LLM Observability

from hexr import hexr_agent, hexr_llm

@hexr_agent(name="my-agent", tenant="acme-corp")
def main():
    # This call generates a full OpenTelemetry span automatically
    response = hexr_llm(
        provider="openai",
        model="gpt-4o",
        prompt="Summarize the latest AI research",
    )

Agent: content-crew (tenant: acme-corp)
├── researcher
│   ├── gpt-4o:      $2.34 (1,247 calls)
│   └── claude-3.5:  $1.12 (423 calls)
├── writer
│   ├── gpt-4o:      $3.67 (2,100 calls)
│   └── gpt-4o-mini: $0.23 (890 calls)
└── editor
    └── gpt-4o:      $0.89 (312 calls)

Total: $8.25 / 4,972 calls

providers = [
    ("openai", "gpt-4o"),
    ("anthropic", "claude-sonnet-4-20250514"),
    ("google", "gemini-1.5-pro"),
]

for provider, model in providers:
    response = hexr_llm(
        provider=provider,
        model=model,
        prompt="Explain quantum computing in one paragraph",
    )
    # Each call traced separately — compare cost/latency in Grafana