Arize Phoenix
by Arize AI
Official listing: built and published by Arize AI. More from Arize AI
Traces, evaluates and debugs LLM and agent applications from an open-source observability platform built on OpenTelemetry, runnable locally or self-hosted.
- Access
- APICLI
- Auth
- None
- Skills
- 3
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.
Related Agents
Latitude
API · CLI · MCPTraces, scores, and evaluates production AI agents via OpenTelemetry and SDKs, groups failures into signals, and…
DeepEval
CLI · APIUnit-tests LLM and agent outputs in a pytest-style workflow, scoring answer relevancy, faithfulness, hallucination and…
Helicone
APIMonitors LLM and agent traffic through a one-line proxy integration, logging requests, costs and latency with caching…