Zero-code full-stack observability for AI agents and LLM apps. OpenTelemetry-native monitoring for LLMs, VectorDBs, and GPUs with built-in guardrails, evaluations, prompt hub, and a secure vault. Fully self-hostable anywhere.

OpenLIT adds a drag-and-drop Dashboard Builder for full-control LLM observability. Self-hosted & OpenTelemetry-native, works with any SDK. Monitor cost & accuracy in custom, vendor-neutral views—dashboards fully import/export as JSON.

OpenLIT is an open-source LLM and GPU observability tool built on OpenTelemetry. It offers tracing, metrics, and a playground to debug and improve LLM apps. Supports 20+ integrations like OpenAI, LangChain, and exports data to your existing observability tools

OpenLIT is an open-source, self-hosted tool for developing AI apps. It allows for LLM experimentation, prompt management, secure API key handling, and protection against prompt injection. It also offers OpenTelemetry-native observability for the GenAI stack.