
Langfuse
8.1#1 in ai agent observability toolsFrom $29 a monthFree planWebAPILinuxSelf-hosted
Visit
| Fact | Langfuse | PromptMetrics |
|---|---|---|
| Headquarters | Berlin, Germany; San Francisco, United States | Berlin, Germany |
| Observability | Hierarchical traces capture LLM calls, tool invocations, and retrieval steps, with filtering by user, session, cost, latency, and metadata. | It logs LLM request metadata such as model, tokens, latency, cost, and custom tags, and can export data through OpenTelemetry. |
| SDKs | Official SDKs are Python v5 and JavaScript/TypeScript v6; other languages can use OpenTelemetry instrumentation. | The project lists Node.js and Python SDKs for programmatic access. |
No prices published.
Langfuse suits teams building AI agent applications that need tracing, prompt management, and evaluation tools. It also supports teams that want to self-host the core on their own infrastructure.
It suits developers and teams that need self-hosted prompt versioning, LLM observability, evaluations, and compliance checks. It fits environments using multiple model providers and Git-backed workflows.