# agentsite-static-version=f282bee9-4c5a-40e1-ac1d-ab2340bca842
# langfuse.com

> AI-optimized mirror of langfuse.com containing 98 pages totalling 92,352 words of clean markdown content, structured data, and semantic HTML. Original source: https://langfuse.com. Last updated: 2026-09-17T02:51:08.888Z.

Each page is available as HTML (with JSON-LD structured data) and Markdown (text-only, ideal for LLMs and RAG).

## Articles & Blog Posts

- [Glossary - Langfuse](/content/docs/glossary/index.html): A comprehensive glossary of key terms and concepts used in Langfuse documentation. (2,244 words)
- [Dashboard changes in Langfuse v4 - Langfuse](/content/faq/all/dashboard-changes-in-v4/index.html): How dashboards change in Langfuse v4 — what stays the same, what's different, and expected numerical differences compared to Langfuse v3. (1,925 words)
- [Langfuse vs. Arize AX and Arize Phoenix - Langfuse](/content/compare/arize-phoenix/index.html): Langfuse is the open-source alternative to Arize AX and Phoenix. September 2026 comparison of unit vs span+GB pricing, evals, and the Dynatrace acquisition. (2,698 words)
- [Langfuse v4: Faster at Scale - Langfuse](/content/changelog/2026-08-17-langfuse-v4/index.html): Query and evaluate every agent step directly, with initial table loads in milliseconds and at least 10x faster dashboards for large projects. (696 words)
- [SCIM and Org API - Langfuse](/content/docs/administration/scim-and-org-api/index.html): Langfuse is open and meant to be extended via custom workflows and integrations. You can use these endpoints to automate project and user management on your Langfuse organization. (436 words)
- [Langfuse raises $4M - Langfuse](/content/blog/announcing-our-seed-round/index.html): We're thrilled to announce that Langfuse, the open source observability and analytics solution for LLM applications, has raised a $4m seed round from Lightspeed Venture Partners, La Famiglia and Y Combinator. (1,616 words)
- [LLM Testing: Automated Tests for LLM Apps - Langfuse](/content/blog/2025-10-21-testing-llm-applications/index.html): Learn how to test LLM applications with automated evaluation, datasets, and experiment runners. A practical guide to LLM testing strategies. (1,188 words)
- [LLM Cost Management: Track and Control Spend - Langfuse](/content/resources/engineering/llm-cost-management/index.html): LLM cost management: track token spend accurately, attribute it to users and features, and control it with alerts. Pitfalls and how to solve them in Langfuse. (2,356 words)
- [users/slite-md.html](/content/users/slite-md.html) (1,296 words)
- [users/canva-md.html](/content/users/canva-md.html) (1,150 words)
- [Designing datasets - Langfuse](/content/academy/datasets/designing-great-datasets/index.html): A practical guide to designing Langfuse datasets with clear scope, realistic inputs, evaluable outputs, useful metadata, and interpretable experiment results. (1,919 words)
- [Observability in Multi-Step LLM Systems - Langfuse](/content/blog/2024-10-observability-in-multi-step-llm-systems/index.html): Optimize multi-step LLM systems with advanced observability, feedback, and testing strategies for better performance and reliability. (2,024 words)
- [Filter search bar - Langfuse](/content/docs/observability/features/filter-search-bar/index.html): Filter and search traces and observations by typing — fields, operators, wildcards, aliases, and full-text search in one query bar with autocomplete. (936 words)
- [Security FAQ - Langfuse](/content/security/security-faq/index.html): Answers to common questions about Langfuse's security practices. (2,154 words)
- [Scores API - Langfuse](/content/docs/api-and-data-platform/features/scores-api/index.html): Retrieve scores from Langfuse with the v3 endpoint featuring a typed value field, cursor-based pagination, and selective field retrieval. (1,005 words)
- [Docker Compose Deployment (Self-Hosted) - Langfuse](/content/self-hosting/deployment/docker-compose/index.html): Step-by-step guide to deploy and run Langfuse locally or on a VM using Docker Compose. The simplest way to self-host Langfuse with Docker. (828 words)
- [Compare experiments - Langfuse](/content/docs/evaluation/experiments/compare-experiments/index.html): Compare application versions against a baseline, inspect individual regressions, and review failures in Langfuse. (486 words)
- [Prompt Management Concepts - Langfuse](/content/docs/prompt-management/data-model/index.html): Core concepts of Langfuse Prompt Management including prompt types, versioning, labels, and configuration. (686 words)
