Tracing AI Agent Execution Paths and Costs with NVIDIA NeMo Relay and Phoenix
NVIDIA Developer · youtube · 2026-10-01
NVIDIA Developer published a tutorial on capturing a Hermes Agent's full execution path with NeMo Relay, from the initial request and file-reading tool calls to the final answer.
- The trace covers which tools the agent used, what data it accessed, tokens consumed, and the cost of the run
- The video opens the trace in Phoenix to review sessions, model and tool activity, and redacted data
- NeMo Relay records activity locally while a sanitizer strips PII before the trace leaves the machine
- Companion resources include GitHub examples (NeMo-Relay, nemoclaw-community) and a tech blog, useful for debugging, evaluation, and agent reliability work
Related event: NVIDIA and Nous Research Detail NeMo Relay for Agent Tracing(2 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16