DeepYardDeepYard

Langfuse vs promptfoo

Side-by-side comparison with live GitHub signals. Last updated May 26, 2026.

L

Langfuse

Open-source LLM engineering platform — traces, evals, prompt management — 23K+ stars

OSSfreemium
28.0Ktoday157
p

promptfoo

Test and evaluate LLM prompts and agents — 11K+ stars

OSSFree
21.6Ktoday286
MetricLangfusepromptfoo
GitHub Stars28.0K21.6K
Contributors157286
Last CommitMay 26, 2026May 26, 2026
Open Issues641312
Licenseopen-sourceopen-source
Pricingfreemiumopen-source
Free TierYesYes
Categorydev-toolsdev-tools
TrendingNoNo

Shared Tags

evaluationopen-source

Only in Langfuse

observabilitytracingprompt-managementanalytics

Only in promptfoo

testingred-teamingsecurityci-cd

About Langfuse

Langfuse is an open-source LLM engineering platform providing observability, analytics, and prompt management. Features distributed tracing for complex agent chains, evaluation scoring, prompt versioning and A/B testing, dataset management, and cost tracking. Integrates with LangChain, LlamaIndex, OpenAI SDK, and any LLM framework via OpenTelemetry.

View full listing

About promptfoo

promptfoo is an open-source tool for testing, evaluating, and red-teaming LLM applications. Run automated evaluations across multiple models and prompts, compare outputs side-by-side, detect regressions, and test for security vulnerabilities. Supports custom assertions, CI/CD integration, and model-graded evaluations.

View full listing