4/ How the design maps to the EU AI Act, NIST AI RMF, and US state laws — not legal advice, just showing the work was done with real requirements in view.

3/ The security model — and an honest list of what v0.1.0 explicitly does NOT do yet (no kill switch, no policy enforcement, no multi-tenant isolation). If you're evaluating self-hosting this, read…

2/ The data behind why this needs to exist: adoption outpacing control, incidents already happening, the identity governance gap, real regulatory pressure.

1/ Added four new docs to BF Agent Viewer's repo — trying to make the case (and the honesty) as transparent as the code will eventually be. #AgentViewer

1/n Building BF Agent Viewer — open source, self-hosted software that shows you what your AI agents are actually doing: which agent touched which tool, using whose credentials, when. No agent-count…

1/n Building BF Agent Viewer — open source, self-hosted software that shows you what your AI agents are actually doing: which agent touched which tool, using whose credentials, when. No agent-count…

4/ It's built for teams that don't have a dedicated security function — not a lighter version of enterprise IAM tooling, a different buyer entirely.