- [Evaluate with Datasets - Langfuse](/content/docs/evaluation/get-started/offline/index.html): Run your first offline evaluation on a Langfuse dataset and compare prompt changes. (776 words)
- [Langfuse for Enterprise - Langfuse](/content/enterprise/index.html): FAQ and deployment options for Langfuse in an enterprise environment. (524 words)
- [PII masking patterns for LLM applications - Langfuse](/content/resources/engineering/pii-masking-llm-applications/index.html): Where to mask PII in an LLM application: client-side SDK masking, server-side ingestion masking, gateway-level filtering, and detection with evaluators. Patterns and trade-offs. (1,006 words)
- [users/hugging-face-md.html](/content/users/hugging-face-md.html) (1,306 words)
- [Langfuse November Update - Langfuse](/content/blog/2025-11-30-langfuse-november-update/index.html): Agent Tracing, Model Pricing Tiers in Cost Tracking, Score Analytics, Langfuse MCP Server & more (741 words)
- [How we use agents to review production infrastructure - Langfuse](/content/blog/2026-06-05-agentic-setup-for-operational-work/index.html): How repo-owned agent workflows help us review incidents, infra cost, security findings, and bugs in production. (788 words)
- [Troubleshooting & FAQ - Langfuse](/content/docs/observability/sdk/troubleshooting-and-faq/index.html): Resolve common Python and JS/TS SDK issues with side-by-side guidance. (316 words)
- [AI is eating the AI engineering loop - Langfuse](/content/blog/2026-06-09-ai-is-eating-ai-engineering/index.html): The full AI engineering loop can technically be automated now. But that doesn't mean it should. Here is what we think you should hand to agents, and what you should keep doing yourself. (1,178 words)
- [Langfuse Community - Langfuse](/content/community/index.html): Join the Langfuse Community to connect with developers, contribute to our open-source LLM observability platform, attend community sessions, and collaborate worldwide. (230 words)
- [n8n and Langfuse - Langfuse](/content/integrations/no-code/n8n/index.html): How to trace n8n workflows in Langfuse, giving you observability over the LLM steps you build in the fair-code workflow automation platform. (162 words)
- [Versions & Compatibility - Langfuse](/content/docs/compatibility/index.html): How Langfuse server, SDK, and API versions relate across Langfuse Cloud and self-hosted deployments, including the SDK ↔ server compatibility matrix. (406 words)
- [Ask AI in the Filter Search Bar - Langfuse](/content/changelog/2026-06-26-ask-ai-filter-search-bar/index.html): Describe the filters you want in plain language and the search bar drafts them as editable query pills. Opt-in on Langfuse Cloud, powered by AWS Bedrock with zero data retention. (514 words)
- [Enterprise License Key (self-hosted) - Langfuse](/content/self-hosting/license-key/index.html): Learn how to activate a license key for your self-hosted Langfuse deployment. (195 words)
- [Custom Base Path (self-hosted) - Langfuse](/content/self-hosting/configuration/custom-base-path/index.html): Follow this guide to deploy Langfuse on a custom base path, e.g. https://yourdomain.com/langfuse. (342 words)
- [LLM regression testing: fail CI before regressions ship - Langfuse](/content/resources/engineering/llm-regression-testing/index.html): Set up LLM regression testing that fails CI: golden datasets, experiment thresholds, RegressionError, and GitHub Actions via langfuse/experiment-action. (882 words)
- [How to manage different environments in Langfuse? - Langfuse](/content/faq/all/managing-different-environments/index.html): Learn how to separate production, staging, and development in Langfuse using built-in environments or separate projects, including how to sync prompts and configurations. (358 words)
- [Where do I find my Langfuse API keys? - Langfuse](/content/faq/all/where-are-langfuse-api-keys/index.html): Where to find or create Langfuse API keys: Project Settings shows your public and secret keys and lets you rotate them. (67 words)
- [Access Control (RBAC) - Langfuse](/content/docs/administration/rbac/index.html): Langfuse offers extensive RBAC capabilities to manage project sharing and permissions across different organizations and projects. (617 words)
- [docs/evaluation/evaluation-methods/annotation-queues-md.html](/content/docs/evaluation/evaluation-methods/annotation-queues-md.html) (532 words)
