Agent Sandboxesagentsandboxes.org
Sandbox profile · Cloud or model provider service

Claude Managed Agents

Answer in brief

Anthropic's hosted agent harness: each session runs Claude in its own Anthropic-managed Linux container, or sends tool calls to a sandbox you run through a worker. Anthropic's managed agent runtime with a per-session container, for teams that want the agent loop and sandbox run for them rather than a raw sandbox API.

By the Agent Sandboxes editors · Updated

Overview

Claude Managed Agents is Anthropic's managed agent harness, in beta behind the managed-agents-2026-04-01 header. You define an agent (model, system prompt, tools, MCP servers, skills), an environment, and then start sessions and exchange events over server-sent events. In a cloud environment each session gets its own fresh Linux container on Anthropic-managed infrastructure: Ubuntu 24.04 on x86_64 with up to 8 GB of memory and 10 GB of disk, preinstalled Python, Node.js, Go, Rust, Java, Ruby, PHP and C/C++ toolchains, PostgreSQL and Redis, and Playwright with Chromium. Networking is limited to an allowlist or unrestricted, and environments can install apt, cargo, gem, go, npm and pip packages before the agent starts. Built-in tools are bash, file operations, web search and fetch, and MCP servers.

This differs from the Claude code execution tool, which is a single server-side tool added to one Messages API request: its container has 1 CPU and 5 GiB of RAM, no internet access, and is billed per container-hour. Managed Agents instead runs the whole agent loop server-side for minutes or hours, with network access, idle checkpoints of the sandbox and billing of $0.08 per session-hour while running, in place of container-hours. Tool calls can also run in a self-hosted sandbox, where a worker on your infrastructure (prebuilt in the ant CLI and the Python, TypeScript and Go SDKs) claims work and runs bash and file calls locally; Anthropic's docs list guides from sandbox providers including E2B, Daytona, Modal, Cloudflare and Vercel. Running the whole service on your own infrastructure (self-hosted Managed Agents) is available by contacting the Anthropic account team. Maximum session length, boot time and GPU support are not documented.

Notable

  • Session runtime is $0.08 per hour, metered to the millisecond only while a session is running, and replaces code execution container-hour billing.
  • Idle sessions have their sandbox checkpointed; sandbox state is kept for 30 days from creation regardless of activity.
  • Anthropic's docs list self-hosted sandbox guides from E2B, Daytona, Modal, Cloudflare, Vercel, Fly.io, Blaxel and others.

Claude Managed Agents specifications

AttributeDetails
IsolationCloud environments: an isolated Linux container per session on Anthropic-managed infrastructure (the container runtime is not named). Self-hosted sandboxes: bash and file tool calls run wherever your worker runs them, with isolation set by you
DeploymentCloud or model provider service · BYOC available · Self-hostable
Open sourceNo
SDKs and interfacesPython, JavaScript/TypeScript, Go, Java, C#, PHP, Ruby, REST API, CLI
Cold start (vendor claim)Not documented
Max session lengthNot documented
PersistenceConversation history is kept until you delete the session. When a session goes idle the service checkpoints its sandbox, including the filesystem, installed packages and files the agent created; sandbox state is kept for 30 days from sandbox creation, after which a resumed session starts from a fresh sandbox. Memory stores mount at /mnt/memory/ and deliverables go to /mnt/session/outputs
GPUNot documented; cloud sandboxes run Ubuntu 24.04 on x86_64 with up to 8 GB of memory and up to 10 GB of disk
NetworkingSet per environment: limited allows only hosts in allowed_hosts, plus optional package-manager hosts and the agent's MCP servers; unrestricted allows any host except a general safety blocklist. API create requests that omit the field get unrestricted; the Console form starts at Limited. With self-hosted sandboxes, network policy is yours
PricingTokens at standard model rates (prompt caching multipliers apply; web search $10 per 1,000 searches) plus $0.08 per session-hour, metered to the millisecond only while the session is running; idle, rescheduling and terminated time is not billed. Session runtime replaces code execution container-hour billing. Self-hosted Managed Agents: pricing through the Anthropic account team
Free tierNot documented
ComplianceNot eligible for zero data retention (except self-hosted Managed Agents) or HIPAA BAA coverage; sessions are stored server-side until deleted
RegionsBeta on the Claude API, Claude Platform on AWS and Claude Models on Google Cloud (Anthropic managed); no sandbox region selection documented. An agent's model.inference_geo can pin inference to the US at 1.1x token rates
Company headquartersSan Francisco, California, United States · More from the United States

Facts from Claude Managed Agents’s public documentation, verified November 18, 2026. Performance numbers are vendor claims.

Strengths and trade-offs

Strengths

  • You want Anthropic to run the agent loop, context management and sandbox for long-running Claude tasks.
  • You need a sandbox with network access and preinstalled toolchains, controlled by a host allowlist.
  • You want to keep files and processes on your own infrastructure while Anthropic runs the agent, via self-hosted sandboxes.
  • You want runtime billed only while the agent is actively working.

