langfuse/langfuse: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Langfuse is an open source LLM engineering platform for observability, evals, metrics, prompt management, playgrounds, and datasets.
It helps teams collaboratively develop, monitor, evaluate, and debug AI applications.
Langfuse can be self-hosted in minutes and is built on ClickHouse.
LLM observability lets you ingest traces to track model calls, retrieval, embeddings, and agent actions.
Prompt management supports centralized versioning and collaboration, with caching to avoid added latency.
Evaluations include LLM-as-a-judge, code evaluators, user feedback, manual labeling, and custom pipelines via APIs/SDKs.
Datasets are used for test sets, benchmarks, continuous improvement, pre-deployment testing, and structured experiments.
The playground lets developers test prompts and model settings and jump from a bad trace directly into iteration.
Langfuse provides a comprehensive API plus OpenAPI, Postman, and typed Python and JS/TS SDKs.
It integrates with tools like OpenAI, LangChain, LlamaIndex, LiteLLM, Vercel AI SDK, and other agent and chat frameworks.

Your notes

Save this item to your library to add private notes.