
Adds Arize AX tracing to an LLM app in two phases: read-only analysis, then implementation
- Open source
- 41.3K GitHub stars
- AI models and LLM tooling


Adds Arize AX tracing to an LLM app in two phases: read-only analysis, then implementation

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

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

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

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

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

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

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

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

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

Sends OpenTelemetry traces, metrics and logs from Python apps to Application Insights

Guides building, running and validating LLM evaluators with the Phoenix framework
The closest alternatives to Arize trace are Arize instrumentation, Arize link, Arize dataset, Phoenix tracing and Phoenix CLI.
Yes. Arize instrumentation, Arize link, Arize dataset have a free or open-source option.