Helicone AI
#1Open-source LLM observability: log, monitor, and optimize AI calls
Helicone is an open-source observability platform that proxies LLM API calls to provide logging, cost tracking, latency metrics, prompt versioning, and caching. It integrates with a one-line code change and supports OpenAI, Anthropic, and Azure. Built for AI teams who need production-grade monitoring without heavy infrastructure.