Agent Sandboxesagentsandboxes.org
Head-to-head

AWS Bedrock AgentCore vs Google Agent Platform Code Execution

Answer in brief

Choose AWS Bedrock AgentCore for teams already on AWS that need IAM- and VPC-integrated code execution for agents; choose Google Agent Platform Code Execution for Google Cloud agents that need stateful, no-network Python execution. AWS Bedrock AgentCore uses MicroVM (Runtime) isolation; Google Agent Platform Code Execution uses gVisor isolation.

By the Agent Sandboxes editors · Updated

Key differences between AWS Bedrock AgentCore and Google Agent Platform Code Execution

  • Isolation: AWS Bedrock AgentCore uses MicroVM (Runtime); Google Agent Platform Code Execution uses gVisor.
  • Session length: Up to 8 h (AWS Bedrock AgentCore) versus 14-day state (Google Agent Platform Code Execution).
  • SDKs and interfaces: Only AWS Bedrock AgentCore lists AWS SDKs and AWS CLI. Only Google Agent Platform Code Execution lists REST API.

What they have in common

  • Both companies are based in the United States.
  • Both are cloud or model provider services.
  • Neither is open source.
  • Both list Python.

AWS Bedrock AgentCore vs Google Agent Platform Code Execution at a glance

AttributeAWS Bedrock AgentCoreGoogle Agent Platform Code Execution
What it isAWS’s managed agent platform: a Code Interpreter tool for running agent-generated code and a Runtime that hosts each agent session in its own microVM.Google-managed sandbox API (the docs also refer to it under Vertex AI Agent Engine) that lets agents deployed anywhere run Python or JavaScript in stateful, network-isolated environments.
TypeCloud or model provider serviceCloud or model provider service
IsolationRuntime: a dedicated microVM per user session with isolated CPU, memory and filesystem, sanitized after the session. Code Interpreter: documented as a containerized environment within AgentCoregVisor-isolated container in a Google-managed tenant project; does not inherit the calling agent’s credentials
Open sourceNoNo
Self-host / BYOCNo / Not documentedNo / No
SDKsPython (AgentCore SDK), AWS SDKs, AWS CLIPython (Agent Platform SDK), REST API
Cold start (vendor claim)No numeric claim; Runtime v2 restores from snapshots for consistent cold startsDocs: create and execute code “in under a second”; a cold provision can take up to 2 minutes
Max sessionCode Interpreter: 15 min default, up to 8 hours. Runtime microVMs: up to 8 hours, stop after 15 min idleState retained up to 14 days (configurable TTL)
PersistenceState persists between executions within a session; Runtime can persist filesystem across stop/resume (managed session storage in preview). Large files via S3Stateful across calls for the TTL; snapshots not supported for Code Execution sandboxes
Snapshots / pauseNot documented / Not documentedNo / Not documented
GPUNot documented for Code Interpreter or Runtime microVMs; the separate Runtime “Instances” compute type is described for agents that need GPUsNot documented
NetworkingCode Interpreter network modes: Sandbox (isolated) or Public; VPC connectivity supportedNo network access from the code execution sandbox; VPC Service Controls supported
PricingCode Interpreter: $0.0895 per vCPU-hour + $0.00945 per GB-hour, billed per second; CPU billed on actual consumption (not during I/O wait), memory on peak$0.085 per vCPU-hour + $0.009 per GiB-hour, rounded to the second
Free tierNo product-specific free tier is listed; general AWS new-customer credits applyNot documented
ComplianceHIPAA eligible and pursuing FedRAMP per the AWS FAQ; AWS reports an internal assessment against programmes including ISO, PCI and SOC, with third-party audits in upcoming cyclesVPC Service Controls, CMEK, data residency at rest and HIPAA per Google’s Agent Platform security table
Regions15 AWS Regions across North America, South America, Europe and Asia PacificNot documented
Company headquartersSeattle, Washington, United StatesMountain View, California, United States
Good fit forTeams already on AWS that need IAM- and VPC-integrated code execution for agentsGoogle Cloud agents that need stateful, no-network Python execution

Verified November 14, 2026 (AWS Bedrock AgentCore) and November 15, 2026 (Google Agent Platform Code Execution) from each provider’s documentation. Cold-start figures are vendor claims, not our measurements.

Which should you choose?

