AutoRAG

Observal is an AI agent registry with first in class observabilty and eval framework

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

The open source post-building layer for agents. Our environment data and evals power agent post-training (RL, SFT) and monitoring.

Supercharge Your LLM Application Evaluations 🚀