Langfuse

Langfuse is an AI engineering platform that provides observability, prompt management, and evaluation tools for large language model applications. It traces LLM calls, tool invocations, and retrieval steps; manages prompts with version control and deployments; and runs evaluations using LLM-as-a-judge, heuristic functions, or human review. The platform works with any language and framework supporting OpenTelemetry instrumentation and integrates with frameworks like LangChain, model providers including OpenAI and Anthropic, and supports self-hosting via Docker, Kubernetes, AWS, GCP, and Azure.