Langfuse
Open-source tracing, evals and cost tracking for LLM applications
What it is
An observability and evaluation platform for LLM applications and agents. It records traces of model calls, tracks usage and cost, and supports evaluating agents against production data; it can be self-hosted with Docker Compose or used as a cloud service. For teams running LLM features in production.
Good for
- Trace every model call in an agent run
- Track token usage and cost per feature
- Evaluate outputs against production data
Install or run
git clone --depth=1 https://github.com/langfuse/langfuse.git && cd langfuse && docker compose upCommand as given in the project README. Read the repository before you run anything on your machine.
What you need
Docker with Compose for self-hosting, or a Langfuse Cloud account
Sources
- https://github.com/langfuse/langfuse (project README, read 10 Nov 2026)
- https://api.github.com/repos/langfuse/langfuse (GitHub API, read 13 Nov 2026)
The summary is ours, written from the README. Spotted an error? See how we work.