Heron is a passive network analyzer that reconstructs what your AI agents are actually doing. Zero SDKs. Zero proxy. Hook eBPF to see TLS-encrypted LLM calls and identify which agent process made them.
Launch Team
Render Sandboxes: a computer for every agentRun untrusted code safely. Idle sandboxes cost nothing
Promoted
eBPF for agent observability is such a smart call. Going passive means I don't have to wrap or instrument anything, which is honestly the part that always scares me about adding monitoring to a live product.
@yibo_wang3 Yes — this is basically the Heron thesis. Agent observability shouldn’t require every team to rewrite their stack or trust framework-level logs. A passive eBPF layer can observe real behavior from below: outbound calls, process activity, file access, tool/API patterns. That gives teams a safer way to add governance and debugging to live agent systems without putting instrumentation in the critical path.
eBPF for agent observability is such a smart call. Going passive means I don't have to wrap or instrument anything, which is honestly the part that always scares me about adding monitoring to a live product.