Phoenix (Arize AI)

Open-source LLM tracing + evaluation. OpenInference standard for traces; runs locally with one pip install. The OSS-first pick for teams that want LangSmith-shaped functionality without vendor lock-in.

By Eruo Fredoline·Last verified Oct 7, 2026·7,000 GitHub stars

Overview

Stack & relationships

How Phoenix (Arize AI) relates to other entries in the catalog — recommended pairings, alternatives, dependencies, and edges to avoid. Each edge carries a one-line operator note from our editorial team.

Phoenix (Arize AI) ↔ ecosystem

Recommended stack

Pairs with
OpenHands
Phoenix instruments OpenHands tool-calls + LLM spans via OpenInference. Drop-in for trace + eval workflows.
Pairs with
vLLM
vLLM exposes OpenInference-compatible spans; Phoenix consumes them directly. The default OSS observability pairing for self-hosted vLLM deployments.

Alternatives

Alternative to
LangSmith
Phoenix is OSS (Apache 2.0) with OpenInference traces; LangSmith is closed-source with deeper LangChain integration. Pick Phoenix for vendor-independence.
Alternative to
LangSmith
LangSmith for the LangChain-native path; Phoenix for the OSS/OpenInference path. Pick by ecosystem fit and self-hosting requirement.

Pros

OSS, Apache 2.0
OpenInference standard for traces
Strong span visualization

Cons

Eval coverage trails LangSmith
Cloud dashboard requires Arize account

Compatibility

Operating systems	macOS Linux Windows
GPU backends	n/a
License	Open source · free (OSS) + Arize cloud

Runtime health

Operator-grade signals on how actively Phoenix (Arize AI) is being maintained, how fresh its measurements are, and what failure classes operators have flagged. Every label below is anchored to a real date or count — we never infer maintainer activity we can't show.