Reasons to choose AWS Bedrock AgentCore

  • You are already on AWS and want IAM, VPC and CloudTrail integration
  • You need long-running sessions (up to 8 hours)
  • You want consumption-based CPU billing that skips I/O wait

Reasons to choose Google Agent Platform Code Execution

  • You want a no-network, gVisor-isolated Python tool
  • You need state that lasts days, not minutes
  • You are on Google Cloud and need CMEK or VPC Service Controls

Trade-offs to check first

  • AWS Bedrock AgentCore: AWS-only; no self-hosting or other clouds
  • AWS Bedrock AgentCore: Code Interpreter isolation is documented only as “containerized”
  • Google Agent Platform Code Execution: Python and JavaScript only, with a fixed library set
  • Google Agent Platform Code Execution: No network access and no snapshots

Both are worth piloting with your own image and region. See the full AWS Bedrock AgentCore profile and Google Agent Platform Code Execution profile, or the complete comparison.

More comparisons

Frequently asked questions

Is AWS Bedrock AgentCore or Google Agent Platform Code Execution better for AI agents?
Neither is better for every workload. AWS Bedrock AgentCore suits teams already on AWS that need IAM- and VPC-integrated code execution for agents. Google Agent Platform Code Execution suits Google Cloud agents that need stateful, no-network Python execution.
What is the difference between AWS Bedrock AgentCore and Google Agent Platform Code Execution?
AWS Bedrock AgentCore uses MicroVM (Runtime); Google Agent Platform Code Execution uses gVisor. Session length: Up to 8 h (AWS Bedrock AgentCore) versus 14-day state (Google Agent Platform Code Execution). Only AWS Bedrock AgentCore lists AWS SDKs and AWS CLI. Only Google Agent Platform Code Execution lists REST API.
Which is open source, AWS Bedrock AgentCore or Google Agent Platform Code Execution?
Neither is open source.
How do AWS Bedrock AgentCore and Google Agent Platform Code Execution isolate code?
AWS Bedrock AgentCore: Runtime: a dedicated microVM per user session with isolated CPU, memory and filesystem, sanitized after the session. Code Interpreter: documented as a containerized environment within AgentCore. Google Agent Platform Code Execution: gVisor-isolated container in a Google-managed tenant project; does not inherit the calling agent’s credentials.
How does AWS Bedrock AgentCore pricing compare with Google Agent Platform Code Execution?
AWS Bedrock AgentCore: Code Interpreter: $0.0895 per vCPU-hour + $0.00945 per GB-hour, billed per second; CPU billed on actual consumption (not during I/O wait), memory on peak. Google Agent Platform Code Execution: $0.085 per vCPU-hour + $0.009 per GiB-hour, rounded to the second. Rates change, so check the AWS Bedrock AgentCore and Google Agent Platform Code Execution pricing pages before deciding.
Can you self-host AWS Bedrock AgentCore or Google Agent Platform Code Execution?
Neither documents a self-hosted option.
How long can sessions run on AWS Bedrock AgentCore and Google Agent Platform Code Execution?
AWS Bedrock AgentCore: Code Interpreter: 15 min default, up to 8 hours. Runtime microVMs: up to 8 hours, stop after 15 min idle. Google Agent Platform Code Execution: State retained up to 14 days (configurable TTL).
Do AWS Bedrock AgentCore and Google Agent Platform Code Execution support snapshots or pause and resume?
AWS Bedrock AgentCore: snapshots not documented, pause and resume not documented. Google Agent Platform Code Execution: snapshots none documented, pause and resume not documented.

Sources

  1. docs.aws.amazon.com/bedrock-agentcore/latest/devguide/code-interpreter-tool.html
  2. docs.aws.amazon.com/bedrock-agentcore/latest/devguide/code-interpreter-resource-session-management.html
  3. docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-how-it-works.html
  4. aws.amazon.com/bedrock/agentcore/pricing/
  5. docs.cloud.google.com/gemini-enterprise-agent-platform/scale/sandbox/code-execution-overview
  6. docs.cloud.google.com/gemini-enterprise-agent-platform/scale/sandbox
  7. cloud.google.com/products/gemini-enterprise-agent-platform/pricing
  8. docs.cloud.google.com/gemini-enterprise-agent-platform/scale

Check before you rely on it. Products change quickly, and this page reflects public documentation as of November 15, 2026. Confirm anything that matters in the provider’s own documentation.

Cite this page

Agent Sandboxes. (2026). AWS Bedrock AgentCore vs Google Agent Platform Code Execution. agentsandboxes.org. Last reviewed November 15, 2026. https://agentsandboxes.org/compare/aws-agentcore-vs-google-code-execution/