- [OpenTelemetry (OTEL) for LLM Observability - Langfuse](/content/integrations/native/opentelemetry/index.html): Connect Langfuse to OpenTelemetry (OTEL) and send OTLP traces from your application or collector to Langfuse. (546 words)
- [Managing Personal Data - Langfuse](/content/security/manage-personal-data/index.html): How to manage personal data processed with Langfuse. (68 words)
- [How to update traces, observations, and scores? - Langfuse](/content/faq/all/tracing-data-updates/index.html): Langfuse treats traces and observations as immutable. What that means in practice, and how to correct or enrich data after it has been ingested. (534 words)
- [Experiments via OpenTelemetry - Langfuse](/content/docs/evaluation/experiments/experiments-via-opentelemetry/index.html): Group OpenTelemetry traces as Langfuse experiments by attaching experiment and item attributes. (101 words)
- [Self-hosting Langfuse v2 - Langfuse](/content/self-hosting/v2/deployment-guide/index.html): Self-host Langfuse in your infrastructure using Docker. (8,327 words)
- [Manage evaluators with the stable API - Langfuse](/content/changelog/2026-08-27-stable-evaluator-api/index.html): Create, version, and manage evaluators and evaluation rules through stable, ID-based public APIs. (213 words)
- [Find your role at Langfuse - Langfuse](/content/role-finder/index.html): Answer a few quick questions and we'll point you to the Langfuse role that fits you best. (77 words)
- [guides/cookbook/error-analysis-llm-applications-md.html](/content/guides/cookbook/error-analysis-llm-applications-md.html) (2,561 words)
- [Integrate Portkey LLM Gateway with Langfuse - Langfuse](/content/integrations/gateways/portkey/index.html): Guide on using Portkey's AI gateway to access 250+ LLM models with Langfuse via the OpenAI SDK. (705 words)
- [LangChain Tracing & Callbacks — Open Source Observability for LangChain & LangGraph - Langfuse](/content/integrations/frameworks/langchain/index.html): Open source LangChain tracing and monitoring. Automatically capture traces of your LangChain callbacks, LLM calls, tools, and retrievers with Langfuse. Python and JS/TS. (1,868 words)
- [Langfuse JS/TS SDK - Langfuse](/content/guides/cookbook/js_langfuse_sdk/index.html): End-to-end example of how to use the Langfuse TypeScript SDK to trace LLM applications. (1,642 words)
- [Guide - Building an intent classification pipeline - Langfuse](/content/guides/cookbook/example_intent_classification_pipeline/index.html): Build an intent classification pipeline to understand how users are using your LLM application and how performance differs by intent. (1,961 words)
- [Audit Logs - Langfuse](/content/docs/administration/audit-logs/index.html): Comprehensive audit logging in Langfuse tracks all system activities with detailed state capture and user attribution for enterprise security and compliance requirements. (530 words)
- [GitHub Integration - Langfuse](/content/docs/prompt-management/features/github-integration/index.html): Integrate Langfuse prompts with GitHub using webhooks for version control, CI/CD workflows, and automated synchronization (1,060 words)
- [Variables - Langfuse](/content/docs/prompt-management/features/variables/index.html): Insert dynamic text into prompts using variables that are resolved at runtime. (449 words)
- [Instrumentation - Langfuse](/content/docs/observability/sdk/instrumentation/index.html): Use native integrations or custom instrumentation patterns in Python and JavaScript/TypeScript to capture rich traces. (500 words)
- [Langfuse](/content/changelog/index.html): Traces, evals, prompt management and metrics to debug and improve your LLM application. (1,184 words)
- [Multi-Modality - Langfuse](/content/docs/observability/features/multi-modality/index.html): Langfuse fully supports multi-modal LLM traces, including text, images, audio, and attachments. (1,568 words)
- [Evaluating Multi-Turn Conversations (Simulation) - Langfuse](/content/guides/cookbook/example_simulated_multi_turn_conversations/index.html): This guide shows how to evaluate conversational applications by simulating conversations and using LLM-as-a-Judge evaluators (1,495 words)
- [Langfuse SDK Performance Test - Langfuse](/content/guides/cookbook/langfuse_sdk_performance_test/index.html) (767 words)
- [Langfuse Tracing and Prompt Management for Azure OpenAI and Langchain - Langfuse](/content/guides/cookbook/integration_azure_openai_langchain/index.html): This cookbook demonstrates use of Langfuse with Azure OpenAI and Langchain for prompt versioning and evaluations. (644 words)
