AI Potluck
Product / UX / Telemetry & observability

Phoenix

Arize AI

Open-source AI observability and evaluation toolkit by Arize AI. Provides tracing, embeddings analysis, experiment tracking, and LLM evaluation in a local-first workflow. Strong integrations with LlamaIndex and LangChain. Built by the team behind the Arize production ML monitoring platform. 9.8K GitHub stars.

arize-phoenix v17.2.0 (released 3 Jun 2026, GitHub); confirmed live June 2026. Open-source-positioned companion to the closed Arize AX platform.

Openness

2 high confidence
2.0
license
Elastic-License-2.0(ELv2, non-OSI: prohibits offering as a managed/hosted service to third parties)
source
public
commercial
Arize-AX-SaaS-is-separate-closed-product

The LICENSE file is ELv2 verbatim, which is not an OSI license, while Arize markets Phoenix as "the open source platform" (open_washed). Source-available and self-hostable, with Arize AX as a separate closed SaaS product. Score corrected from 3 to 2 on 2026-07-30. The software ladder has rungs at 1, 2, 4 and 5 and none at 3, so 3/source_available was not a pair any rule could produce; the ladder scores "you can read it and not run it freely" at 2.

Adoption

4 high confidence
4.0

arize-phoenix ~2.46M PyPI downloads/month; broad OTel-based framework integrations; ~10k GitHub stars corroborates only.

Capability

4 high confidence
4.0

Full-coverage observability/eval platform across all six feature-matrix dimensions; on par with MLflow/Langfuse anchors (C4).

Unchanged since 2026-07-30 (last edited, not re-checked)