Microsoft releases Orchard, a lightweight framework for small-model agentic AI
Orchard provides a reusable Kubernetes‑based environment that lets researchers train and evaluate agents for coding, web navigation, and personal assistance without building custom sandboxes. The open‑source stack lets 3‑billion‑parameter models hit near‑state‑of‑the‑art performance, lowering the cost barrier for agentic AI research.