Langfuse: Open-Source LLM Observability You Can Self-Host
Langfuse brings full tracing, prompt versioning, dataset evaluation, and cost attribution to LLM apps - and you can run the entire stack on your own servers.
Traditional APM tools (Datadog, New Relic) capture HTTP latency and error rates. They tell you a request took 4 seconds - but not that 3.8 seconds was an LLM call, that the prompt had 1,200 tokens, that the model used was gpt-4o, or that the user-visible answer was a hallucination. Langfuse fills this gap with LLM-native observability.
Core Hierarchy
Trace → Span → Generation
A Trace represents one user interaction (e.g., one chat message)
Spans are logical steps within a trace (retrieve documents, format prompt, call LLM)
A Generation is a specific LLM call with input/output tokens, model name, latency, and cost
Team workspace
Ship faster with chat, meetings, and projects in one place — Zlyqor.
Changing a prompt in production no longer requires a code deploy.
Dataset Creation From Production Traces
Mark any trace as a dataset item directly from the UI. Build ground-truth datasets from real user interactions, then run batch evaluations to compare prompt versions or models.
Practical deep-dives on LLMs, developer tools, and AI engineering. No filler. Unsubscribe any time.
// written byFIG. AUTH-01
530
Mahmudul Haque Qudrati
CEO & ML Engineer
CEO and ML Engineer at Pristren. Builds AI-powered software for teams and writes about machine learning, LLMs, developer tools, and practical AI applications.
SpaceX is buying Cursor, the AI-powered code editor. The deal signals a shift in how AI coding tools are valued and deployed. Here's a practical breakdown of what's happening and what it means for developers.
