Langfuse

Name: Langfuse
Author: Langfuse

Open-source LLM tracing, evaluation, and prompt management.

Source Docs Website

Overview

Langfuse traces nested agent calls into a readable tree, tracks cost and latency per span, and supports both dataset-based and LLM-as-judge evaluation. Because it self-hosts cleanly, it is a common choice where prompts and completions cannot leave the network.

Why it's indexed

Full-featured tracing you can self-host — rare in this category.

Editorial judgement, not a measurement — see our methodology. Listing is never paid for.

At a glance

Vendor: Langfuse
Category: Observability & Evals
License: MIT
Deployment: Hybrid
Languages: Python, TypeScript
Pricing model: Open source · Free tier · Usage-based

Pricing is shown as a model, not a rate. Published rates change without notice — check the vendor's own page before budgeting.

Also in Observability & Evals

LangSmith

Tracing, evaluation, and monitoring from the LangChain team.

Phoenix

Open-source, OpenTelemetry-native tracing and evaluation for LLM apps.

Braintrust

Evaluation-first platform for shipping LLM changes with measured confidence.