LLM observability & evals

Langfuse

Rankedopen-source

77.9/100 · #15 overall

Trace, evaluate, and improve AI agents with one open platform. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.

Visit Langfuse ↗ add to compare slip

Stat lines

Product quality25/ 25

verified

Traction15.4/ 25

verified

Value15/ 15

verified

Reliability / freshness10/ 10

verified

Bio

Pricing type	open-source
Website	https://langfuse.com
GitHub	langfuse/langfuse · 35,914 ★
HN stories (12 mo)	10
Added	2026-10-16

Division ranks

LLM observability & evals#1 of 4

Score breakdown

Component	Points	Evidence
Traction verified	15.4/25	10 HN stories linking to it (12 mo), pctl 77% in all tools; 35,914 GitHub stars, pctl 46% in all open-source tools; blended 50/50
Momentum provisional	7.5/15	Needs 30 days of score history; neutral midpoint
Product quality verified	25/25	7/7 checklist items found on live site (checked )
Value verified	15/15	Open-source repo langfuse/langfuse
Reliability / freshness verified	10/10	Homepage check 2026-10-16: HTTP 200
Editor / community rating provisional	5/10	No ratings yet; neutral 5/10

Product-quality checklist

✓Docs/helphttps://langfuse.com/docs

✓Pricing pagehttps://langfuse.com/pricing

✓API/developershttps://langfuse.com/docs/api-and-data-platform/overview

✓Privacy policyhttps://langfuse.com/privacy

✓Termshttps://langfuse.com/terms

✓Changelog/bloghttps://langfuse.com/changelog

✓Security/compliancehttps://langfuse.com/security/gdpr

Data checked 2026-10-16. Think this is wrong? Dispute a score.