清华团队开源 PilotDeck 2.0，办公 Agent 跑赢 Claude Code
OpenBMB 开源的 Agent 系统，Word/Excel/PPT 的活能直接干完，基准分还压过 Claude Code，模型随便换。
PilotDeck 2.0 由清华 THUNLP、ModelBest、OpenBMB 和 AI9Stars 联合开发，是一个开源、模型无关的 Agent 系统。新版能端到端创建、编辑并校验 Word、Excel 和 PowerPoint 文件，而不只是生成草稿。复杂长任务经过 2,000 条交互消息压测，支持中断后继续执行。在 Workbuddy Bench 上，搭配 Qwen3.6-35B-A3B 得分 79.1，高于 WorkBuddy 的 74.7 和 Claude Code 的 77.3。产品提供一键桌面安装，数据流向对用户完全可见。
🚀 PilotDeck 2.0 is here!
Meet the open-source AI Agent Harness built to get complex work done. Developed by Tsinghua THUNLP, @modelbest_ai, @OpenBMB , and AI9Stars, PilotDeck is a model-agnostic Agent operating system that turns natural language instructions into completed tasks — with transparent data flows and the freedom to choose your models.
What’s new in 2.0?
📄 End-to-end office work: Create, edit, and verify Word, Excel, and PowerPoint files — not just generate drafts.
🔄 More reliable execution: complex, long-running tasks going through interruptions. Stress-tested with 2,000 interaction messages.
🛠️ Easy to get started: One-click desktop installation and a streamlined setup flow to connect your model and create your workspace.
🔓 Open by design: Fully open-source, model-agnostic, with data flows visible to users.
On Workbuddy Bench, PilotDeck scored 79.1 with Qwen3.6-35B-A3B, outperforming WorkBuddy (74.7) and Claude Code (77.3).
Build your own AI workspace for the Agent era.
🔗 GitHub: https://t.co/kAzhy09NWg Web: https://t.co/VKiK2qp0An
