# Langfuse

> Open-source platform for tracing, evaluating and improving LLM apps and agents, with prompt management

Source: https://dontaskagain.com/langfuse
Website: https://langfuse.com/?utm_source=dontaskagain
Pricing: Freemium
Categories: [Observability](https://dontaskagain.com/categories/observability.md), [Evals](https://dontaskagain.com/categories/evals.md), [Open source](https://dontaskagain.com/categories/open-source.md)
Listed: 2026-10-18
Updated: 2026-10-18

Langfuse is an open-source AI engineering platform for tracing, evaluating and improving AI agents and LLM applications. It connects tracing, monitoring, datasets, experiments and evaluation in one loop, so developers can use production data to understand agent behavior and ship fixes.

**Key features:**

- Capture hierarchical traces of every LLM call, tool call and retrieval step with cost and latency.
- Evaluate with LLM-as-a-judge, heuristic functions or human review.
- Version prompts separately from code, with one-click deployments and rollbacks.
- Compare models side by side in a playground on real inputs.
- Build golden datasets through annotation queues and run experiments.
- Track cost, latency and quality in dashboards with alerts.

Langfuse offers Python and JavaScript SDKs, OpenTelemetry support and many framework integrations. It is MIT licensed and free to self-host. Langfuse Cloud has a free Hobby plan with 50k units a month; Core is $29/month, Pro $199/month and Enterprise $2,499/month.

## More observability agents

- [LangSmith](https://dontaskagain.com/langsmith.md): LangChain's platform for tracing, monitoring, evaluating and debugging LLM apps and agents in production
- [Arize](https://dontaskagain.com/arize.md): Observability and evaluation platform that traces agents, runs evals at scale and helps debug and fix them
- [Helicone](https://dontaskagain.com/helicone.md): Open-source LLM gateway and observability platform for routing, debugging and analyzing AI app requests
- [AgentOps](https://dontaskagain.com/agentops.md): Observability SDK for tracing, replaying and debugging AI agent runs across 400+ LLMs and frameworks
- [Braintrust](https://dontaskagain.com/braintrust.md): Platform for tracing agents in production, running evals and turning real traffic into regression tests
- [Galileo](https://dontaskagain.com/galileo.md): Evaluation and observability platform that turns tuned evals into low-cost runtime guardrails for agents