Skip to content

From Love Letters to Thesis Papers: How Langfuse Saves the Day

Langfuse is a Berlin-based company.

• It is an open-source observability & analytics solution for LLM-based applications.

• Founded in 2022 by Maximilian Deichmann, Marc Klingen, and Clemens Rawert

Today we are stepping into a realm where language meets technology, a place where words transform into powerful applications. 

Language Models (LLMs) are powerful machine learning models trained on vast amounts of text data. They can understand and generate human-like text, making them valuable for applications such as text completion, translation, sentiment analysis, and more.

Look at it as Chat GPT. All of us have used it at least once. It can write any story, poem, or letter you can imagine. Even those essays that we sneakily use it for. 

It's super versatile and helpful, but sometimes it ends up giving us unexpected results, like maybe turning your paper into a love letter, just because of one wrong word. It's a struggle, isn't it? You go to the application to make your work easier and it ends up messing everything up!

Well, Langfuse, a pre-seed, Berlin-based company, is here to help us with that.

What is Langfuse?

It is an open-source observability & analytics solution for LLM-based applications. They help companies to track and analyze quality, cost, and latency across product releases and use cases. Langfuse is mostly geared towards production usage but some users also use it for local development of their LLM applications.

Langfuse is focused on applications built on top of LLMs. Many new abstractions and common best practices evolved recently, e.g. agents, chained prompts, embedding-based retrieval, and LLM access to REPLs & APIs. These make applications more powerful but also unpredictable for developers as they cannot fully anticipate how changes impact the quality, cost, and overall latency of their applications. Thus Langfuse helps to monitor and debug these applications.

In simpler words, Langfuse supervises LLM applications. It makes the application more efficient and reliable. It focuses on three main things- 

  • Quality: It checks if the apps are doing what they're supposed to do, like providing accurate information or solving problems correctly.
  • Cost: It helps businesses figure out if running these apps is too expensive, like whether they're spending too much on computer power.
  • Latency: It measures how fast these apps respond to users. Nobody likes a slow app, right?

Langfuse is currently in its early stages, with three active founders


Marc Klingen - Marc has diverse experience across Product, Sales, Business Intelligence, and full-stack engineering at companies from large (Google, DHL) to early-stage startups.

He graduated within the top 1% of his Masters in Management and Computer Science from Technical University Munich. Besides that, he loves to hack on personal projects and connect with other builders (something he does not get to do too much right now).

Maximilian Deichmann - Max built trading systems at European 5bn Fintech, Trade Republic. He knows the ins and outs of building reliable, scalable systems to handle our customers’ most critical business processes.

While Max started out studying Management as an undergrad, he quickly found his love for computer science and transitioned into engineer self-taught and with a graduate degree.

Clemens Rawert - Before starting Langfuse, Clemens worked with the founder-CEOs of German Fintech Unicorn Scalable Capital including a unicorn fundraising, an acquisition, and helped scale the org and team from 100 - 400 employees. On another note, he studied Economic History, dropped out of a PhD at Oxford, and was a competitive wine taster.

As Langfuse continues to evolve under the visionary guidance of its founders, we anticipate a future where LLM applications can truly flourish, delivering precision and reliability in every keystroke.

Edited by Shruti Thapa