Registry › Compare › Evidently vs Langfuse

Evidently vs Langfuse

Both are Grade B and 0.1 points apart, so choose on what you weigh most. Evidently leads on provenance and supply-chain integrity; Langfuse leads on maintenance and adoption.

B Evidently 78.4

Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.

evidentlyai/evidently · #167 overall · #8 Observability & Evaluation · coverage A (4/5)

Choose Evidently if provenance and supply-chain integrity matter most.

+7.2Identity / Provenance: package provenance attested, against none
+3.0Safety / Integrity: package provenance attested, against none

B Langfuse 78.5

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

langfuse/langfuse · #165 overall · #7 Observability & Evaluation · coverage A (4/5)

Choose Langfuse if maintenance and adoption matter most.

+6.6Maintenance: last push today, against 15d ago
+3.5Adoption: 5.5M weekly downloads against 199.6k
+3.0Transparency: OSSF Scorecard 6.9 against 3.4

Where they differ

16.2

Safety / IntegrityEvidently +3.0

13.2

18.0

Identity / ProvenanceEvidently +7.2

10.8

11.4

TransparencyLangfuse +3.0

14.4

13.4

MaintenanceLangfuse +6.6

20.0

16.4

AdoptionLangfuse +3.5

19.9

+3.0

Runtime calibrationEvidently +2.8

+0.2

Full evidence table

An independent, evidence-based trust comparison of Evidently 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	Evidentlyevidentlyai/evidently	Langfuselangfuse/langfuse
HVTrust score	78.4	78.5
Evidence grade	B	B
Coverage grade	A	A
Overall rank	#167	#165
Rank in Observability & Evaluation	#8	#7
GitHub stars	7.9k	35.1k
Last updated	15d ago	today
Build provenance	Yes	No
OSSF Scorecard	3.4 / 10	6.9 / 10
License	Apache-2.0	NOASSERTION
Downloads	200k/wk	5.5M/wk
Trust dimensions (points earned)
Safety / integrity / 25	16.2	13.2
Identity & provenance / 18	18.0	10.8
Transparency / 17	11.4	14.4
Maintenance / 20	13.4	20.0
Adoption / 20	16.4	19.9
Runtime capability surface (full matrix)
MCP server	—	Implemented
External providers	3 — Multi-provider (LiteLLM), OpenAI, Postgres	2 — Anthropic, OpenAI
Requires API keys	No	Yes
Plugin surface	—	plugins
Provenance drift	Match	Unknown

Open in the live compare tool → Evidently 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 v4.3 →