Langfuse

Overview

Langfuse is an open-source platform for agent evals and observability. It connects tracing, monitoring, datasets, experiments, and evaluation in one continuous loop, enabling teams to trace every LLM call, manage prompts, evaluate, and experiment from prototype to production scale.

Key Features

• Hierarchical traces capture every LLM call, tool invocation, and retrieval step, filterable by user, session, cost, latency, or custom metadata.
• Evaluation with LLM-as-a-judge, heuristic functions, or human review, run on production data or during experiments.
• Prompt Management separates prompts from code with one-click deployments and rollbacks.
• Playground to test prompts on real production inputs and compare models side-by-side.
• Experiments to define test cases, run experiments, and compare results side by side.
• Cost & Latency monitoring with dashboards and automated alerts.

Use Cases

• Chat agents: session-level tracing, evals, and cost visibility for chat support and assistant experiences.
• Coding agents
• Workflow automation

Getting Started

• Start by following the 'Get Started with Tracing' guide to ingest your first trace using OpenAI, LangChain, or the SDKs.

Deployment & Requirements

• Self-hosting is supported via Docker Compose, Kubernetes (Helm), and Terraform for AWS, GCP, and Azure.

Before You Adopt

• License: Other. Review its terms before using, modifying, or distributing the project.