
Arize trace
SkillExports and inspects Arize traces, spans and sessions to debug what an LLM app is doing
- Open source
- 41.3K GitHub stars
- AI models and LLM tooling


Exports and inspects Arize traces, spans and sessions to debug what an LLM app is doing

Lets an agent create, list, update and delete Arize AI LLM provider integrations

Guides an agent to add Phoenix LLM tracing with OpenInference span conventions

Lets your agent manage Arize annotation configs, review queues and span labels

Creates Arize LLM-as-judge evaluators and runs them on traces or experiment results

Improves LLM prompts using trace data, eval scores and experiments in Arize

Builds clickable Arize UI links for traces, spans, sessions, datasets and evaluators

Guides agents through debugging LLM apps with Phoenix traces, datasets and experiments

Runs a model over an Arize dataset, saves the results as an experiment and compares runs

Creates, exports and appends to Arize evaluation datasets using the ax command line

Guides an agent through Azure observability troubleshooting, from telemetry and alerts

Sends OpenTelemetry traces, metrics and logs from Python apps to Application Insights
The closest alternatives to Arize instrumentation are Arize trace, Arize AI provider integration, Phoenix tracing, Arize annotation and Arize evaluator.
Yes. Arize trace, Arize AI provider integration, Phoenix tracing have a free or open-source option.