Max Deichmann

@DanielLockyer @langfuse Here is a talk where I describe what is going on: youtube.com/watch?v=NXYQ5o… We will launch this more broadly over the next weeks. The new APIs are the first product on the new data model.

@maxdeichmann @langfuse Curious if you can share the main diff between the two? Diff tables? Diff architecture?

Been seeing HTTP 502/503 responses from the @langfuse API for a while now - is this normal? Would love to know why this is happening 🙃

@DanielLockyer @langfuse Awesome! Yes, the v2 APIs are very high performance APIs. If you have feedback here, let us know!

@maxdeichmann @langfuse api/public/traces/<id>, BUT I've just followed up with my client and it seems you've recommended the v2 API :) I'll check it out!

@mgill25 @mgill25 love this. We can host in our office at @langfuse and are also happy to share insights about our system architecture. Do you want to chat about this?

#Berlin peeps - thinking of organising another edition of Berlin Systems Group Meetup in January. If you’re interested in speaking - check out berlinsystems.xyz and DM me!

We don’t only want to show taste in product design but also in office design. Next to the neon logo, what are best ways to make an office unique?

@skylar_b_payne @langfuse @langfuse_dev Hi, im the CTO at Langfuse. Correct, the ClickHouse nodes should never scale to zero. Otherwise you won’t be able to ingest data.

@langfuse / @langfuse_dev - am I right in understanding the architecture that clickhouse query processor will basically never scale down to zero as long as traces are continuously coming through? (unless aggressive batching?) Trying to estimate costs :). I think this is right, but love double checking my work haha

The team is excited to watch Steffen launching his new Rust container which he build over night to fix some of our big data challenges we were not able to solve in our database.

@langfuse More: langfuse.com/blog/2025-10-2…

Last day of @Langfuse Launch Week. Schema Enforcement: Guarantee a consistent data structure for all dataset items, making your experiments reliable. Second, Dataset Folders. As your app matures, test datasets multiply. Easily organize them in folders.

@langfuse We also added new guides on experimentation and CI/CD integration here: - langfuse.com/blog/2025-11-0… - langfuse.com/blog/2025-10-2…

@langfuse More: langfuse.com/blog/2025-10-2…

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.

@langfuse More: langfuse.com/changelog/2025…

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.

@langfuse More: langfuse.com/changelog/2025…

Today is Day 2 of @Langfuse Launch Week 4, and we're launching features for better team collaboration. You can now use @ Mentions to tag teammates directly on traces, prompts, or sessions, and use Emoji Reactions to quickly acknowledge insights and share feedback.

Thanks so much for having me, @tylerhannan and @ClickHouseDB! It was fun to talk with the ClickHouse team about database internals during the event.

@ClickHouseDB @langfuse Event: clickhouse.com/openhouse/amst…

Excited to be speaking at @ClickHouseDB Open House Amsterdam on October 28 I'll share how we use ClickHouse as the backbone of @Langfuse’s real-time observability platform for LLM apps, powering everything from high-volume tracing to complex evaluations and dashboards.

@qoega where do you visualize the data? I’d love to have this side by side in Datadog with my other traces and metrics

We are using @ClickHouseDB heavily in production at @langfuse and I am wondering how we can attribute CH resource usage (CPU, mem) to specific users and features? We are currently running CH queries on the system tables and move the results hourly to Metabase.