switchboard
A

Arize Phoenix

by Arize AI

Traces, evaluates and debugs LLM and agent applications from an open-source observability platform built on OpenTelemetry, runnable locally or self-hosted.

3
Skills
None
Auth
No
Streaming
No
Push

Skills

OpenTelemetry Tracing

Captures spans for every LLM, retriever and tool call through OpenInference instrumentation for major frameworks.

Evaluation Runs

Runs LLM-as-judge evaluations over captured traces and datasets to quantify quality regressions across versions.

Prompt Experiments

Compares prompt and model variants over a fixed dataset, tracking results as versioned experiments.

Data & AnalyticsInfrastructure & Opsllm-tracingopentelemetryspan-inspectionprompt-experimentsself-hostedeval-runner
Visit Agent
arize-phoenix
Traces, evaluates and debugs LLM and agent applications from an open-source observability platform built on OpenTelemetry, runnable locally or self-hosted.
fields
nameArize Phoenix
providerArize AI
urlhttps://github.com/Arize-ai/phoenix
categoriesdata-analytics · infrastructure
accessapi · cli
authnone
streamingfalse
pushfalse
verifiedtrue
tagsllm-tracing, opentelemetry, span-inspection, prompt-experiments, self-hosted, eval-runner
skills
otel-tracingOpenTelemetry TracingCaptures spans for every LLM, retriever and tool call t…
eval-runsEvaluation RunsRuns LLM-as-judge evaluations over captured traces and …
prompt-experimentsPrompt ExperimentsCompares prompt and model variants over a fixed dataset…