AWS Bedrock AgentCore vs Google Agent Platform Code Execution
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.
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
| Attribute | AWS Bedrock AgentCore | Google Agent Platform Code Execution |
|---|---|---|
| What it is | AWS’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. |
| Type | Cloud or model provider service | Cloud or model provider service |
| Isolation | 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 | gVisor-isolated container in a Google-managed tenant project; does not inherit the calling agent’s credentials |
| Open source | No | No |
| Self-host / BYOC | No / Not documented | No / No |
| SDKs | Python (AgentCore SDK), AWS SDKs, AWS CLI | Python (Agent Platform SDK), REST API |
| Cold start (vendor claim) | No numeric claim; Runtime v2 restores from snapshots for consistent cold starts | Docs: create and execute code “in under a second”; a cold provision can take up to 2 minutes |
| Max session | Code Interpreter: 15 min default, up to 8 hours. Runtime microVMs: up to 8 hours, stop after 15 min idle | State retained up to 14 days (configurable TTL) |
| Persistence | State persists between executions within a session; Runtime can persist filesystem across stop/resume (managed session storage in preview). Large files via S3 | Stateful across calls for the TTL; snapshots not supported for Code Execution sandboxes |
| Snapshots / pause | Not documented / Not documented | No / Not documented |
| GPU | Not documented for Code Interpreter or Runtime microVMs; the separate Runtime “Instances” compute type is described for agents that need GPUs | Not documented |
| Networking | Code Interpreter network modes: Sandbox (isolated) or Public; VPC connectivity supported | No network access from the code execution sandbox; VPC Service Controls supported |
| Pricing | 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 | $0.085 per vCPU-hour + $0.009 per GiB-hour, rounded to the second |
| Free tier | No product-specific free tier is listed; general AWS new-customer credits apply | Not documented |
| Compliance | HIPAA 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 cycles | VPC Service Controls, CMEK, data residency at rest and HIPAA per Google’s Agent Platform security table |
| Regions | 15 AWS Regions across North America, South America, Europe and Asia Pacific | Not documented |
| Company headquarters | Seattle, Washington, United States | Mountain View, California, United States |
| Good fit for | Teams already on AWS that need IAM- and VPC-integrated code execution for agents | Google 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
- AWS Bedrock AgentCore vs E2B
- AWS Bedrock AgentCore vs Azure Container Apps dynamic sessions
- AgentBay vs AWS Bedrock AgentCore
- AWS Bedrock AgentCore vs DigitalOcean Harness Runtime
- Azure Container Apps dynamic sessions vs Google Agent Platform Code Execution
- Google Agent Platform Code Execution vs OpenAI Code Interpreter & Hosted Shell
Frequently asked questions
Is AWS Bedrock AgentCore or Google Agent Platform Code Execution better for AI agents?
What is the difference between AWS Bedrock AgentCore and Google Agent Platform Code Execution?
Which is open source, AWS Bedrock AgentCore or Google Agent Platform Code Execution?
How do AWS Bedrock AgentCore and Google Agent Platform Code Execution isolate code?
How does AWS Bedrock AgentCore pricing compare with Google Agent Platform Code Execution?
Can you self-host AWS Bedrock AgentCore or Google Agent Platform Code Execution?
How long can sessions run on AWS Bedrock AgentCore and Google Agent Platform Code Execution?
Do AWS Bedrock AgentCore and Google Agent Platform Code Execution support snapshots or pause and resume?
Sources
- docs.aws.amazon.com/bedrock-agentcore/latest/devguide/code-interpreter-tool.html
- docs.aws.amazon.com/bedrock-agentcore/latest/devguide/code-interpreter-resource-session-management.html
- docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-how-it-works.html
- aws.amazon.com/bedrock/agentcore/pricing/
- docs.cloud.google.com/gemini-enterprise-agent-platform/scale/sandbox/code-execution-overview
- docs.cloud.google.com/gemini-enterprise-agent-platform/scale/sandbox
- cloud.google.com/products/gemini-enterprise-agent-platform/pricing
- 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/