BrainforgeLangfuse

Ship AI you can trace, test, and improve

We implement Langfuse tracing, evaluations, and production monitoring so teams can understand how their LLM applications behave and catch regressions before release.

Proven in production

  • 85K–200Kagent traces a month, projectedABC Home & CommercialLangfuse on a customer-service agent, a current joint opportunity.
  • 9 monthsin productionBrainforgeOur own agents across six surfaces, traced on Langfuse.
“The whole pipeline to improve our chat agent happens entirely in Langfuse. We screen conversations, review flagged sessions, turn clusters of unwanted behavior into datasets, and run those evals as regression tests before every release.”
Laurenz HemmenMachine Learning Scientist, DKBRead the story on langfuse.com ↗ (opens in a new tab)
Langfuse customer stories ↓

What we build with Langfuse

Tracing

Langfuse tracing for LLM calls, tool use, retrieval, and multi-step agent workflows.

Evals

Eval harnesses and scorecards that catch regressions before users do.

Production observability

Observability setups that connect traces to human review and release gates.

How we work together

  1. We implement Langfuse for teams putting AI into production and need visibility from day one.

  2. We partner on observability and eval design with ClickHouse and Langfuse field motions.

  3. We operate the trace and eval loop as models, prompts, and agents evolve.

Langfuse at scale

Langfuse is the open-source platform teams use to trace, evaluate, and improve LLM apps and agents. It joined ClickHouse in January 2026. These figures are Langfuse's own.

companies using Langfuse
50k+
of the Fortune 500 use it
129
SDK installs a month
65M+
observations a month
90B+

In production at Canva · Khan Academy · Ramp · Twilio · Intuit · Samsara · Hugging Face · SumUp · Merck Group

Sources: About Langfuse ↗ · langfuse.com ↗ · Langfuse customers ↗

Langfuse customer stories

All customer stories on langfuse.com ↗

This partnership is for you if

  • You have LLM features in production and cannot explain what they did on a bad run.
  • You need evals and traces behind releases, not ad hoc spot checks in a dashboard.
  • You want open-source observability with a path to self-host or cloud as requirements grow.

Sound like you? Book a call ↗

Resources

Let’s scope your Langfuse build

We use Langfuse to trace, evaluate, and improve LLM apps in production.

More partnerships

Explore the partner ecosystem

Explore partnerships →

Press Esc to close