Langfuse vs OpenLLMetry
OpenLLMetry leads on trust: 85.9/100 (Grade A) against 79.4/100 (Grade B), a 6.5-point gap. Langfuse leads on maintenance and adoption, and rests on broader evidence; OpenLLMetry leads on supply-chain integrity and provenance. Note: OpenLLMetry's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
Choose Langfuse if maintenance and adoption matter most.
- +3.5Maintenance
- +3.2Adoption: 9.8M weekly downloads against 449.4k
- +0.7Transparency: OSSF Scorecard 7.2 against 6.3
- A vs BEvidence coverage: 4 of 5 independent signal types, against 3
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
Choose OpenLLMetry if supply-chain integrity and provenance matter most.
- +7.2Identity / Provenance: package provenance attested, against none
- +5.6Safety / Integrity: package provenance attested, against none
Where they differ
An independent, evidence-based trust comparison of Langfuse and OpenLLMetry, 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 | OpenLLMetrytraceloop/openllmetry |
|---|---|---|
| HVTrust score | 79.4 | 85.9 |
| Evidence grade | B | A |
| Coverage grade | A | B |
| Overall rank | #187 | #85 |
| Rank in Observability & Evaluation | #6 | #4 |
| GitHub stars | 36.9k | 7.5k |
| Last updated | 1d ago | 1d ago |
| Build provenance | No | Yes |
| OSSF Scorecard | 7.2 / 10 | 6.3 / 10 |
| License | NOASSERTION | Apache-2.0 |
| Downloads | 9.8M/wk | 449k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 13.9 | 19.5 |
| Identity & provenance / 18 | 10.8 | 18.0 |
| Transparency / 17 | 14.6 | 13.9 |
| Maintenance / 20 | 19.9 | 16.4 |
| Adoption / 20 | 20.0 | 16.8 |
| 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 | Match |
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 →