Langfuse
Open Source LLM Engineering Platform
Start new thread

Langfuse 2.0 - the open source LLM engineering platform

by•
Langfuse is the open source LLM Engineering Platform. It provides observability, tracing, evaluations, prompt management, playground and metrics to debug and improve LLM apps. Langfuse is open. It works with any model, framework and you can export all data.

Add a comment

Replies

Best
Great product! Congratulations! Supported
Maker
thank you! Appreciate it
Congrats! 🪢✨
Maker
🫡🫡🫡
Congratulations on the new launch !!
Maker
thank you! Let me know if you have any feedback while giving Langfuse a spin
This is very cool! Will share it with my team at QueryPal(), as we start benchmarking and evaluating, we are currently looking into WandB.
A bit late here, but I was wondering how you charge for evaluations?

Super impressive how far this has evolved — especially the shift from pure observability to a full LLM engineering platform.

One thing I keep running into though: even with great tracing and evals, debugging still breaks down when you try to reproduce issues locally — especially with non-deterministic behavior (tool calls, async chains, external APIs, etc).


Feels like we’ve solved “what happened”, but not fully “how do I deterministically replay and fix it”.


Curious how you think about that layer — is that something you see Langfuse moving towards over time?

Been tracking Langfuse for a while and the growth is impressive. LLM cost tracking alone is worth the setup. I run multiple LLM providers across different workflows and having one dashboard to see token usage and latency across all of them would save me from some surprise bills. The self-hosting option is a big plus.

First
Previous
•••
345