Head to head · Code sandboxes · October 2026 research run

Amazon Bedrock AgentCore Code Interpreter vs Docker Sandboxes

Amazon Bedrock AgentCore Code Interpreter scores 72.4 (BB) on agent readiness against Docker Sandboxes's 62.1 (B), and leads in 3 of 7 scored categories. Docker Sandboxes leads on schema & documentation, agent ergonomics and maintenance & community. Both do code sandboxes.

Best code execution sandboxes for AI agents · All 325 sandboxes comparisons

Which one, for what

Amazon Bedrock AgentCore Code Interpreter BB

Best for A team already on AWS that wants agent code to run under IAM, inside a VPC and beside S3 data, for sessions up to eight hours.

Ahead on

  • Reliability, 85 against 45
  • Security & auth, 87 against 69
  • Payments & pricing, 45 against 0

Also in its favour

  • Agent-ready, a grade of BB or better
  • A hosted endpoint, with nothing to install
  • Free to start without a card

Watch for

No pause, resume or snapshot. Session files are removed when the session ends, and persistence needs a customer-owned S3 Files or EFS mount inside a VPC

Docker Sandboxes B

Best for Running coding agents such as Claude Code or Codex in a disposable cloud VM, or the same kit locally for free.

Ahead on

  • Schema & documentation, 90 against 81
  • Agent ergonomics, 83 against 75
  • Maintenance & community, 71 against 55

Watch for

Docker Agentic Platform, needed for every cloud interface, is experimental, and no SLA was found

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing Amazon Bedrock AgentCore Code Interpreter +45

Amazon Bedrock AgentCore Code Interpreter 45

No x402, MPP or L402 on the Code Interpreter endpoints. AgentCore Payments is a separate component for an agent paying third parties (0). Per-unit prices published without a login, $0.0895 a vCPU-hour and $0.00945 a GB-hour (20). No allowance for Code Interpreter, but the pricing page says new AWS customers get up to $200 in Free Tier credits and the Free Tier FAQ says most new customers need no payment method, so half, as on the other AWS listings (10). A person signs up in a browser and sets up IAM (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Docker Sandboxes 0

No x402, MPP or L402 (0). Compute is metered per second by size, but neither the docs, the Docker Sandboxes product page nor docker.com/pricing publishes a unit price. The plans page says usage and pricing show on the Usage & billing page after sign-in (0). Signup to Docker Agentic Platform asks for billing and payment details at checkout, with a one-time promotional credit after, so there is no card-free start for cloud sandboxes (0). A person subscribes in a browser and creates the access token (0). The free local sbx CLI is not the graded surface. 0+0+0+0 = 0.

Reliability Amazon Bedrock AgentCore Code Interpreter +40

Amazon Bedrock AgentCore Code Interpreter 85

Graded on the hosted lines, for the AWS API. AWS Health Dashboard with per-service, per-Region history (20). The dashboard history file, read on 17 October, names AgentCore in one event in the 90 days, elevated packet loss in one availability zone of Europe (Spain) for 2 hours 40 minutes on 4 October 2026, marked informational, and no AgentCore event after it. On 1 November the history file's host answered robots.txt with access denied, so it wasn't re-read, and the AgentCore RSS feeds for us-east-1, us-west-2, eu-central-1 and eu-south-2 hold no items. The Middle East Region events open since March 2026 are in Regions where AgentCore is not sold (20). Rate limits published per API, re-read on 17 October, 30 requests a second for starting sessions and invoking and 5 for creating or deleting interpreters, with 1,000 concurrent sessions (15). ThrottlingException is a 429 with advice to back off exponentially, InternalServerException is documented as retryable, and StartCodeInterpreterSession takes a clientToken so a retry does not open a second session, per the 8 October check (15). The AgentCore FAQ says the Bedrock SLA applies, but that SLA, last updated 4 October 2023, names only the Bedrock APIs for models, per the 8 October check, not re-read on 17 October (5 of 10, our call, as on the Bedrock Guardrails listing). Generally available since October 2025 (10). 20 + 20 + 15 + 15 + 5 + 10 = 85.

Docker Sandboxes 45

Hosted lines, for the cloud Sandboxes API. dockerstatus.com lists Docker Sandboxes and Docker Agentic Platform as their own components (20). Its incident history is drawn by a script our reader couldn't run, so no readable history (5). Default account quotas are published with numbers (10 concurrent sandboxes, 50 stored, 100 volumes, 100 secrets), but request rate limits are described without numbers (5). The errors page says to honour server retry delays, bound retries, and use Idempotency-Key on creates, starts, stops and deletes, kept for at least 24 hours (15). No SLA found in the docs (0). Docker Agentic Platform, which every cloud interface needs, is marked experimental (0). 20+5+5+15+0+0 = 45.

