Claude Managed Agents at a glance
Self-hosted Claude Managed Agents, in private beta from November 12, 2026, lets businesses run the full Managed Agents service — harness, sandboxes, credentials and session history — in their own cloud or on-premises, routing model calls where they choose.
Ask your AI about this story
Use this story in your business: Anthropic opens self-hosted Claude Managed Agents in private beta: run agents inside your own cloud (Anthropic). Ask your AI to explain what happened, how it could affect your business and how to put it to work. It also weighs price, speed, intelligence and the lab behind it. The link to the story is included.
What changed with Claude Managed Agents
Anthropic opened self-hosted Claude Managed Agents in private beta on November 12, 2026. Managed Agents is Anthropic's suite of composable APIs for building and deploying autonomous agents, until now run as a hosted service on the Claude Platform, with self-hosted sandboxes added later for teams whose code had to stay in their own environment. With self-hosting, every part of the service runs in the customer's own cloud or on-premises — the harness, the sandboxes, credential handling and session history — while developers keep building agents with the same core APIs as the hosted service.
The customer operates the Managed Agents server, its database and the workers where agents run their shell and file tools, and session history is stored in that database. Model requests go where the customer chooses: to Anthropic directly, to a cloud provider (Amazon Bedrock, Google's Agent Platform or Microsoft Foundry), or through the customer's own gateway, and an existing zero data retention agreement applies to requests sent to Claude as it does to any Messages API call. The design keeps the agent loop and vault secrets outside the sandbox, lets credentials live in the customer's own secrets manager, allows network access to be limited to an allowlist of hosts, and records every session for export over OpenTelemetry. Access is by request through an Anthropic account team.
Why Claude Managed Agents matters for businesses
Why it matters: agents that fix broken builds, test releases and triage alerts run unattended inside a company's systems, and many businesses could not adopt them while the agent control plane sat outside their own perimeter. Self-hosted Claude Managed Agents removes that blocker: your team runs the service where your code and credentials already live, chooses where model calls go, and can audit every session — a deployment pattern agencies can now offer to regulated or security-sensitive clients.
Put it to work: AI Agents
Get AI News by email
Verified AI stories, each with its official source, on Monday and Thursday mornings. Add breaking news to hear about the biggest ones as soon as we publish them.
Every story links its official source
Free, in English or Spanish
Unsubscribe with one click, any time
Sources for this story
- Operate Claude Managed Agents inside your security perimeter (opens in a new tab)Official
Anthropic · claude.com
Last verified: . IA Compa summarizes public announcements for business readers. We are not affiliated with the companies mentioned. Always confirm details, pricing, and availability with the official source.
- #claude-managed-agents
- #self-hosted-agents
- #private-beta
- #agent-infrastructure
- #amazon-bedrock
- #microsoft-foundry
- #enterprise-ai