Microsoft open-sources Orchard to cut AI agent training costs
The Kubernetes-based framework reuses sandboxes, datasets and training pipelines across coding, browser and assistant agents.
By Ryan Merket · Published
Primary source: Microsoft Research on X
Why it matters
Orchard makes a costly layer of agent training available as open-source infrastructure, giving startups and labs a self-hosted alternative to managed sandbox vendors.
Microsoft Research said in an August 3rd post on X that it has released Orchard, an MIT-licensed framework for training and evaluating AI agents across coding, browser navigation and personal-assistant tasks. The project targets a costly problem behind agent development: researchers repeatedly building sandbox infrastructure, data pipelines and evaluation systems for each model and use case.
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.