Claude Managed Agents now on Cloudflare
Cloudflare and Anthropic have announced a deep integration of managed agents with the Cloudflare platform. This builds on the previously announced self-hosted sandbox concept, which separates model logic from code execution environments.
Developers can now run agents in isolated Linux micro-VMs or ultra-lightweight V8 isolates. The latter load in milliseconds and enable scaling to millions of concurrent sessions.
The integration includes built-in tools: Browser Run for browser management, email handling via Cloudflare Email, and secure access to private services through VPC or Mesh without exposing to the open internet. All agent actions are logged, and browser or terminal sessions can be connected in real-time for auditing.
Up next
Pope to present AI document with Anthropic co-founder
The Pope is hosting an Anthropic co-founder to present an AI manifesto. This is historic: the church recognizes algorithms now impact human dignity as profoundly as the industrial revolution. When spiritual leaders discuss neural networks with developers, AI safety is officially beyond just a technical issue.
Related stories
- Anthropic introduces self-hosted sandboxes and MCP tunnels for agents
- Anthropic hands Agent Skills to the foundation behind MCP
- Anthropic’s daily-brief agent treats a failed read as news
- Claude’s SDKs run the click loop, but the browser is yours
- Opus 5.5 costs less and answers old agent code with 400s
- Claude Managed Agents get auto mode and a session viewer
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.