Registry › Compare › Langfuse vs Weights & Biases Weave

Langfuse vs Weights & Biases Weave

Weights & Biases Weave leads on trust: 84.8/100 (Grade A) against 78.4/100 (Grade B), a 6.4-point gap. Langfuse leads on adoption and transparency; Weights & Biases Weave leads on provenance and supply-chain integrity.

B Langfuse 78.4

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

langfuse/langfuse · #167 overall · #6 Observability & Evaluation · coverage A (4/5)

Choose Langfuse if adoption and transparency matter most.

+5.5Adoption: 5.6M weekly downloads against 184.4k
+0.6Transparency: OSSF Scorecard 6.9 against 6.2
+0.6Maintenance

A Weights & Biases Weave 84.8

Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.

wandb/weave · #88 overall · #3 Observability & Evaluation · coverage A (4/5)

Choose Weights & Biases Weave if provenance and supply-chain integrity matter most.

+7.2Identity / Provenance: package provenance attested, against none
+6.4Safety / Integrity: package provenance attested, against none

Where they differ

13.2

Safety / IntegrityWeights & Biases Weave +6.4

19.6

10.8

Identity / ProvenanceWeights & Biases Weave +7.2

18.0

14.4

TransparencyLangfuse +0.6

13.8

19.9

MaintenanceLangfuse +0.6

19.3

19.9

AdoptionLangfuse +5.5

14.4

+0.2

Runtime calibrationLangfuse +0.5

-0.3

Full evidence table

An independent, evidence-based trust comparison of Langfuse and Weights & Biases Weave, 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	Langfuselangfuse/langfuse	Weights & Biases Weavewandb/weave
HVTrust score	78.4	84.8
Evidence grade	B	A
Coverage grade	A	A
Overall rank	#167	#88
Rank in Observability & Evaluation	#6	#3
GitHub stars	35.2k	1.1k
Last updated	1d ago	1d ago
Build provenance	No	Yes
OSSF Scorecard	6.9 / 10	6.2 / 10
License	NOASSERTION	Apache-2.0
Downloads	5.6M/wk	184k/wk
Trust dimensions (points earned)
Safety / integrity / 25	13.2	19.6
Identity & provenance / 18	10.8	18.0
Transparency / 17	14.4	13.8
Maintenance / 20	19.9	19.3
Adoption / 20	19.9	14.4
Runtime capability surface (full matrix)
MCP server	Implemented	Implemented
External providers	2 — Anthropic, OpenAI	9 — Amazon Bedrock, Anthropic, Cohere, …
Requires API keys	Yes	No
Plugin surface	plugins	—
Provenance drift	Unknown	Partial

Open in the live compare tool → Langfuse profile Weights & Biases Weave 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 →