emisar: emisar enables MCP-capable agents to perform declared infrastructure actions securely on remote hosts, governed by strict policy. It provides a control plane and an outbound-only runner that enforces execution limits and ensures audited, safe interaction with production systems.; 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.
Enabling AI/LLM agents to securely perform infrastructure actions.
Function calling in LLMs