Registry › Compare › Arize Phoenix vs Langfuse

Arize Phoenix vs Langfuse

Both are Grade B and 2.4 points apart, so choose on what you weigh most. Arize Phoenix leads on provenance; Langfuse leads on transparency and adoption.

B Arize Phoenix 76.9

AI Observability & Evaluation

Arize-AI/phoenix · #236 overall · #8 Observability & Evaluation · coverage A (4/5)

Choose Arize Phoenix if provenance matters most.

+7.2Identity / Provenance: package provenance attested, against none

B Langfuse 79.3

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

langfuse/langfuse · #192 overall · #6 Observability & Evaluation · coverage A (4/5)

Choose Langfuse if transparency and adoption matter most.

+6.0Transparency
+3.3Adoption: 9.8M weekly downloads against 137.1k
+1.3Safety / Integrity

Where they differ

12.5

Safety / IntegrityLangfuse +1.3

13.8

18.0

Identity / ProvenanceArize Phoenix +7.2

10.8

8.5

TransparencyLangfuse +6.0

14.5

16.7

AdoptionLangfuse +3.3

20.0

+1.2

Runtime calibrationArize Phoenix +1.0

+0.2

1 dimension identical: Maintenance 20.0 · Full evidence table

An independent, evidence-based trust comparison of Arize Phoenix and Langfuse, two Observability & Evaluation projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal	Arize PhoenixArize-AI/phoenix	Langfuselangfuse/langfuse
HVTrust score	76.9	79.3
Evidence grade	B	B
Coverage grade	A	A
Overall rank	#236	#192
Rank in Observability & Evaluation	#8	#6
GitHub stars	12.2k	37.1k
Last updated	today	today
Build provenance	Yes	No
OSSF Scorecard	—	7.1 / 10
License	NOASSERTION	NOASSERTION
Downloads	137k/wk	9.8M/wk
Trust dimensions (points earned)
Safety / integrity / 25	12.5	13.8
Identity & provenance / 18	18.0	10.8
Transparency / 17	8.5	14.5
Maintenance / 20	20.0	20.0
Adoption / 20	16.7	20.0
Runtime capability surface (full matrix)
MCP server	Implemented	Implemented
External providers	6 — Amazon Bedrock, Anthropic, E2B, …	2 — Anthropic, OpenAI
Requires API keys	No	Yes
Plugin surface	plugins	plugins
Provenance drift	Partial	Unknown

Open in the live compare tool → Arize Phoenix profile Langfuse profile More Observability & Evaluation →

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →