Langfuse

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

36043 stars · 4026 forks observed · 2026-10-20

What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-28, confidence 0.97

Langfuse is an open‑source platform for tracing, evaluating, and monitoring LLM applications. It provides unified observability, prompt management, and evaluation tools for AI agents.

Use cases

• trace and debug LLM calls and tool invocations in production
• evaluate LLM output quality with automated judges or human review
• manage and version prompts separately from code
• monitor cost, latency, and token usage of AI agents
• run experiments and A/B tests on prompt or model changes

When to choose

• You need end‑to‑end observability for complex LLM agents
• You want a self‑hosted, open‑source alternative to proprietary AI monitoring services
• Your team requires prompt versioning and collaborative editing
• You need built‑in evaluation pipelines for regression testing of LLM outputs

When to avoid

• You only need simple logging without full tracing or evaluation features
• Your deployment environment cannot run Docker or a Node/Python backend
• You prefer a tightly integrated solution within a specific cloud vendor’s AI suite

Facets

service · maturity active

monitoring logging api-framework artificial-intelligence large-language-models monitoring cloud self-hosted cli llm-observability agent-evals prompt-versioning trace-analysis cost-latency-monitoring evaluation prompt-management llmops devops docker web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="langfuse/langfuse")