Langfuse is an open-source LLM engineering platform that offers various features such as observability, prompt management, evaluations, datasets, and metrics. Users can monitor LLM analytics, collect scores, and run model-based evaluations within Langfuse. The platform allows for manual scoring of LLM outputs and testing of app behavior before deployment using datasets. Langfuse can be deployed through their cloud managed service or self-hosted using Docker. The platform integrates with various SDKs and supports a wide range of LLMs for different applications. Users can also contribute to Langfuse through GitHub discussions, Discord, or by opening PRs.
https://github.com/langfuse/langfuse