Anthropic launches self-hosted Claude Managed Agents for customer cloud accounts and on-premises data centers
Anthropic launched self-hosted Claude Managed Agents on November 12, 2026. Customers can run the full service and its sandboxes in their own cloud account or on-premises data center, with agents, sessions and session history stored on that infrastructure.
Anthropic launched self-hosted Claude Managed Agents on November 12, 2026, allowing customers to run the full service and its sandboxes in their own cloud account or on-premises data center, according to Unite.AI.
What is hosted where
Under the new setup, agents, sessions and session history are stored on the customer's infrastructure. Model requests can go to a chosen inference provider.
How it differs from the earlier option
Anthropic's earlier self-hosted sandboxes moved an agent's tool execution onto customer systems, while Anthropic continued running the agent. The new release extends self-hosting from the sandbox to the full Claude Managed Agents service.
What this means
The change moves where agent state lives. With the earlier sandbox option, Anthropic still ran the agent. With the full service self-hosted, agents, sessions and session history sit in the customer's own cloud account or data center. Model requests can be directed to an inference provider the customer selects. For teams that need agent data kept on infrastructure they control, this changes where that data is stored.
Related Articles
Anthropic Launches Claude for Manufacturing, a 17-Skill Plugin for Quoting, Quality and Maintenance
Anthropic launched Claude for Manufacturing on November 12, 2026. The plugin has 17 skills for quoting, quality investigations, production reporting, maintenance diagnosis, sourcing and design. It works from a manufacturer's existing records and sends processes to employee review.
Databricks updates Genie agent to run multi-step business tasks unsupervised, built on a new ontology
Databricks unveiled an updated version of its AI agent Genie, which can now perform multi-step jobs that take extended work to finish. The company says leaders can assign a wide range of tasks and the agent completes them unsupervised. CEO Ali Ghodsi showed TechCrunch how he uses it internally.
VulnCheck: Project Glasswing has 37,966 candidate vulnerabilities, 217 marked fixed in public records
Security firm VulnCheck reports that seven months after launch, Anthropic's Project Glasswing has produced 37,966 candidate vulnerabilities, with 217 marked fixed in public disclosure records. Anthropic's own figures, as of November 2, show 629 upstream patches, and both sides point to human review as the bottleneck.
Claude Fable 5.2 scores 65 on Artificial Analysis index but costs about 2x Opus 5.5 per task
Anthropic announced Claude Fable 5.2, its top model, on November 9 (US time). ITmedia tested it against Opus 5.5 and Sonnet 5.5 on two office tasks and found the best-structured output, at the highest cost.
Comments
Loading...