Anthropic 推出自托管版 Claude Managed Agents 私测
做企业级 agent 的开发者该看看这个。Anthropic 把 harness、沙箱和会话记录都开放自托管，模型请求走向也能自己控制，比起纯托管方案，金融、医疗这类对数据落地有要求的团队终于有得选了。
Anthropic 宣布 Self-hosted Claude Managed Agents 进入 private beta 阶段。该方案允许企业把 agent harness、sandboxes 和 session history 部署在自己的云环境或本地服务器上运行。
关键变化在于数据驻留的可控性：企业可以选择对 Claude 模型的请求发往何处，会话历史和沙箱执行环境都留在自有基础设施内，不经第三方托管层。
这类自托管 agent 运行时主要面向对合规和数据隔离有硬性要求的行业，如金融、医疗和政府部门，此前这些团队往往因数据外流问题无法采用托管型 agent 服务。
Self-hosted Claude Managed Agents is now in private beta.
You can host the agent harness, sandboxes, and session history, in your own cloud or on-premises, and choose where requests to Claude are sent. https://t.co/JaiwF1SvKE
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Claude, Anthropic, Managed Agents, 私有化部署.
Source attribution: curated from claudedevs (@claudedevs). Cross-source corroboration: 11 independent sources have covered this development (including 宝玉, Dylan Patel (SemiAnalysis), Aravind Srinivas), confirming industry-wide signal strength.
