Developers in Berlin! We're stoked to host another Langfuse Context event with our friends at Anthropic. This time our CEO Marc Klingen is joined by Adam Jones (Tech Lead working on MCP). Sign-up link in comments, seats limited. Marc and Adam will chat about building MCP, how Langfuse and Anthropic use AI to ship faster and finally, where they see the industry heading. The chat will be followed by cozy conversations over drinks.
About us
Langfuse is the 𝗺𝗼𝘀𝘁 𝗽𝗼𝗽𝘂𝗹𝗮𝗿 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲 𝗟𝗟𝗠𝗢𝗽𝘀 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!
- Website
-
https://langfuse.com
External link for Langfuse
- Industry
- Software Development
- Company size
- 2-10 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.
Locations
-
Primary
Get directions
San Francisco, US
-
Get directions
Berlin, DE
Employees at Langfuse
Updates
-
The final day of Launch Week brings dataset schema enforcement and folders to help you better manage and scale your evaluations.
Last day of Langfuse Launch Week: Dataset Schema Enforcement & Folders You can now define a schema for dataset inputs and expected outputs. This guarantees a consistent data structure across all dataset items. Second, Dataset Folders. As your app matures, test datasets multiply. Easily organize them in folders by adding slashes to the dataset name. 🔗 Link in comments to learn more.
-
For Day 5 of Launch Week, we are launching Score Analytics to validate your evaluation methods.
It's Day 5 of Langfuse Launch Week, and we are adding Score Analytics, a simple way to measure and align your evaluators. Quickly answer questions like “Is my LLM-as-a-judge actually measuring what I expect?” and “How well does user feedback match our manually annotated data?” 🔗 Link in comments to learn more.
-
Upgrade your experimentation workflow with in-view annotations, baseline comparisons, and the new Runner SDK.
Day 4 of Launch Week brings major upgrades to Experiments in Langfuse. You can now annotate traces side-by-side in the compare view, set baselines to instantly spot regressions, and filter for outliers. We also added new guides on experimentation and CI/CD integration here (🔗 link in comments)
-
Launch week 4 continues - today we shipped some major improvements for agent tracing and evaluation.
Day 3 of Langfuse Launch Week is all about Agents. We have released major improvements to help you debug and evaluate complex agents. This includes a new tools overview to validate tool choices, new observation types, a log view, and agent graphs. Check out the full changelog to see these features in action (🔗 Link in comments)
-
Langfuse now natively integrates with Mixpanel, export Langfuse metrics by setting up the integration
As part of Launch Week 4, Langfuse now integrates natively with Mixpanel 🎉 This integration combines Langfuse LLM Traces, Evals, and Metrics with other product analytics events in Mixpanel. Langfuse data is continuously exported to Mixpanel and can be incorporated into Mixpanel Boards. This helps answer questions such as: - Are my most active users also the ones most engaged with LLM content? - Does LLM feature usage correlate with higher retention? - How does the LLM feature impact conversion rates? - Does user feedback in Langfuse align with behavior in Mixpanel? How it works: 1. Configure your Langfuse project settings by selecting your Mixpanel region and Project Token. 2. Enjoy automatic hourly syncing of traces, generations, and scores. Historical data syncs on the first run. 3. Use Mixpanel's "AI Company KPIs" template to get started quickly.
-
Collaborate with your team directly in Langfuse 🚀
Day 2 of Langfuse Launch Week 4 is here, and we're rolling out new features to improve collaboration with your team. You can now use @ mentions and emoji reactions directly in the comments on sessions, traces, observations, or prompts. This update makes it easier than ever to bring specific findings to a teammate's attention with an @ mention, acknowledge insights or share quick feedback with an emoji reaction, and keep all your LLM-related conversations centralized in Langfuse. Stay tuned for more updates this week!
-
Langfuse reposted this
Building an AI product or feature? With our new Langfuse integration, you can now easily see how your LLM outputs tie to user-level outcomes. Join LLM observability data from Langfuse — such as cost, latency, accuracy, and model version — with product analytics data in Mixpanel to answer questions like: “Are my most active users also the ones who are most engaged with my LLM content?” “Does interacting with the LLM feature relate to higher retention rates?” “How does the LLM feature impact my conversion rates?” Add your Langfuse data to Mixpanel in seconds 👇 https://lnkd.in/e-r9FgWq
-
-
We are kicking off Launch Week 4 with two powerful new features designed to provide sophisticated data discovery and precise API-level querying at scale.
Today is day 1 of Langfuse Launch Week 4, and we're kicking things off with two features to help you navigate millions of traces: New Filter Sidebar (UI): One-click filtering, filter for “contains” and “does not contain”, and save your views. API Filters for Traces and Observations: Pass complex filter objects supporting datetime, string, number, and array filter types.
-
We can’t wait to show you what we’ve been building - see you next week!
Langfuse Launch Week 4 is coming next week! We'll be dropping a new feature every single day. This launch will bring major updates to evaluations, agent insights, team collaboration, and integrations. We'll also be hosting a special Virtual Community Hour mid-week to show the new features and chat with the team. See the full schedule and follow the reveals on our Launch Week Hub (🔗 link in comments)
-