Langfuse Assistant is now in public beta on Langfuse Cloud. Chat with your data in Langfuse and get answers in plain language. Ask things like "why did latency spike yesterday?", "which generations are failing?", or "where is my token spend going?" It's powered by the Langfuse MCP under the hood. This is an initial release, with more capabilities coming over time. Free of charge while in beta. Full story in the comments.
Langfuse
Software Development
Open Source LLM Engineering Platform, now part of ClickHouse
About us
Langfuse is an open source AI engineering platform. It helps teams collaboratively develop, monitor, evaluate, and debug AI applications. Langfuse can be self-hosted in minutes and is battle-tested and used in production by thousands of users from YC startups to large companies like Khan Academy or Twilio. Langfuse builds on a proven track record of reliability and performance. Developers can trace any Large Language model or framework using our SDKs for Python and JS/TS, our open API or our native integrations (OpenAI, Langchain, Llama-Index, Vercel AI SDK). Beyond tracing, developers use Langfuse Prompt Management, its open APIs, and testing and evaluation pipelines to improve the quality of their applications. Product managers can analyze, evaluate, and debug AI products by accessing detailed metrics on costs, latencies, and user feedback in the Langfuse Dashboard. They can bring humans in the loop by setting up annotation workflows for human labelers to score their application. Langfuse can also be used to monitor security risks through security framework and evaluation pipelines. Langfuse enables non-technical team members to iterate on prompts and model configurations directly within the Langfuse UI or use the Langfuse Playground for fast prompt testing. Langfuse is open source and we are proud to have a fantastic community on GitHub and Discord that provides help and feedback. Do get in touch with us! Langfuse is now part of ClickHouse.
- Website
-
https://langfuse.com
External link for Langfuse
- Industry
- Software Development
- Company size
- 11-50 employees
- Headquarters
- San Francisco
- Type
- Privately Held
- Founded
- 2022
- Specialties
- Langfuse, Large Language Models, Observability, Prompt Management, Evaluations, Testing, Open Source, LLM, AI, Analytics, Open Source, and Artificial Intelligence
Products
![Click here to view Langfuse]()
Langfuse
Product Analytics Software
Langfuse is an open-source LLM engineering platform that helps teams collaboratively debug, analyze, and iterate on their LLM applications.
Employees at Langfuse
View 21 employees at Langfuse
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
Locations
-
Primary
Get directions
San Francisco, US
-
Get directions
Berlin, DE
Updates
-
Langfuse is going on Europe Tour! 🚌 We're joining ClickHouse in Amsterdam, London, and Munich later this year. Join us for a hands-on Langfuse workshop where we'll show you how to observe, debug, and improve your AI applications, step by step, using a real sample app. Bring your questions and discover how Langfuse can level up your specific use cases! Sign-up links in the comments. ⬇️
-
-
Now live: Langfuse x Hermes integration. Hermes Agent by Nous Research is a self-improving AI agent with persistent memory, autonomous skill creation, and support for any LLM provider. It ships with a bundled Langfuse observability plugin that automatically captures every conversation turn, LLM request, and tool call, including token usage and cost. All details in the comments.
-
-
Meet us at AI Engineer Melbourne!
AI Engineer, Melbourne today and tomorrow. Langfuse and ClickHouse, one booth. If you're tracing LLM calls and wondering where the data should live at scale, we have an answer. We also have quality merch, cloud credits and live demo's cc Marc Klingen
-
-
𝗗𝗮𝘆 𝟱 𝗼𝗳 𝗟𝗮𝗻𝗴𝗳𝘂𝘀𝗲 𝗟𝗮𝘂𝗻𝗰𝗵 𝗪𝗲𝗲𝗸: Langfuse MCP. Until this week, the hosted Langfuse MCP server only exposed prompt management. Today, it covers most of Langfuse: observations, metrics, scores, score configs, datasets, and their items and runs, comments, annotation queues, models, media, and health. Agents such as Claude Cowork or Linear can now investigate a production issue, pull the relevant observation, query metrics, drop a comment for the team, create a score, or create dataset items for regression testing, all without leaving the chat. The MCP server complements the Langfuse Skill and the Langfuse CLI. Use the CLI when your agent can run bash and pre-filter data. Use the MCP server when it cannot. Restrict to read-only by allow-listing lookup tools if you don't want writes. Shoutout to Ben Bachem for shipping this. Link in comments.
-
𝗗𝗮𝘆 𝟰 𝗼𝗳 𝗟𝗮𝗻𝗴𝗳𝘂𝘀𝗲 𝗟𝗮𝘂𝗻𝗰𝗵 𝗪𝗲𝗲𝗸: Code evaluators. Not every evaluation needs an LLM. JSON parseability, schema validation, exact match, required tool arguments, custom business rules: things you can verify with code, you should verify with code. Deterministic, reproducible, no token cost. You can now write an 𝘦𝘷𝘢𝘭𝘶𝘢𝘵𝘦 function in Python or TypeScript directly in Langfuse, attach it to live observations or a dataset experiment, and the result lands as a native Langfuse score. Code evaluators sit alongside LLM-as-a-Judge rather than replacing it. Code wins for objective checks. A judge wins for quality, tone, or to add reasoning. They complement each other and give you a better, more complete picture together. Link in comments.
-
𝗗𝗮𝘆 𝟯 𝗼𝗳 𝗟𝗮𝗻𝗴𝗳𝘂𝘀𝗲 𝗟𝗮𝘂𝗻𝗰𝗵 𝗪𝗲𝗲𝗸 𝟱: Full-Text Search When something breaks in your AI app, you need to pull the one trace that says "refund failed" out of hundreds of GB of production data. Scroll-and-hope doesn't cut it at that scale. Full-text search is now live on Langfuse Cloud. In our benchmarks, large input/output searches that took 18 seconds and scanned 494 GB now return in under half a second and read less than a gigabyte. Built on top of ClickHouse's new full-text search and a tight feedback loop with their team, helping us land features in Langfuse weeks after they ship in ClickHouse core. Humans benefit in the UI. Agents benefit in the API: the new 'matches' operator on Observations API v2 lets coding agents and scripts run token-based search programmatically. Link in comments.
