Choose a setup method
Start with one method for a call path. Combining SDK tracking with framework
OpenTelemetry on the same call can create duplicate interactions.
Recommended: Agnost AI skill
Recommended. Choose this path when you want your coding agent to inspect the
project, select a supported transport, make the smallest instrumentation change,
send a test event, and verify that it reached Agnost AI.
Manual setup: Agnost AI SDK
Manual setup: OpenTelemetry
OpenLit is the recommended path: it auto-instruments CrewAI plus the underlying LLM provider.Install
Setup
gen_ai.prompt.{n}.content, gen_ai.completion.{n}.content, gen_ai.usage.*) plus gen_ai.agent.name and gen_ai.operation.name on agent/task spans.
Caveats
- Call
openlit.init()before constructing anyCrew/Agentobjects. - CrewAI’s own anonymized telemetry (sent to CrewAI’s servers) is unrelated and can be left enabled.
Verify
Run oneCrew(...).kickoff() call, then open Events in Agnost AI. Confirm CrewAI and provider spans are present.
Troubleshooting
- Call
openlit.init()before constructing crews or agents. - Confirm
OTEL_EXPORTER_OTLP_HEADERScontainsX-Agnost-Org-ID=<your-org-id>. - Wrap runs with
using_attributesif you need explicit user/session grouping.
References
Next steps
- Conversations: review the complete CrewAI execution.
- Events: inspect crew, task, and model activity.
- Intents: organize production conversations by what users wanted.
