# Langfuse

> Updated 2026-08-25 · type: tool · category: ai-infrastructure · status: active · rev 1

LLM engineering platform: observability, evals, prompt management, traces, and datasets — for diagnosing why a marketing/GTM agent made a bad recommendation,…

- Open source: yes (MIT)
- Self-hostable: yes
- Pricing model: freemium
- Best for: Engineering teams building LLM applications who need observability, tracing, prompt management, and evaluations.
- Last verified: 2026-09-04

- **Canonical:** https://gtmstacker.com/registry/tool/langfuse/
- **Source:** [github · langfuse/langfuse](https://github.com/langfuse/langfuse)
- **Tags:** ai-infrastructure, llm-observability, evals, prompt-management
- **Repository:** https://github.com/langfuse/langfuse

## Is Langfuse open source?

Yes — MIT-licensed.

## How much does Langfuse cost?

It has a free tier plus paid plans.

## Can I self-host Langfuse?

Yes — it can be self-hosted.


---

LLM engineering platform: observability, evals, prompt management, traces, and datasets — for diagnosing why a marketing/GTM agent made a bad recommendation, not just that it failed.

## Provenance

- MIT core verified (34.2k★, YC W23). Open-core: `ee/` folders are enterprise-licensed.
- Surfaced via the GTM Stacker X/Twitter signal reports (the "35 marketing repos" list + named drops); license independently WebFetch-verified 2026-09-03.