip through or when I need to understand patterns over time.
Curious about a few things:
- How granular are the JSON policies in practice? I found that "agent X can use tool Y" breaks down fast when agents chain tools in unexpected ways. The sequence matters more than individual permissions. - The hash-chained audit trail — how do you handle schema evolution? After a few months of production, what you want to log changes significantly. Hash chains make adding fields tricky without breaking the chain. - What happens when an agent crashes mid-action? With the hash chain, do you risk a corrupted tail entry that invalidates subsequent verification?
The runtime vs. after-the-fact distinction is important. Ideally you want both — prevent what you can, reconstruct what you couldn't prevent. Nice to see someone tackling the prevention side seriously.