Langfuse vs LangSmith

Langfuse

LangSmith

Langfuse · 16 features

• Annotation Queues — Human reviewers rate traces. Unlimited on Pro+.
• Dashboards — Aggregate metrics, cost, quality across projects.
• Datasets — Curate test sets from production traces. Run experiments.
• EU Cloud Region — GDPR-compliant hosting in EU.
• Evaluations — LLM-as-judge, manual scores, custom model-graded evaluators.
• LLM Cost Tracking — Automatic cost calculation per provider/model.
• OpenTelemetry Native — OTel SDK → Langfuse endpoint works out of box.
• Playground — Test prompts + models + variables live.
• Prompt Management — Version, tag, label prompts. Reference from code by label.
• Public API — Full REST API for ingest, query, prompt management.
• Python @observe decorator — One-line decorator to trace any function.
• Self-Hosting — Docker Compose + k8s Helm chart.
• Sessions — Group related traces (conversations, agent runs).
• Tracing — Capture every LLM call, tool call, nested span with inputs/outputs/cost.
• Users Tracking — Segment traces by user ID, track per-user cost.
• Webhooks — Subscribe to trace completion events.

LangSmith · 14 features

• Alerts — Threshold alerts on latency, cost, eval metrics.
• Annotation Queues — Human-review workflows for trace quality rating.
• Custom Dashboards — Aggregate metrics dashboards per project/tag.
• Datasets — Collect examples → use as eval sets or training data.
• Evaluations — LLM-as-judge, embedding similarity, custom Python evaluators, offline batch eval…
• LangChain Integration — Auto-trace any LangChain/LangGraph run with env var.
• LangGraph Integration — First-class trace + eval for LangGraph agents.
• LLM Tracing — Automatic trace every LLM call + tool call + chain step.
• OpenTelemetry Export — Export traces as OTLP to Datadog/Honeycomb/etc.
• Playground — Test prompts + models inline before deploying.
• Prompt Canvas — Visual prompt editor with live test + eval.
• Prompt Hub — Public + private prompt library with versioning.
• Self-Hosted (Enterprise) — Docker + k8s deployment in your infra.
• Threads + Sessions — Group traces into conversational sessions.