Claude Managed Agents on Cloudflare

The self-managed runtime for Claude Managed Agents — sandboxes, egress, custom tools — mapped against Claude Tag's own primitives, and adapted for open models.

overview

• Custom tools: one file, typed, gated — Cloudflare's control plane keeps every custom tool in a single file — `src/tools/custom-tools.ts` — so adding one is a typed code change, not new infrastructure.
• Egress and identity: two products, one pattern — Claude Managed Agents on Cloudflare and Claude Tag arrive at the same design independently: the sandbox never holds a credential, and a boundary proxy attaches one only when a request matches a rule.
• Claude Managed Agents on Cloudflare — The brain runs on Anthropic. The hands — sandboxes, egress, browser, email, custom tools — run on infrastructure you own. Cloudflare ships the control plane as an open-source deployment template: [cloudflare/claude-managed-agents](https://github.com/cloudflare/claude-managed-agents).
• Open models: the same primitives, a different brain — Real Claude Managed Agents needs `ANTHROPIC_API_KEY` and a Workers Paid plan. If your stack can't or won't hold that key, the sandbox / egress / typed-tools shape still stands — only the loop that decides which tool to call next has to move.
• Sandboxes: MicroVM vs. Isolate — Every session gets its own sandbox. Which kind is a per-agent setting, not a global one.