In progress — we're building and shipping updates often. More features and insights for LLM evaluation and AI agent observability are on the way.

About TraceDog

TraceDog is an open-source project focused on observability and reliability for LLM-powered agents and RAG systems. We combine trace ingestion, hybrid grounding scores, and a decision-oriented UI so engineers can see why a run looks safe or risky — not just raw logs.

The project is early (V1) and evolving in public with the community.

← Back to home