Anthropic announced a public beta of self-hosted environments for Claude Code, allowing organizations to run coding-agent sessions on their own infrastructure rather than Anthropic’s servers. The feature, available to Team and Enterprise customers, lets a session started from the web, mobile, desktop, terminal, or a scheduled routine execute inside an organization’s own network alongside its internal services and security controls. Model inference still runs on Anthropic’s servers, but code execution takes place on the customer’s own infrastructure, letting agents work with private build systems and databases without exposing them to the public internet.