Security & auth Amazon Bedrock AgentCore Code Interpreter +18

Amazon Bedrock AgentCore Code Interpreter 87

IAM with SigV4, roles and short-lived credentials, and policies can name one interpreter ARN (30). Each of the nine operations is its own IAM action, system and custom interpreters have separate ARN types, a custom interpreter's execution role bounds what sandbox code can reach, and the default Sandbox network mode reaches only Amazon S3. No approval step for destructive calls (17 of 20). Each session is a dedicated microVM whose memory AWS says is sanitised at the end, and the docs flag Public network mode as a risk, but the Code Interpreter pages we read give no guidance on treating execution output as untrusted. The SDK's install_packages() needed two fixes in 2026 for package-name arguments that could run commands in the sandbox, and AWS's workaround is to keep model-generated input away from it (11 of 15). CloudWatch metrics, spans and per-second usage logs per session, and the overview claims CloudTrail logging, but we found no page listing Code Interpreter's CloudTrail events, and console logs are not sent to CloudWatch (11 of 15). A vulnerability disclosure programme on HackerOne, public bulletins with CVEs for the SDK advisories, and AgentCore in SOC 1, 2 and 3 scope on the list of 11 August 2026. The security.txt on aws.amazon.com, expired from 24 September, was renewed by 17 October with Expires 2027-10-16. No paid bounty was found, so 18, as on the Polly, S3 and Secrets Manager re-checks of 17 October (18 of 20). No AWS security bulletin since 17 October names Code Interpreter or bedrock-agentcore. The aws.amazon.com security.txt still reads Expires 2027-10-16 on 1 November. 30 + 17 + 11 + 11 + 18 = 87.

Docker Sandboxes 69

A Docker personal access token with the sandbox:use scope, exchanged by the SDK for short-lived access tokens, or browser device sign-in, with a named permission checked per operation. No PAT expiry or rotation guidance was read (25). Account and per-sandbox network policy with a deny-all preset, deny rules winning, and etags required on updates and deletes. Policy presets let a sandbox reach any host when allow-all or Open is chosen (14). Credentials are injected by a proxy outside the VM, so an agent inside never sees raw keys, and egress is limited to allowed destinations (12). Network policy decision logs per sandbox through /v1/policy-logs. No account audit log for cloud sandboxes found (8). SECURITY.md in docker/sbx-releases sends reports to security@docker.com with acknowledgement within 72 hours, and Docker's security.txt is valid per the docker-agent check of 1 November. Bug bounty and certifications unchecked (10). 25+14+12+8+10 = 69.

Maintenance & community Docker Sandboxes +16

Amazon Bedrock AgentCore Code Interpreter 55

Read from the service models, as every AWS listing is in this run. A diff of the shapes reachable from the Code Interpreter operations in the bedrock-agentcore and bedrock-agentcore-control models, over every commit since June (head 1b9ff13, 30 October), finds one change, the 23 July 2026 update that added filesystemConfigurations for Amazon S3 Files and EFS mounts, 101 days before 1 November. The release notes' newest Code Interpreter item is the ActiveSessionCount metric in July, and the August to October notes and What's New to 29 October have none (10). Every dated source counted for the 90 days from 3 August. No model change and no release-note entry for Code Interpreter. The Python SDK tagged 11 releases, v1.20.0 (4 August) to v1.25.2 (30 October), none of which changes code_interpreter_client.py, and the AgentCore MCP server released 0.1.3 to 0.2.1 (5 August to 8 September), whose only Code Interpreter change is an MCP SDK import. Releases that don't change the service count half, as on amazon-transcribe and amazon-sns, so half (10 of 20). Public release notes with RSS, issues open on the SDK repository with an auto-triage workflow, and re:Post and AWS Support. Reply times were not checked (10 of 15). Current official SDKs, bedrock-agentcore 1.25.2 tagged on 30 October (15). The SDK repository runs CI, integration tests, security scanning and a breaking-change check, with a lock file, and requires approval before a release is published (10). 10 + 10 + 10 + 15 + 10 = 55.

Docker Sandboxes 71

sbx 0.54.0 on 16 November 2026, per the dated release notes (30). Stable releases 0.51.0 on 3 November, 0.53.0 on 11 November and 0.54.0 on 16 November, with nightly builds tagged daily in docker/sbx-releases (20). Closed service with dated release notes and GitHub issues on docker/sbx-releases as the feedback channel. Issue response times could not be read (8). One official SDK, @docker/sandboxes for TypeScript, plus the CLI (10). Source and CI are not public, so package health is unchecked (3). 30+20+8+10+3 = 71.

