◈AI Codex
Agents & Orchestration◆ ClaudeOperatorsDevelopers

Managed Agents

Also: Claude Managed Agents, cloud agents

Managed Agents are agents that Anthropic runs for you through the Claude API. You define the agent once (its model, instructions, tools and skills), then start sessions; Anthropic runs the loop and gives each session its own secure workspace for files, code and browsing. They can run on a schedule, work toward a defined outcome until a grader is satisfied, split work across several agents, and stop at budgets you set. Use them when you want an agent in production without building and hosting the infrastructure yourself.

◎

In practice

You build an agent that drafts weekly status reports. You deploy it through Anthropic's managed infrastructure — it runs on a schedule, Anthropic handles the compute, logging, and uptime, and you just configure what it does. Managed Agents are hosted agents where Anthropic manages the runtime so you don't have to.

Related concepts

Where Managed Agents shows up

5 articles

On September 3, 2026 Anthropic shipped `ant apply` in version 1.30.0 of the ant CLI. It reads agents, environments, skills, memory stores, and scheduled deployments from files in your repository, prints a plan, and reconciles the Claude API against them once you approve. A committed claude-lock.json maps each file to the resource it created. This is the piece that was missing between clicking an agent together in the Console and having one your team can review, diff, and roll back.

Implementation guide·ant apply: your agents, skills, and schedules as files in the repo →·13 min

Managed Agents run Claude on long, multi-step jobs in Anthropic's cloud, so you don't build the infrastructure. You pay normal token rates plus $0.08 per session-hour while an agent runs. Still in beta. Here's who it suits, what it costs and how to start.

Role-Specific·Claude Managed Agents: what they are and when your organization should use them →·5 min

Between August 7 and August 19, 2026, Anthropic shipped a hard spend cap per Managed Agents session, an advisor model the primary thread can consult mid-turn, inference geo pinning, GitHub-loaded Skills, memory stores in self-hosted sandboxes, and a rebuilt session viewer. Taken together, this is the month Managed Agents became something you can put a budget behind.

update·Managed Agents got budgets, an advisor, and geo pinning — the guardrails arrived →·11 min

On September 10, 2026 Anthropic added an `auto` permission policy to Claude Managed Agents. The server evaluates each agent or MCP tool call against the session so far and either runs it, denies it outright, or pauses for your approval. Here is what the three policies do, what `auto` will and will not protect you from, and how to read the new `evaluation` field on the event stream.

update·Managed Agents permission policies: letting the server decide which tool calls run →·11 min

On November 12, 2026 Anthropic released self-hosted Claude Managed Agents in private beta. You run the server (cma-server), a PostgreSQL 16+ database, and the workers. Agents, sessions, history, and credentials stay on your infrastructure, and model calls go to the Claude API, Bedrock, Google Cloud, Microsoft Foundry, or your own gateway. Same API, so the SDK and ant CLI work by changing the base URL. What you gain, the features you lose (Files API, scheduled deployments, webhooks, dreams, prebuilt document skills), and a first session in Docker Compose.

update·Self-hosted Claude Managed Agents: run the whole service, and pick your own model provider →·11 min