Plain-AyI
← All projects
Running AI at scale

Langfuse

Helps teams track, test and improve their AI apps by recording what the AI did and how well it did.

What it does

Langfuse is a platform for teams building apps with large language models. It records "traces", step-by-step logs of each AI call and action, so developers can see what happened when something goes wrong.

It also stores and versions prompts, runs evaluations (checks of how good the answers are, by AI judges, code or people), manages test datasets, and has a playground for trying out prompts.

It can be used as a hosted cloud service or run on your own servers.

Who it's for

Developers and teams running AI-powered products.

Can I use it without coding?

Developers only. Needs code changes in your app to send it data; self-hosting uses Docker. New to this? Start here.

Can I run it?

Cost
Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
Runs on
Server, Cloud
Privacy
Your choice: run it on your device or use an online service
API key
Not needed

Try it

  1. Sign up for Langfuse Cloud's free tier, or run Langfuse on your own machine with Docker.
  2. Connect your AI app using one of its integrations so it starts recording what the AI does.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • No standard license listed. Check the GitHub page before using it for business.
  • More on staying safe

Where people are talking about it