AWS Bedrock AgentCore
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. The natural default for AWS-centric teams; less attractive if you want portability or a provider-neutral SDK.
Overview
Amazon Bedrock AgentCore is AWS’s set of managed building blocks for production agents. Two pieces matter for sandboxing: the Code Interpreter tool, which runs Python, JavaScript, TypeScript and shell commands for an agent, and the Runtime, which hosts the agent itself with each user session in a dedicated microVM.
Its distinguishing features are long sessions (up to 8 hours), consumption-based CPU billing that does not charge for I/O wait such as waiting on model responses, and native IAM, VPC and regional controls. It is model- and framework-agnostic and supports MCP and A2A.
Notable
- Code Interpreter sessions can run up to 8 hours — long for a hosted code interpreter.
- CPU is not billed while the agent waits on I/O, such as LLM responses.
AWS Bedrock AgentCore specifications
| Attribute | Details |
|---|---|
| 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 |
| Deployment | Cloud provider service |
| Open source | No |
| SDKs and interfaces | Python (AgentCore SDK), AWS SDKs, AWS CLI |
| Cold start (vendor claim) | No numeric claim; Runtime v2 restores from snapshots for consistent cold starts |
| Max session length | Code Interpreter: 15 min default, up to 8 hours. Runtime microVMs: up to 8 hours, stop after 15 min idle |
| Persistence | State persists between executions within a session; Runtime can persist filesystem across stop/resume (managed session storage in preview). Large files via S3 |
| GPU | Not for Code Interpreter or Runtime microVMs; the separate Runtime “Instances” compute type supports GPUs |
| Networking | Code Interpreter network modes: Sandbox (isolated) or Public; VPC connectivity 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 |
| Free tier | No product-specific free tier; general AWS new-customer credits apply |
| Compliance | HIPAA eligible per AWS FAQ; further attestations described as in progress |
| Regions | 15 AWS Regions across North America, South America, Europe and Asia Pacific |
Facts from AWS Bedrock AgentCore’s public documentation, verified November 8, 2026. Performance numbers are vendor claims.
Strengths and trade-offs
Strengths
- 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
Trade-offs
- AWS-only; no self-hosting or other clouds
- Code Interpreter isolation is documented only as “containerized”
- No GPU in Code Interpreter or Runtime microVMs
Best for: Teams already on AWS that need IAM- and VPC-integrated code execution for agents.
Where AWS Bedrock AgentCore ranks
How AWS Bedrock AgentCore compares
| Sandbox | Isolation | Open source | Self-host / BYOC | Cold start (vendor) | Max session | Snapshots / pause | GPU | SDKs |
|---|---|---|---|---|---|---|---|---|
| AWS Bedrock AgentCore | MicroVM (Runtime) | No | No / No | Not documented | Up to 8 h | Not documented / Not documented | No | Python (AgentCore SDK), AWS SDKs, AWS CLI |
| Azure Container Apps dynamic sessions | Hyper-V VM | No | No / No | Sub-second (pooled) | 220 s / exec | No / No | No | REST API, Azure CLI, LangChain, LlamaIndex, Semantic Kernel |
| Google Agent Platform Code Execution | gVisor | No | No / No | <1 s (warm) | 14-day state | No / Not documented | No | Python (Agent Platform SDK), REST API |
| E2B | Firecracker microVM | Yes | Yes / Yes | Not documented | 1 h / 24 h (Pro) | Yes / Yes | No | Python, JavaScript/TypeScript |
| Modal Sandboxes | gVisor or VM | No | No / Not documented | <1 s | Up to 24 h | Yes / Yes | Yes | Python, JavaScript/TypeScript, Go |
Head-to-head: AWS Bedrock AgentCore vs E2B
Frequently asked questions
What is AWS Bedrock AgentCore?
How does AWS Bedrock AgentCore isolate code?
Is AWS Bedrock AgentCore open source?
How much does AWS Bedrock AgentCore cost?
What are the best AWS Bedrock AgentCore alternatives?
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/
- aws.amazon.com/bedrock/agentcore/faqs/
Cite this page
Agent Sandboxes. (2026). AWS Bedrock AgentCore. agentsandboxes.org. Last reviewed November 8, 2026. https://agentsandboxes.org/sandboxes/aws-agentcore/
Found an error or a missing sandbox? Submit a correction — every entry links to the sources it relies on.