- [Evaluate Langfuse LLM Traces with UpTrain - Langfuse](/content/guides/cookbook/evaluation_with_uptrain/index.html): This notebook demonstrates how to run UpTrain's evaluation metrics on the traces generated by Langfuse. (1,181 words)
- [Example - Tracing and Evaluation for the OpenAI-Agents SDK - Langfuse](/content/guides/cookbook/example_evaluating_openai_agents/index.html): This guide shows how to evaluate the OpenAI-Agents SDK with Langfuse using online and offline evaluation methods. (867 words)
- [Langfuse joins ClickHouse - Langfuse](/content/blog/joining-clickhouse/index.html): Our goal continues to be building the best AI engineering platform (1,154 words)
- [Self-Hosted Pricing - Langfuse](/content/pricing-self-host/index.html): Deploy Langfuse OSS today. Upgrade to Enterprise at any time. (593 words)
- [Trace Claude Code with Langfuse - Langfuse](/content/integrations/developer-tools/claude-code/index.html): Trace Claude Code AI coding assistant conversations, user inputs, and tool usage with Langfuse for comprehensive observability. (661 words)
- [llms-txt.html](/content/llms-txt.html) (1,288 words)
- [MCP Server - Langfuse](/content/docs/api-and-data-platform/features/mcp-server/index.html): Native Model Context Protocol (MCP) server for Langfuse, enabling AI assistants to interact with your Langfuse data programmatically. (496 words)
- [Braintrust Data Alternatives? The best LLMOps platform? - Langfuse](/content/resources/engineering/best-braintrustdata-alternatives/index.html): his article compares Langfuse and Braintrust for LLM observability, analytics, evaluations, and engineering workflows. (666 words)
- [Langfuse Launch Week #1 - Langfuse](/content/blog/launch-week-1/index.html): Unveiling Langfuse 2.0 in a week of releases (829 words)
- [Authentication & SSO - Langfuse](/content/docs/administration/authentication-and-sso/index.html): Overview of Single Sign-On (SSO) methods in Langfuse (1,123 words)
- [Event queuing/batching - Langfuse](/content/docs/observability/features/queuing-batching/index.html): Queuing/batching configuration for Langfuse Tracing. (426 words)
- [Caching - Langfuse](/content/docs/prompt-management/features/caching/index.html): Langfuse prompts are cached client-side in the SDKs, so there's no latency impact after the first use. (805 words)
- [Blog - Langfuse](/content/blog/index.html): The latest updates from Langfuse: product announcements, engineering deep dives, and guides for building LLM applications. (496 words)
- [Observability for LlamaIndex with Langfuse Integration - Langfuse](/content/guides/cookbook/integration_llamaindex_workflows/index.html): Discover how to integrate Langfuse with LlamaIndex for enhanced LLM application monitoring, debugging, and tracing. Improve your AI development workflow today. (913 words)
- [Langserve Integration - Langfuse](/content/guides/cookbook/integration_langserve/index.html): This guide shows how to natively integrate Langfuse with LangChain's Langserve for observability, metrics, evals, prompt management, playground, datasets. (456 words)
- [Open Source Observability for LiteLLM Proxy - Langfuse](/content/integrations/gateways/litellm/index.html): Open source observability and tracing for LiteLLM Proxy. Log every LLM call routed through LiteLLM to Langfuse for tracing, cost tracking, and debugging. (589 words)
- [Langfuse agent skill - Langfuse](/content/changelog/2026-05-26-langfuse-agent-skill/index.html): Your agent's playbook for production-ready LLM apps (409 words)
- [Python v2 → v3 - Langfuse](/content/docs/observability/sdk/upgrade-path/python-v2-to-v3/index.html): Migration guide for upgrading the Langfuse Python SDK from v2 to v3. (623 words)
- [integrations/other/hermes-md.html](/content/integrations/other/hermes-md.html) (650 words)
- [Corrections - Langfuse](/content/docs/observability/features/corrections/index.html): Capture improved versions of LLM outputs directly in traces and observations to build better datasets and drive continuous improvement. (367 words)
- [OpenLIT Integration via OpenTelemetry - Langfuse](/content/guides/cookbook/otel_integration_openlit/index.html): Example cookbook for the OpenLIT Langfuse integration using OpenTelemetry. (392 words)
- [Error analysis - Langfuse](/content/academy/monitoring/error-analysis/index.html): A structured way to identify how your LLM application fails by reading traces and grouping the failures into categories you can act on. (654 words)
