Open Source Observability & Analytics for LLM Apps

Detailed production traces and a granular view on quality, cost and latency
Backed by
Star us on Langfuse Github stars
Product Hunt - Product of the Day

Teams building complex LLM apps rely on Langfuse

FastgenLangdockAlphawatchBerryNucleus

Observability

Debug faster

LLM applications are increasingly complex, Langfuse helps to trace & debug them. Understand how changes to one step impact overall application performance.

Made for agents & LLM chains.
Trace unlimited nested actions and get a detailed view of the entire request.
Track non-LLM actions.
Database queries, API calls, and other actions that lead to the response can be tracked for optimal visibility into issues.
Open.
Works with all models and configurations.
Screenshot single trace in Langfuse

Analytics

Metrics for LLM devs

Based on the ingested data, Langfuse provides prebuilt analytics to help teams focus on the most important metrics when improving their LLM app.

Cost.
Track token usage and cost of your LLM application. Drill-down by users, models, or application features.
Quality.
Track user feedback (via Langfuse Web SDK), internal reviews (in the Langfuse UI) and evals to track quality of your LLM application.
Latency.
Monitor and improve latency by getting breakdowns of the added latency of each step of the LLM chain.
More to come.
We currently run a closed alpha with selected users as we build out the analytics features. All users of Langfuse Cloud have early access.
Dashboard Langfuse

Integrations

Integrates with any LLM app

Use the Langchain integration or track your application using the Langfuse Client SDKs.

🦜🔗 Langchain integration
Using Langchain? Get full execution traces in 5 minutes by adding the Langfuse Callback Handler to your app. Learn more →
SDKs for Python & JS/TS
Typed SDKs that capture trace data and send it fully async to Langfuse. You have full control on what is sent to Langfuse. Learn more →
Web SDK
Capture user feedback and other quality scores right from the frontend using the Langfuse Web SDK. Learn more →
API
Need more control? Use the Langfuse API to ingest traces and quality scores. Learn more →

Proudly Open Source

We are committed to open source and Langfuse is easy to run locally and self-hosted.

Pricing

Simple pricing for projects of all sizes

All plans include: unlimited projects and unlimited events (fair use)

Hobby

Get started, no credit card required. Great for hobby and internal projects.

Free

Sign up
  • Unlimited projects & events (fair use)
  • 1 GB of storage
  • Support via Discord and Chat

Starter

More storage and support for projects that move in production.

Starts at$95/month

Sign up
  • Unlimited projects & events (fair use)
  • 10 GB of included storage
  • 1:1 support, Slack Channel, integration help

Pro

Organizational features and security for growing teams.

Starts at$395/month

Sign up
  • Unlimited projects & events (fair use)
  • 30 GB of included storage
  • Dedicated support contact
  • SSO, custom domains, advanced RBAC, and more (soon)

Enterprise

Dedicated solutions and support. Contact founders to learn more. Can include prioritization of your feature requests, self-hosting support (VPS or cloud), dedicated instances, and support SLAs.

Talk to founders