langfuse.com

So excited to finally drop this. Langfuse joins @ClickHouseDB to push Agentic AI development forward. Open Source. Faster than ever. Full story: langfuse.com/blog/joining-c…

langfuse just got much faster. read about all changes and how to enable the upgrades here: langfuse.com/docs/v4

Give @cursor_ai access to your traces, scores, and prompts to suggest how to improve your agent

🎌

JetBrains launches Tracy, an open-source Kotlin library for observability with OTel under the hood and native Langfuse support

New on the blog: how to set up evaluation for AI agent skills with Langfuse datasets and experiments. We used it to improve our own Langfuse skill 👇 langfuse.com/blog/2026-02-2…

btw if you are serious about OpenClaw or similar, the best advice I have is: use OpenRouter (easy observability), and export your API calls to LangFuse (free plan) do a few tasks, and read the prompts in LangFuse. Notice where it gets confused. Read reasoning traces, tool calls, etc. Review the system prompts for irrelevant jank. This is the fundamental analysis that allows you to tweak everything else, add new skills, etc. Don’t tweak your agent in the dark!

@cursor_ai has a @langfuse plugin! it's now easier than ever to build with langfuse from inside cursor install from: cursor.com/marketplace/la…

@wasss_im 🫢 Allemand / Americain 🇩🇪🇺🇸 — mais on trace tes LLMs avec une précision très… suisse

@langfuse C'est français !?

C'est ça!

llm-as-a-judge in langfuse can now target observations thanks to @marliessophie significant granularity & performance increase compared to trace-level scores! check out the changelog and give it a spin: langfuse.com/changelog/2026…

Shoutout to the new @langfuse cli - really helps to identify and correlate issues in agentic systems quickly 🙌

@lotte_verheyden shared her first use-case for it: using the CLI to let your agent auto-improve application prompts based on your langfuse evals 1. agent pulls traces and related evals 2. agent pulls related prompts 3. agent suggests prompt improvements based on evals 4. agent updates new prompt version to langfuse after approval read the guide here: langfuse.com/blog/2026-02-1…

"please install langfuse-cli" built for coding agents and power users who prefer the command line to interact with their langfuse data start here: langfuse.com/changelog/2026…

without @langfuse, it would be much harder to build agentic systems. At the same time, I still feel like a beginner here.

Happy to welcome @canva as a Langfuse customer! Read the story of how @andischuster & team are building their multi-agent support experience on Langfuse. Full story: langfuse.com/customers/canva

OpenClaw can create new Langfuse accounts and instruments your application

Langfuse is now much more accessible for Agents: try the new CLI, skills, MCP server, and RAG api. Start with the skill as it helps agents onboard onto all of these features.

How can you see what your AI agent is actually doing? In part three of our blog series, we add observability using LangFuse tracing to our Kotlin coding agent, giving us step-by-step insights and clearer debugging. We even uncover a bug we didn't know about. Read more: jb.gg/3ge5e6

@langfuse is genuinely one of the best products i’ve used. Saves us so much time!!