Tools #Anthropic#AI agents Nov 13, 2026 · Originally published Nov 12

Anthropic launches self-hosted Claude Managed Agents: the service, agents, sessions and history live on your own infrastructure, with model calls routable to Bedrock, Google Cloud or Foundry

Until now only the sandboxes could be self-hosted; now the whole Managed Agents service can move into your own cloud account or data center. Who hosts what, when to choose it, and what it costs you.

Primary source Claude Platform release notes · platform.claude.com Read the original ↗

// Key points

  • You host the API, the agent loop, and storage for agents, sessions and session history; model requests go to the provider you choose, Anthropic by default.
  • Supported inference providers include Amazon Bedrock, Claude Models on Google Cloud (Google managed), Microsoft Foundry, or your own model gateway.
  • It exposes the same API as the hosted service, so the SDK and the ant CLI work against your server; the server never runs the agent's shell or file tools, which stay in sandboxes.
  • You run and secure the server, database and sandboxes and install each release yourself, and some features exist only on the hosted service. Access is by request through your Anthropic account team.

Builder's takeThis is for customers whose session history cannot leave their cloud or data center, who until now had to build an agent loop from scratch. I would evaluate it first for the enterprise version of AI Cloud Drive: data stays on our side and model calls go through the customer's existing cloud account. But count the operating cost; if you only need tools to run on your own machines, self-hosted sandboxes are enough.

// Background · from #Anthropic

Full timeline →
  1. Nov 11 Anthropic launches its IPO roadshow: 825 million Class A shares at $70 to $78 each, applying to list on Nasdaq as "ANT"
  2. Nov 10 Anthropic releases Claude Fable 5.2 and Mythos 5.2 at $8 input and $40 output per million tokens, scoring 49.1% on FrontierCode 2.0
  3. Nov 7 AWS runs Claude Code as a remote agent on Bedrock AgentCore: one microVM per task, up to three attempts, and a draft pull request unless verification passes

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →