Langfuse vs Promptfoo
Promptfoo leads on trust: 92.6/100 (Grade A) against 79.4/100 (Grade B), a 13.2-point gap. Langfuse leads on adoption; Promptfoo leads on supply-chain integrity and provenance.
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
Choose Langfuse if adoption matters most.
- +1.2Adoption: 9.8M weekly downloads against 1.3M
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
Choose Promptfoo if supply-chain integrity and provenance matter most.
- +8.0Safety / Integrity: 100% of recent commits signed, against 97%
- +7.2Identity / Provenance: package provenance attested, against none
Where they differ
1 dimension identical: Maintenance 19.9 · Full evidence table
An independent, evidence-based trust comparison of Langfuse and Promptfoo, 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 | Promptfoopromptfoo/promptfoo |
|---|---|---|
| HVTrust score | 79.4 | 92.6 |
| Evidence grade | B | A |
| Coverage grade | A | A |
| Overall rank | #187 | #8 |
| Rank in Observability & Evaluation | #6 | #1 |
| GitHub stars | 36.9k | 26.8k |
| Last updated | 1d ago | 1d ago |
| Build provenance | No | Yes |
| OSSF Scorecard | 7.2 / 10 | 7.5 / 10 |
| License | NOASSERTION | MIT |
| Downloads | 9.8M/wk | 1.3M/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 13.9 | 21.9 |
| Identity & provenance / 18 | 10.8 | 18.0 |
| Transparency / 17 | 14.6 | 14.9 |
| Maintenance / 20 | 19.9 | 19.9 |
| Adoption / 20 | 20.0 | 18.8 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 2 — Anthropic, OpenAI | 3 — Amazon Bedrock, Anthropic, OpenAI |
| Requires API keys | Yes | Yes |
| Plugin surface | plugins | 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 →