Langfuse
Open-source LLM engineering platform for agent tracing, prompt management, and evals
Replaces custom scripts and internal glue code for evals, tracing & guardrails workflows.
Dossier overview
Langfuse gives agent teams complete visibility into multi-step tool calls, token costs, latency bottlenecks, and automated evaluation scores—available as cloud or self-hosted open source.
Quickstart
npm i langfuseWhat people say on X
Live feed on X ↗We pull unfiltered builder mentions (praise and complaints) from X on our daily sync. Inspect the live unfiltered stream directly on X right now:
Read latest "Langfuse" mentions on X ↗Best use cases
- Debugging nested multi-agent trajectories and tool failures
- Running LLM-as-a-judge and dataset regressions in CI
- Tracking per-user token spend and model latency
Field notes
Strengths
- OpenTelemetry native ingestion
- Versioned prompt management and playground
- Designed specifically for dev teams / byok
Tradeoffs
- Free/starter tiers have rate or seat limits
- Self-hosting requires managing your own model keys and runtime
Compare with Evals & Tracing alternatives
| Tool | Best for | Runs in | Pricing | Setup |
|---|---|---|---|---|
| Langfuse | Dev teams / BYOK | API / SDK | Freemium | CLI / SDK install |
| Braintrust | Agent builders | API / SDK | Freemium | CLI / SDK install |
| Arize Phoenix | Dev teams / BYOK | API / SDK | Free / OSS | CLI / SDK install |
| Promptfoo | Dev teams / BYOK | CLI · API / SDK | Free / OSS | CLI / SDK install |
| LangSmith | Agent builders | API / SDK | Freemium | API / SDK setup |