xLAM

xLAM is a research repository for Large Action Models (LAMs), which aggregates and unifies agent trajectories from diverse environments into a consistent format. It streamlines the creation of a generic data loader optimized for agent training, enabling robust model development across various scenarios.

xLAM is currently grouped under LLM Infra, which makes it easier to evaluate through workflow fit instead of isolated features alone. Based on the available data, it leans most heavily toward Aggregates agent trajectories from distinct environments and Function calling in LLMs. The listed license is APACHE, which is useful when adoption constraints matter. It also shows measurable community traction with 634 GitHub stars.