~ / directory / langfuse
LA
Generative · AI Development Tools · reviewed 2026-04

Langfuse

Open-source LLM observability — traces, evals, prompt management.

Visit langfuse.com
01

What it does

An open-source LLM observability platform providing traces, evaluations, and prompt management. Captures every LLM interaction — prompts, completions, latency, costs, and scores — creating a complete audit trail for AI systems. Cited by CB Insights as a leading AI agent observability tool in the emerging Trust & Performance layer of the agent tech stack. Critical for detecting ASI06 (Memory & Context Poisoning) and ASI08 (Cascading Failures) in agentic deployments.

02

Security relevance

Observability is the foundation of AI security monitoring. Without traces, you can't detect prompt injection attempts, data leakage, or anomalous model behaviour. Langfuse provides the audit trail that security teams need to investigate incidents and demonstrate compliance.

03

When to use it

Deploy when you need observability and audit trails for LLM applications. SDK integration is straightforward — add tracing calls to your application code. Self-hosted or cloud options. Essential infrastructure for any AI security monitoring programme.

04

OWASP coverage

Risks addressed — mapped to both OWASP Top 10 standards. 0 in LLM, 2 in Agentic.

LLM Top 10 · 2025 · 0/10 covered
01
02
03
04
05
06
07
08
09
10
Agentic Top 10 · 2026 · 2/10 covered
01
02
03
04
05
06
07
08
09
10
05

The raw record

What Yuntona stores. Single source of truth — fork it on GitHub.

name: Langfuse
slug: langfuse
type: Generative
category: AI Development Tools
url: https://langfuse.com

reviewed:   2026-04
added:      2026-04
updated:    2026-04

risks:
  llm:  []
  asi:  [ASI06, ASI08]

complexity:    Guided Setup
pricing:       —
audience:      Builder
lifecycle:     [monitor]

tags: [Observability, Open Source, Tracing]