Registry › Compare › Langfuse vs Weights & Biases Weave

Langfuse vs Weights & Biases Weave

Weights & Biases Weave leads on trust: 83.8/100 (Grade A) against 79.3/100 (Grade B), a 4.5-point gap. Langfuse leads on maintenance and adoption; Weights & Biases Weave leads on supply-chain integrity and provenance.

B Langfuse 79.3

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

langfuse/langfuse · #193 overall · #6 Observability & Evaluation · coverage A (4/5)

Choose Langfuse if maintenance and adoption matter most.

  • +5.7Adoption: 10.0M weekly downloads against 171.9k
  • +1.2Maintenance
  • +0.6Transparency: OSSF Scorecard 7.1 against 6.4

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

wandb/weave · #124 overall · #5 Observability & Evaluation · coverage A (4/5)

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

  • +7.2Identity / Provenance: package provenance attested, against none
  • +5.9Safety / Integrity: package provenance attested, against none

Where they differ

13.8
Safety / IntegrityWeights & Biases Weave +5.9
19.7
10.8
Identity / ProvenanceWeights & Biases Weave +7.2
18.0
14.5
TransparencyLangfuse +0.6
13.9
20.0
MaintenanceLangfuse +1.2
18.8
20.0
AdoptionLangfuse +5.7
14.3
+0.2
Runtime calibrationLangfuse +1.1
-0.9

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 79.3 83.8
Evidence grade B A
Coverage grade A A
Overall rank #193 #124
Rank in Observability & Evaluation #6 #5
GitHub stars 37.3k 1.1k
Last updated today today
Build provenance No Yes
OSSF Scorecard 7.1 / 10 6.4 / 10
License NOASSERTION Apache-2.0
Downloads 10.0M/wk 172k/wk
Trust dimensions (points earned)
Safety / integrity / 25 13.8 19.7
Identity & provenance / 18 10.8 18.0
Transparency / 17 14.5 13.9
Maintenance / 20 20.0 18.8
Adoption / 20 20.0 14.3
Runtime capability surface (full matrix)
MCP server Implemented Implemented
External providers 2 — Anthropic, OpenAI 8 — Amazon Bedrock, Anthropic, Cohere, …
Requires API keys Yes Yes
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 v4.4 →