- [Security & Guardrails - Langfuse](/content/docs/security-and-guardrails/index.html): Comprehensive guide to LLM security guardrails — protect against prompt injection, PII leakage, and harmful content. Learn how to use LLM Guard, NeMo Guardrails, and Langfuse to monitor and evaluate LLM safety. (1,077 words)
- [Guaranteed Availability - Langfuse](/content/docs/prompt-management/features/guaranteed-availability/index.html): Ensure 100% availability of prompts by pre-fetching them on application startup and providing a fallback prompt. (502 words)
- [Music streaming DJ - Langfuse](/content/academy/examples/music-streaming-dj/index.html): How a net-new, low-risk DJ feature in a music streaming app goes live almost immediately and improves from listening behavior. (770 words)
- [Experiments via SDK - Langfuse](/content/docs/evaluation/experiments/experiments-via-sdk/index.html): Start experiments via the Langfuse SDK to programmatically test your application (646 words)
- [Annotation Queues - Langfuse](/content/docs/evaluation/evaluation-methods/annotation-queues/index.html): Manage your annotation tasks with ease using our new workflow tooling. Create queues, add traces to them, and get a simple UI to review and label LLM application traces in Langfuse. (498 words)
- [Example: Langfuse Prompt Management for OpenAI functions (Python) - Langfuse](/content/guides/cookbook/prompt_management_openai_functions/index.html): Cookbook on how to use Langfuse Prompt Management to version control prompts collaboratively when using OpenAI functions. (723 words)
- [Perks and Pay - Langfuse](/content/handbook/perks-and-pay/index.html): Compensation and benefits at Langfuse. (402 words)
- [Cookbook - Langchain Integration (JS/TS) - Langfuse](/content/guides/cookbook/js_integration_langchain/index.html): Cookbook with examples of the Langfuse Integration for Langchain (JS/TS). (486 words)
- [Application Containers (self-hosted) - Langfuse](/content/self-hosting/deployment/infrastructure/containers/index.html): Langfuse uses Docker to containerize the application. The application is split into two containers (Langfuse Web and Langfuse Worker). (475 words)
- [Experiments - Langfuse](/content/academy/experiments/index.html): How to use experiments to systematically improve your LLM application by isolating variables and comparing outputs. (632 words)
- [External Evaluation Pipelines - Langfuse](/content/guides/videos/external-evaluation-pipelines/index.html): Introduction to building fully cusotmizable evaluation pipelines on top of Langfuse. (47 words)
- [Billable Units - Langfuse](/content/docs/administration/billable-units/index.html): Learn how billable units are calculated in Langfuse. (333 words)
- [How to set up a user feedback loop for your application - Langfuse](/content/guides/user-feedback-loop/index.html): Capture explicit and implicit user feedback as scores on your traces, surface the responses worth reviewing, and turn what you learn into datasets and automated evaluators. (736 words)
- [AI Engineering Loop - Langfuse](/content/academy/ai-engineering-loop/index.html): A high-level map of the AI engineering lifecycle, from tracing and monitoring to building datasets, experimenting, and evaluating. (734 words)
- [Web Callouts - Langfuse](/content/docs/observability/features/web-callouts/index.html): Trigger an HTTP callout from a trace, observation, or session in Langfuse. (433 words)
- [n8n Node - Langfuse](/content/docs/prompt-management/features/n8n-node/index.html): Community-maintained n8n node that enables seamless integration of Langfuse prompt management capabilities into n8n workflows. (276 words)
- [Graph View: Aggregated and Expanded modes - Langfuse](/content/changelog/2026-07-13-graph-view-modes/index.html): The trace graph view now offers two layouts, an aggregated overview and an expanded as-it-ran DAG, on a rebuilt deterministic renderer. (447 words)
- [Troubleshooting and FAQ - Langfuse](/content/docs/evaluation/troubleshooting-and-faq/index.html): Troubleshooting and FAQ for Langfuse Evaluation. (4,114 words)

## Resources

- [Full Page Index](/index.html): Browse all cached pages with rich metadata
- [About This Cache](/about.html): Methodology, technical details, and usage guidelines
- [XML Sitemap](/sitemap.xml): Machine-readable sitemap for crawler discovery
- [Robots.txt](/robots.txt): Crawler directives
- [AgentSite Network](https://agentsite.network/network.html): Public index of AgentSites and their machine-readable resources