langfuse-observability

SKILL.md

Langfuse is the open-source LLM observability platform that OrchestKit uses for tracing, monitoring, evaluation, and prompt management. Unlike LangSmith (deprecated), Langfuse is self-hosted, free, and designed for production LLM applications.

| Distributed Tracing | Track LLM calls with parent-child spans | references/tracing-setup.md | | Cost Tracking | Automatic token & cost calculation | references/cost-tracking.md | | Prompt Management | Version control for prompts | references/prompt-management.md | | LLM Evaluation | Custom scoring with G-Eval | references/evaluation-scores.md |

| Session Tracking | Group related traces | references/session-tracking.md | | Experiments API | A/B testing & benchmarks | references/experiments-api.md | | Multi-Judge Eval | Ensemble LLM evaluation | references/multi-judge-evaluation.md |

LLM observability platform for tracing, evaluation, prompt management, and cost tracking. Use when setting up Langfuse, monitoring LLM costs, tracking token usage, or implementing prompt versioning. Source: yonatangross/orchestkit.

View raw