Skip to content
local-ai

Langfuse

Monitoring Intermediate Open source Open core

An open-source observability platform for LLM applications: tracing, cost and latency tracking, evaluations, datasets, and prompt management. It is self-hostable, so you can keep your traces on your own infrastructure.

Strengths

  • Detailed tracing, with token, cost, and latency per call
  • Evaluations, datasets, and prompt management in one place
  • Self-hostable, and integrates with LiteLLM, LangChain, and more

Weaknesses

  • Self-hosting adds infrastructure to run, such as a database
  • Some features are reserved for the paid and enterprise tiers
  • Observability is one more system to operate and maintain

At a glance

Licence
MIT
Pricing
Open core
Platforms
Docker, Web, Linux
GPU required
No

Links

See also

Entry last verified 30 July 2026.