Microsoft Research· Baolin Peng, Wenlin Yao, Qianhui Wu, Hao Cheng, Jianfeng Gao·· 2026-08-04
Orchard: An open framework for scalable agentic AI
Orchard: An open framework for scalable agentic AI
AI summary
Microsoft Research released the open-source Orchard framework, centred on the Kubernetes environment service Orchard Env. It reuses environments, data pipelines and evaluation workflows across tasks and supports training agents directly within real deployment frameworks such as Codex, OpenClaw and ZeroClaw.
Selection record
Threshold 60Official, first-handFirst 71Second 71
AdmittedSum of both 142 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：开源智能体AI框架与训练评测
- Why it was chosen
- The open-source environment service, training workflow and data explain how small models can be trained inside real deployment frameworks.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Microsoft Research · microsoft.com