Clavia is a research lab studying how traces of real work can become training data and learning signals for AI agents. We build evaluations, environments, and post-training tools for domains where frontier model performance remains uneven. We work with AI labs and companies exploring these problems.
Our work
Tardigrade
Tardigrade is a TypeScript framework for building modular agents around a durable event log. The log records every message, model call, tool result, compaction, and handoff.