Langfuse
by Langfuse
What is Langfuse? Langfuse is an open-source (MIT core) platform for tracing, evaluating and improving LLM applications and agents: it records traces, runs LLM-as-a-judge evaluations on them, and manages datasets and experiments. It can be self-hosted.
Editor note
An open-source, self-hostable platform for tracing LLM apps and agents and scoring them with LLM-as-a-judge evaluators, datasets and experiments.
- What it tests
- Your own LLM app, on production traces and test datasets.
- Original source
- github.com/langfuse/langfuse
- Last updated
- Repo last commit 2026-10-16
- License
- MIT (core)
When to use Langfuse
- You want evaluation scores attached to real production traces, not only offline test sets.
- You need to self-host your observability and eval data.
Limitations
- It is a platform, not a benchmark: the quality of its scores depends on the judges and datasets you set up.
How to run it
- Self-host with the repository's deployment docs or use the hosted version.
- Send traces with the SDK, then configure evaluators and datasets.
Notable results
- README (read 16 Oct 2026): MIT licensed, self-hostable. [Official repository]
Sources
Reviews
No reviews yet.
Reviews from practitioners who sign in with GitHub open soon.
Related rubric libraries & frameworks evals
- Inspect Evals — Many benchmarks under one runner: coding, agents, safety, knowledge.
- OpenAI Evals — Building and running your own evals; community registry.
- LLMJury rubric library — LLM-as-judge rubrics for support, RAG, summaries, code and tone.
- Prompt Assay judge templates — Starter LLM-as-judge prompts.