Anthropic just added scheduled deployments and environment variable vaults to Claude Managed Agents in public beta. Agents can now automatically run recurring tasks on a cron schedule without custom scheduling infrastructure, while the new vaults inject API keys at the network boundary so the AI never sees raw credentials.
Anthropic just announced two enterprise-focused upgrades for Claude Managed Agents at its Code w/ Claude event in London. Self-hosted sandboxes move tool execution to your own infrastructure or cloud providers like Vercel and Cloudflare, keeping sensitive code inside your perimeter. Meanwhile, new MCP tunnels let agents securely reach internal MCP servers without exposing public endpoints. It basically solves one of the biggest security blockers for deploying coding agents in production.
Anthropic just gave Claude Managed Agents two major enterprise upgrades: self-hosted sandboxes and MCP tunnels. You can now keep tool execution, sensitive code, and data entirely inside your own infrastructure or providers like Cloudflare and Modal, while Claude only handles the agent orchestration. MCP tunnels also let agents securely call internal databases without punching holes in corporate firewalls. Self-hosted sandboxes are in public beta, while tunnels require an access request.
Anthropic just gave Claude Managed Agents a major brain boost with "dreaming," a scheduled background process that analyzes past sessions to extract patterns and refine agent memory over time. The update also adds outcomes—letting a separate AI grader score results against a rubric so agents can self-correct—and native multiagent orchestration. In tests, outcomes boosted complex task success rates by up to 10 points.
Anthropic just doubled rate limits for Claude Code and shipped four major upgrades to Claude Managed Agents at its developer conference. The platform now supports parallel multi-agent workflows, automated memory curation called Dreaming, and a built-in rubric grader that boosted success on hard tasks by 10 points.
Anthropic just overhauled the architecture behind Claude Managed Agents, splitting the harness (brain), sandbox (hands), and session logs into independent components. The redesign turns fragile containers into disposable infrastructure, slashing p95 time-to-first-token latency by over 90% while locking credentials away from sandbox code. Why it matters: It gives long-running agents an operating-system-level foundation to recover instantly from crashes and control multiple environments simultaneously.
