Langfuse provides open-source observability, logging, debugging and product analytics focused on applications built with large language models. Its SDKs and integrations capture full execution context (inference, embeddings, API usage and internal system interactions) and support frameworks like LangChain. The project is MIT-licensed, simple to self-host, and is offered as both a managed cloud and self-hosting product. Langfuse has open partnerships and integrations (e.g., LiteLLM, Flowise, Langflow) and works with eval projects such as Ragas to apply model-based evaluations on production data. The team originally iterated on LLM-native apps during Y Combinator’s winter 2023 batch, then open-sourced the product and launched on Product Hunt. The company says it will expand from observability into test-selection and eval tooling to close the loop between production traces and representative test sets.

Total raised

$4M

Funding rounds

1

Latest round

Seed

Latest activity

Nov 2023