platoseedplatoseed
Open source LLM engineering platform
Traces, evals, prompt management and metrics to debug and improve your LLM application. Onboard via https://langfuse.com Langfuse helps you build and improve LLM applications across the entire lifecycle: - Develop: Observability, Langfuse UI & Prompt Management - Monitor: Traces, Analytics, Metrics & Evaluations - Test: Experiments, Releases & Datasets We are hiring: https://langfuse.com/careers Langfuse was acquired by Clickhouse in January of 2026.
Langfuse is an open-source LLM engineering platform that provides observability, prompt management, evaluation, and human annotation to debug and improve LLM applications. It supports tracing, metrics, and a full production-grade workflow for moving from prototype to production with real usage data.
Langfuse ingests and queries LLM traces, provides hierarchical traces of calls and tool invocations, offers evaluation with LLM-based or human review evaluators, enables separate prompt management with one-click deployments and rollbacks, supports a playground for A/B testing prompts, defines experiments, and includes human annotation for golden datasets. It integrates with OpenTelemetry-compatible stacks, ships with multiple SDKs, supports self-hosting via Docker Compose or Kubernetes, and scales with enterprise-grade reliability and security features.
Who it’s for: AI teams building and operating production-grade LLM applications and agents, including developers, MLOps, and SREs needing observability, prompt management, and evaluation capabilities.
Customers: Canva
Community and open-source traction with 22,000+ GitHub stars, 2300+ customers, 10+ billion observations processed per month, and ongoing releases; mentions of enterprise-scale self-hosting and security/compliance indicate growth and adoption signals.
Marc has diverse experience across Product, Sales, Business Intelligence and full-stack engineering at companies from large (Google, DHL) to early stage startups. He graduated within the top 1% of his Masters in Management and Computer Science from Technical University Munich. Besides that, he loves to hack on personal project and connect with other builders (something he does not get to too much right now).
Max built trading systems at European 5bn Fintech, Trade Republic. He knows the ins and outs of building reliable, scalable systems to handle our customers’ most critical business processes. While Max started out studying Management in undergrad, he quickly found his love for computer science and transitioned into engineer self-taught and with a graduate degree.
Before starting Langfuse, Clemens worked with the founder-CEOs of German Fintech Unicorn Scalable Capital including a unicorn fundraising, an acquisition and helped scale the org and team from 100 - 400 employees. On another note, he studied Economic History, dropped out of a PhD at Oxford, and was a competitive wine taster.
Track quality, cost and latency of your LLM apps
Langfuse provides open-source product analytics for LLM apps to track quality, cost and latency across releases and use cases. The launch introduces tools to monitor, debug, and analyze LLM app performance with SDKs, self-hosting or a managed cloud, aimed at teams building production LLM applications.
From the original launch (Jul 2023) — may be outdated.
Formerly “Finto” · why startups rename →
Know what your LLM is doing — and why it’s failing
Observability and evaluation platform for LLM apps.
