langfuse-cli

Query Langfuse traces, sessions, observations, scores, metrics, and datasets via CLI.

Updated Dec 15, 2025
One-click install
npx skills add https://github.com/tavva/ben-claude-plugins --skill langfuse-cli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: langfuse-cli
Source: https://github.com/tavva/ben-claude-plugins/tree/main/plugins/langfuse/skills/langfuse-cli
Command: npx skills add https://github.com/tavva/ben-claude-plugins --skill langfuse-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Langfuse CLI provides a unified interface to query traces, sessions, observations, scores, metrics, and datasets from Langfuse observability platform, enabling rapid investigation and reporting.

Core Features & Use Cases

  • Query traces, sessions, observations, scores, metrics, and datasets with flexible filters and exports for fast debugging and performance analysis.
  • Manage prompts and datasets with versioning, labeling, and structured item handling to support evaluation and experimentation at scale.
  • Use cases include diagnosing API latency, token usage, model costs, and trace provenance across environments, plus generating reports from CLI data.

Quick Start

Install the Langfuse CLI and run lf commands to explore traces, sessions, observations, prompts, datasets, and metrics.

Frequently Asked Questions about langfuse-cli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query Langfuse traces and metrics from the command line?

Query Langfuse traces and metrics from the command line using the Langfuse CLI. It provides a unified interface to run lf commands for exploring traces and datasets with comprehensive filtering options.

Can I diagnose API latency and model costs using Langfuse observability data?

Diagnose API latency and model costs using Langfuse observability data by querying metrics and cost analyses. The CLI enables rapid investigation of token usage and trace provenance across production environments.

What is the best way to manage prompts and datasets for LLM evaluation at scale?

Manage prompts and datasets for LLM evaluation at scale using the Langfuse CLI. It supports versioning, labeling, and structured item handling to facilitate experimentation and evaluation workflows.

Does the Langfuse CLI support exporting observations and scores for reporting?

The Langfuse CLI supports exporting observations and scores for reporting. It offers flexible export options alongside robust handling of pagination and formatting to assist in performance analysis and investigation.

How do I filter Langfuse sessions and observations across production environments?

Filter Langfuse sessions and observations across production environments by applying comprehensive filters within the CLI commands. This enables targeted investigation and performance analysis across deployed applications.