[{"data":1,"prerenderedAt":14},["ShallowReactive",2],{"artikel-en-berita-anthropic-managed-agents-self-hosted":3},{"slug":4,"lang":5,"title":6,"description":7,"date":8,"updated":9,"topic":10,"product":9,"cover":11,"readMin":12,"html":13},"berita-anthropic-managed-agents-self-hosted","en","Anthropic lets companies run AI agents on their own servers","Anthropic launched Self-hosted Claude Managed Agents in private beta, so AI agents, credentials and session history can stay inside a company's own infrastructure.","2026-11-15",null,"berita","\u002Fimages\u002Fartikel\u002Fberita-anthropic-managed-agents-self-hosted.webp",3,"\u003Cp>AI agents have started doing important work without supervision: fixing broken builds, testing releases and triaging internal alerts. Until now, all of their records and credentials lived on Anthropic&#39;s servers. On 12 November 2026, Anthropic opened a new option called Self-hosted Claude Managed Agents in private beta, letting companies run the whole service in their own cloud or on their own hardware.\u003C\u002Fp>\n\u003Ch2>1. What was launched\u003C\u002Fh2>\n\u003Cp>Managed Agents is a set of APIs for building and running autonomous AI agents. It provides four things: the agent harness, the sandbox where agent code runs, credential handling, and session history.\u003C\u002Fp>\n\u003Cp>From 12 November, all four can run inside a company&#39;s own environment. This is a private beta: companies request access through their Anthropic account team. No pricing has been announced.\u003C\u002Fp>\n\u003Ch2>2. What the customer runs\u003C\u002Fh2>\n\u003Cp>In the self-hosted setup, the customer operates three components: the Managed Agents server, a PostgreSQL database that stores session history, and the workers where agents run their shell and file tools.\u003C\u002Fp>\n\u003Cp>The Claude model itself still runs outside the customer&#39;s network. Model requests go wherever the customer points them: directly to Anthropic, to Amazon Bedrock, Google&#39;s Agent Platform, Microsoft Foundry, or the company&#39;s own gateway. Developers use the same core APIs as the hosted version, so existing agents do not need a rewrite.\u003C\u002Fp>\n\u003Ch2>3. Security built into the system\u003C\u002Fh2>\n\u003Cp>Anthropic argues that an unattended agent cannot rely on a person checking every step, so the limits have to be built into the system itself. It uses four principles:\u003C\u002Fp>\n\u003Col>\n\u003Cli>The harness, which calls Claude, is kept separate from the sandbox where agent code runs.\u003C\u002Fli>\n\u003Cli>Credentials stay out of the sandbox. A proxy outside the sandbox attaches the credential to each request, and self-hosted customers can keep credentials in their own secrets manager.\u003C\u002Fli>\n\u003Cli>Each environment can be locked to a list of allowed hosts. Requests to any other host are blocked.\u003C\u002Fli>\n\u003Cli>Every step an agent takes is logged, including tool calls and their results, and the log exports over OpenTelemetry into existing monitoring tools.\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cfigure>\n  \u003Cimg src=\"\u002Fimages\u002Fartikel\u002Fberita-anthropic-managed-agents-self-hosted\u002Fmanaged-agents-keselamatan.webp\" alt=\"Official Anthropic illustration for Self-hosted Claude Managed Agents, a laptop with a keyhole symbol\" loading=\"lazy\" decoding=\"async\" width=\"950\" height=\"369\">\n  \u003Cfigcaption>Anthropic's official illustration for Self-hosted Claude Managed Agents, highlighting security. Image: Anthropic.\u003C\u002Ffigcaption>\n\u003C\u002Ffigure>\u003Ch2>4. Why it matters\u003C\u002Fh2>\n\u003Cp>Banks, hospitals and defense companies have hesitated to allow AI agents because data and credentials would have to leave their perimeter. With self-hosting, session history and credentials stay on their own servers, while model requests remain covered by a zero data retention agreement if one is in place.\u003C\u002Fp>\n\u003Cp>Anthropic launched Managed Agents as a hosted service in April, then added self-hosted sandboxes in May. This release completes the set: fully hosted, customer-hosted sandboxes, and now fully self-hosted.\u003C\u002Fp>\n\u003Cp>The New Stack also highlighted a detail in the software license: if Anthropic flags a security risk in software a customer runs, the customer has eight hours to act. Even on the customer&#39;s own servers, Anthropic keeps some control.\u003C\u002Fp>\n\u003Ch2>What it means for you\u003C\u002Fh2>\n\u003Cp>If you work at a company with strict data rules, this is more than another product launch.\u003C\u002Fp>\n\u003Col>\n\u003Cli>\u003Cstrong>Large companies have a new option.\u003C\u002Fstrong> IT teams that previously rejected AI agents over data concerns can evaluate this beta through their Anthropic account team.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Operational costs shift to you.\u003C\u002Fstrong> The server, database and firewall rules are now the customer&#39;s responsibility to patch and maintain.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>No pricing yet.\u003C\u002Fstrong> Do not budget for it; Anthropic has not announced pricing for the self-hosted option.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Vendor control remains.\u003C\u002Fstrong> The eight-hour response requirement for flagged security risks means you should read the license terms before signing.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Regular users are unaffected.\u003C\u002Fstrong> Everyday Claude users need to do nothing; this is for companies running autonomous agents on internal systems.\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Ch2>Sources\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Ca href=\"https:\u002F\u002Fclaude.com\u002Fresources\u002Farticles\u002Fself-hosted-claude-managed-agents\" target=\"_blank\" rel=\"noopener\">Operate Claude Managed Agents inside your security perimeter\u003C\u002Fa> (Anthropic)\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"https:\u002F\u002Fwww.helpnetsecurity.com\u002F2026\u002F11\u002F12\u002Fanthropic-self-hosted-claude-managed-agents\u002F\" target=\"_blank\" rel=\"noopener\">Self-hosted Claude Managed Agents keeps agent credentials in your environment\u003C\u002Fa> (Help Net Security)\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"https:\u002F\u002Fthenewstack.io\u002Fself-hosted-claude-managed-agents\u002F\" target=\"_blank\" rel=\"noopener\">Anthropic now lets you self-host Claude Managed Agents\u003C\u002Fa> (The New Stack)\u003C\u002Fli>\n\u003C\u002Ful>\n",1795068892573]