Open Source AI Engineering Platform - Langfuse

Langfuse is an open-source AI engineering platform (GitHub) that helps teams collaboratively debug, analyze, and iterate on their AI agent applications. All platform features are natively integrated to accelerate the development workflow. Langfuse is open, self-hostable, and extensible (why Langfuse?).
Lowest level transparency
Understand cost and latency
Version control and deploy
Collaborate on prompts
Test prompts and models
Measure output quality
Monitor production health
Test changes in development
API-first architecture
Data exports to blob storage
Enterprise security and administration
One endpoint for model providers
Manage provider keys centrally
Track AI usage and cost per user
Observability is essential for understanding and debugging AI agent applications. Unlike traditional software, AI agent applications involve complex, non-deterministic interactions that can be challenging to monitor and debug. Langfuse provides comprehensive tracing capabilities that help you understand exactly what's happening in your application.
Want to see an example? Play with the interactive demo.
Watch end-to-end walkthrough of Langfuse Observability and how to integrate it with your application.
Traces allow you to track every LLM call and other relevant logic in your app.
Trace detail of a RAG answer with the generation selected. Hover the cost and token values in the generation header to see the cost and usage breakdowns, expand the collapsed chat history, then select the retrieval span in the tree to see the context it returned.
Sessions allow you to track multi-step conversations or agentic workflows.
Trace detail of one support-chat turn. Click the “session” badge in the trace header to open the session: every turn of the conversation in one view, with the user and assistant messages in order. Click the last turn in the list on the left to jump to it.
Debug latency issues by inspecting the timeline view.
Trace detail of an agent trace. Switch from “Tree” to “Timeline” to see each step as a bar on a time axis with its duration and cost, so the slowest steps stand out. Click one of the llm.chat calls to open it, then switch back to “Tree”.
Add your own userId to monitor costs and usage for each user. Optionally, create a deep link to this view in your systems.
Users list with each user's first and last event, trace count, tokens and cost. Click a user to open their page with total observations, tokens and cost, their traces, and the “Scores” tab with every score on their traces.
LLM agents can be visualized as a graph to illustrate the flow of complex agentic workflows.
Trace detail of an agent trace, “Graph” tab next to Tree and Timeline. In the default Aggregated mode, repeated steps collapse into one node such as “llm.chat (3/3)”; select it to see its observations. Switch the toggle to Expanded to see the run as it happened, click a tool call node, then switch back to Aggregated.
See quality, cost, and latency metrics in the dashboard to monitor your LLM application.
Home dashboard with traces by name, model costs and scores. Change the time range from “Past 1 day” to “Past 7 days”, then scroll through observations by level, model usage and cost, user consumption, score trends and latency percentiles.
Get notified over Slack, GitHub Actions, or Webhooks when a metric crosses a threshold with alerts.
The AI Gateway gives your organization one endpoint for calls to your model providers. Every call is recorded in Langfuse, so you can see and control AI usage across your company.
See what your organization spends on AI and who uses it, with cost, requests, and tokens per user, API key, and model on the analytics page.
Every call through the gateway becomes a regular Langfuse trace. With the FULL ingestion mode, traces include the full input and output, so you can debug, evaluate, and annotate them.
Choose which models each provider connection allows, so only approved models can be called through the gateway.
Issue user and service account gateway keys instead of sharing provider API keys. Add metadata such as a team or cost center to attribute spend.
Prompt Management lets you manage and version model-call templates. Skill Management, currently in beta, brings versioning and labels to agent instructions and supporting files. Use both to connect the instructions your application receives to its behavior in traces.
Want to learn more? Watch end-to-end walkthrough of Langfuse Prompt Management and how to integrate it with your application.
Create a new prompt via UI, SDKs, or API.
Prompts > “New prompt”. Enter the name order-status-reply and a text prompt with the variables {{customer_name}} and {{order_id}}; Langfuse lists the detected variables below the editor. Keep “Set the production label” checked and click “Create prompt”: version 1 opens with the production and latest labels.