An open-source platform that helps teams collaboratively observe, evaluate, and debug LLM calls. It provides tracing, prompt management, and testing capabilities for AI engineering workflows.
Project overview
An open-source platform that helps teams collaboratively observe, evaluate, and debug LLM calls. It provides tracing, prompt management, and testing capabilities for AI engineering workflows.
Project type
Evaluation & Observability · Infrastructure
Deployment
Docker / Docker Compose
License
License pending
Best for
AI engineers, developers, and data teams who need to collaboratively trace, evaluate, and debug LLM applications.
Key capabilities
Instrument your app and start ingesting traces to Langfuse, tracking LLM calls and other relevant logic such as retrieval, embedding, or agent actions.
Supports LLM-as-a-judge, Code evaluators, user feedback collection, manual labeling, and custom evaluation pipelines via APIs/SDKs.
Enable test sets and benchmarks for evaluating your LLM application, supporting pre-deployment testing and structured experiments.
A tool for testing and iterating on your prompts and model configurations to shorten the feedback loop.
Public API to power bespoke LLMOps workflows with OpenAPI spec, Postman collection, and typed SDKs.
Limitations and risks
The platform relies on ClickHouse open source database for its operations.
Self-hosted instances automatically report basic usage statistics to a centralized server by default.
Some folders containing enterprise edition features are not MIT licensed.
Getting started
The platform is rated as easy to set up, supporting local deployment in minutes via Docker Compose. The first success path involves cloning the repository, running docker compose up, accessing the local Web GUI, and creating a new project and API credentials.
Evidence and sources
README: Langfuse is an **open source LLM engineering** platform. It helps teams collaboratively **develop, monitor, evaluate,** and **debug** AI applications. Langfuse can be **self-hoste…
README: - [LLM Application Observability](https://langfuse.com/docs/tracing): Instrument your app and start ingesting traces to Langfuse, thereby tracking LLM calls and other relevant log…
README: - [Prompt Management](https://langfuse.com/docs/prompt-management/get-started) helps you centrally manage, version control, and collaboratively iterate on your prompts. Thanks to…
README: Managed deployment by the Langfuse team, generous free-tier, no credit card required.
README: - [Local (docker compose)](https://langfuse.com/self-hosting/local): Run Langfuse on your own machine in 5 minutes using Docker Compose.