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.
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
| Attribute | Details |
|---|---|
| Isolation | 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 |
| Deployment | Cloud or model provider service · BYOC available · Self-hostable |
| Open source | No |
| SDKs and interfaces | Python, JavaScript/TypeScript, Go, Java, C#, PHP, Ruby, REST API, CLI |
| Cold start (vendor claim) | Not documented |
| Max session length | Not documented |
| Persistence | Conversation 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 |
| GPU | Not documented; cloud sandboxes run Ubuntu 24.04 on x86_64 with up to 8 GB of memory and up to 10 GB of disk |
| Networking | Set 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 |
| Pricing | 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 |
| Free tier | Not documented |
| Compliance | Not eligible for zero data retention (except self-hosted Managed Agents) or HIPAA BAA coverage; sessions are stored server-side until deleted |
| Regions | 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 |
| Company headquarters | San 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
unrestrictednetworking unless you setlimited.
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
| Sandbox | Company HQ | Isolation | Open source | Self-host / BYOC | Cold start (vendor) | Max session | Snapshots / pause | GPU | SDKs |
|---|---|---|---|---|---|---|---|---|---|
| Claude Managed Agents | United States | Hosted Linux container | No | Yes / Yes | Not documented | Not documented | Not documented / Not documented | Not documented | Python, JavaScript/TypeScript, Go, Java, C#, PHP, Ruby, REST API, CLI |
| Claude code execution tool | United States | Hosted Linux container | No | No / No | Not documented | 30 days (container) | Not documented / Not documented | Not documented | Python, JavaScript/TypeScript, Go, Java, C#, PHP, Ruby, REST API, CLI |
| AWS Bedrock AgentCore | United States | MicroVM (Runtime) | No | No / Not documented | Not documented | Up to 8 h | Not documented / Not documented | Not documented | Python (AgentCore SDK), AWS SDKs, AWS CLI |
| OpenAI Code Interpreter & Hosted Shell | United States | VM (unspecified) | No | No / No | Not documented | 20 min idle | Not documented / No | Not documented | OpenAI Responses API, Containers API, OpenAI SDKs |
| E2B | United States | Firecracker microVM | Yes | Yes / Yes | Not documented | 1 h / 24 h (Pro) | Yes / Yes | No | Python, JavaScript/TypeScript |
| Daytona | United States | Containers or VMs | No | Not documented / Yes | <90 ms | Unlimited | Yes / Yes | Yes | Python, TypeScript, Ruby, Go, Java |
| Kubernetes Agent Sandbox | Not documented | gVisor or Kata | Yes | Yes / Yes | <1 s (warm pool) | Not documented | Yes / Yes | Yes | Kubernetes CRDs, Python, kubectl |
Head-to-head: Claude code execution tool vs Claude Managed Agents
Frequently asked questions
What is Claude Managed Agents?
How does Claude Managed Agents isolate code?
Is Claude Managed Agents open source?
How much does Claude Managed Agents cost?
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?
Which regions does Claude Managed Agents run in?
What compliance certifications does Claude Managed Agents have?
Where is Anthropic based?
What are the alternatives to Claude Managed Agents?
Sources
- platform.claude.com/docs/en/managed-agents/overview
- platform.claude.com/docs/en/managed-agents/choosing-an-environment
- platform.claude.com/docs/en/managed-agents/environments
- platform.claude.com/docs/en/managed-agents/cloud-sandboxes-reference
- platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes
- platform.claude.com/docs/en/managed-agents/self-hosted
- platform.claude.com/docs/en/managed-agents/events-and-streaming
- platform.claude.com/docs/en/managed-agents/session-operations
- platform.claude.com/docs/en/about-claude/pricing
- platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool
- 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/