Trade-offs

  • Beta, and tied to Claude models; it is not a general-purpose sandbox API for your own code.
  • Not eligible for zero data retention (except self-hosted Managed Agents) or HIPAA coverage.
  • Maximum session length, boot time, user-triggered snapshots and GPU support are not documented.
  • API-created environments default to unrestricted networking unless you set limited.

Good fit for: Long-running Claude agents that need a managed sandbox with network access and persistent session state, without building an agent loop.

How Claude Managed Agents compares

SandboxCompany HQIsolationOpen sourceSelf-host / BYOCCold start (vendor)Max sessionSnapshots / pauseGPUSDKs
Claude Managed AgentsUnited StatesHosted Linux containerNoYes / YesNot documentedNot documentedNot documented / Not documentedNot documentedPython, JavaScript/TypeScript, Go, Java, C#, PHP, Ruby, REST API, CLI
Claude code execution toolUnited StatesHosted Linux containerNoNo / NoNot documented30 days (container)Not documented / Not documentedNot documentedPython, JavaScript/TypeScript, Go, Java, C#, PHP, Ruby, REST API, CLI
AWS Bedrock AgentCoreUnited StatesMicroVM (Runtime)NoNo / Not documentedNot documentedUp to 8 hNot documented / Not documentedNot documentedPython (AgentCore SDK), AWS SDKs, AWS CLI
OpenAI Code Interpreter & Hosted ShellUnited StatesVM (unspecified)NoNo / NoNot documented20 min idleNot documented / NoNot documentedOpenAI Responses API, Containers API, OpenAI SDKs
E2BUnited StatesFirecracker microVMYesYes / YesNot documented1 h / 24 h (Pro)Yes / YesNoPython, JavaScript/TypeScript
DaytonaUnited StatesContainers or VMsNoNot documented / Yes<90 msUnlimitedYes / YesYesPython, TypeScript, Ruby, Go, Java
Kubernetes Agent SandboxNot documentedgVisor or KataYesYes / Yes<1 s (warm pool)Not documentedYes / YesYesKubernetes CRDs, Python, kubectl

Head-to-head: Claude code execution tool vs Claude Managed Agents

See all Claude Managed Agents alternatives →

Frequently asked questions

What is Claude Managed Agents?
Anthropic's hosted agent harness: each session runs Claude in its own Anthropic-managed Linux container, or sends tool calls to a sandbox you run through a worker. Anthropic's managed agent runtime with a per-session container, for teams that want the agent loop and sandbox run for them rather than a raw sandbox API.
How does Claude Managed Agents isolate code?
Claude Managed Agents documents its isolation as: Cloud environments: an isolated Linux container per session on Anthropic-managed infrastructure (the container runtime is not named). Self-hosted sandboxes: bash and file tool calls run wherever your worker runs them, with isolation set by you.
Is Claude Managed Agents open source?
No, Claude Managed Agents is not open source. It does offer a bring-your-own-cloud deployment.
How much does Claude Managed Agents cost?
Tokens at standard model rates (prompt caching multipliers apply; web search $10 per 1,000 searches) plus $0.08 per session-hour, metered to the millisecond only while the session is running; idle, rescheduling and terminated time is not billed. Session runtime replaces code execution container-hour billing. Self-hosted Managed Agents: pricing through the Anthropic account team Check the official pricing page for current rates.
Can you self-host Claude Managed Agents?
Yes, Claude Managed Agents can be self-hosted. It also offers a bring-your-own-cloud deployment.
Which regions does Claude Managed Agents run in?
Beta on the Claude API, Claude Platform on AWS and Claude Models on Google Cloud (Anthropic managed); no sandbox region selection documented. An agent's model.inference_geo can pin inference to the US at 1.1x token rates.
What compliance certifications does Claude Managed Agents have?
Not eligible for zero data retention (except self-hosted Managed Agents) or HIPAA BAA coverage; sessions are stored server-side until deleted.
Where is Anthropic based?
Anthropic, the organisation behind Claude Managed Agents, is headquartered in San Francisco, California, United States. That is where the company is based, not where sandboxes run; for that, see the regions listed for Claude Managed Agents.
What are the alternatives to Claude Managed Agents?

Sources

  1. platform.claude.com/docs/en/managed-agents/overview
  2. platform.claude.com/docs/en/managed-agents/choosing-an-environment
  3. platform.claude.com/docs/en/managed-agents/environments
  4. platform.claude.com/docs/en/managed-agents/cloud-sandboxes-reference
  5. platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes
  6. platform.claude.com/docs/en/managed-agents/self-hosted
  7. platform.claude.com/docs/en/managed-agents/events-and-streaming
  8. platform.claude.com/docs/en/managed-agents/session-operations
  9. platform.claude.com/docs/en/about-claude/pricing
  10. platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool
  11. anthropic.com/legal/privacy

Check before you rely on it. Products change quickly, and this page reflects public documentation as of November 18, 2026. Confirm anything that matters in the provider’s own documentation.

Cite this page

Agent Sandboxes. (2026). Claude Managed Agents. agentsandboxes.org. Last reviewed November 18, 2026. https://agentsandboxes.org/sandboxes/claude-managed-agents/