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 sits in the LLM Infra category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Aggregates agent trajectories from distinct environments. A representative use case is Function calling in LLMs. The listed license is Apache-2.0. GitHub stars are currently 639. Relevant tags include Large Action Models, Function Calling.