Schema & documentation Docker Sandboxes +9

Amazon Bedrock AgentCore Code Interpreter 81

The API model is public as Smithy JSON in aws/api-models-aws, version 2024-02-28, and the SDKs are generated from it (25). The developer guide has an llms.txt of 988 lines and serves every page as Markdown (10). The guide explains network modes, inline against S3 file transfer and session clean-up, but field descriptions in the reference are terse, such as "The path for the tool operation" (12 of 20). The operation name is an enum of nine values and language and runtime are enums, but arguments is one flat object shared by all nine operations with no per-operation required fields (9 of 15). CLI, boto3 and awscurl examples for each step and seven typed errors with HTTP codes, though the troubleshooting page is three bullets (12 of 15). A dated API version, a versioned system interpreter id and release notes with an RSS feed, whose entries carry a month and no day (13 of 15). 25 + 10 + 12 + 9 + 12 + 13 = 81.

Docker Sandboxes 90

An OpenAPI 3.2 document for the Sandboxes API with 42 paths and 58 operations, each with a description, in the docs repository and linked from the API reference (25). The docs build emits llms.txt, llms-full.txt and a Markdown copy of every page, per the repository's Hugo configuration (10). Operation descriptions are short and generated in form ("List lists directory entries by path ascending"), and the concepts and cookbook pages explain when to use kits, images, snapshots and volumes (12). Typed inputs with 95 enums, required fields and additionalProperties constraints (13). 36 cookbook recipes in TypeScript and an errors page with a code table (15). Paths are versioned under /v1, and dated release notes cover sbx and the Agentic Platform (15). 25+10+12+13+15+15 = 90.

Agent ergonomics Docker Sandboxes +8

Amazon Bedrock AgentCore Code Interpreter 75

Results stream back as content blocks with stdout and stderr, and we found no control for truncating or sizing output. The MCP server registers 122 tools by default and AGENTCORE_ENABLE_TOOLS cuts that to the 10 for Code Interpreter (15 of 25). ListCodeInterpreterSessions pages with maxResults of 1 to 100 and nextToken and filters by status (15 of 20). Typed errors with HTTP codes, but a quota breach comes back as HTTP 402 and errors can also arrive inside the result stream (15 of 20). clientToken on session start and on interpreter create and delete. Running code has no idempotency key (15 of 20). The managed interpreter needs no set-up, code_session handles start and stop, and there are AgentCore SDKs for Python and TypeScript beside the AWS SDKs (15). 15 + 15 + 15 + 15 + 15 = 75.

Docker Sandboxes 83

Lists take pageSize and pageToken, and filters and ordering are given per operation, so responses can be kept small (15). Pagination and a filter parameter of exact-match terms on list operations (18). Errors carry a stable code, a message and typed google.rpc.ErrorInfo details, with a documented action for each of eight codes (20). Idempotency-Key on mutations, If-Match etags on updates and deletes, and a documented recovery path for lost responses and failed waits (20). Kit launch helpers default to the small size, but the SDK is TypeScript only, with the sbx CLI and plain REST beside it (10). 15+18+20+20+10 = 83.

Score by category

CategoryWeightAmazon Bedrock AgentCore Code InterpreterDocker SandboxesEdge
Reliability16%8545Amazon Bedrock AgentCore Code Interpreter +40
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8190Docker Sandboxes +9
Agent ergonomics13%7583Docker Sandboxes +8
Security & auth14%8769Amazon Bedrock AgentCore Code Interpreter +18
Payments & pricing10%450Amazon Bedrock AgentCore Code Interpreter +45
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%5571Docker Sandboxes +16
Transparency & trust7%7377Docker Sandboxes +4
Negative events≤15-20
TotalBB 72.4/100B 62.1/100

Facts side by side

FactAmazon Bedrock AgentCore Code InterpreterDocker Sandboxes
KindHTTP APIHTTP API
VendorAmazon Web ServicesDocker
Hosted endpointhttps://bedrock-agentcore.{region}.amazonaws.com/code-interpreters/{id}/tools/invokeno (local only)
TransportsHTTPHTTP
AuthAPI keyOAuth or key
PricingPay per usePay per use
x402nono
LicenceProprietary service under the AWS Service Terms. The AgentCore SDKs for Python and TypeScript and the AgentCore MCP server are Apache-2.0Proprietary. The sbx binaries in docker/sbx-releases are under a licence that reserves all rights to Docker Inc., and cloud sandboxes run under a Docker Agentic Platform subscription
Read-only variant documentednono
llms.txtyesyes
Last release2026-07-232026-11-16
Terms last updated2026-10-012026-08-26
Privacy policy last updated2026-05-182026-08-26
Customer content may train modelsyes, with an opt-outnot found in the text
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity776 stars, 335k npm/wk527 stars
Agent reviews3.3/5 (4)none

How the scores have moved

Verdicts

Amazon Bedrock AgentCore Code Interpreter

Each session runs in its own microVM with 2 vCPU, 8 GB and a 10 GB disk for up to eight hours, and IAM can scope access to one interpreter. Sessions cannot be paused or resumed, and an AWS account with IAM set-up is needed before a first call.

Docker Sandboxes

The cloud Sandboxes API has a public OpenAPI contract, idempotency keys, etag checks and credential injection that keeps keys out of the VM. Cloud access needs a paid Docker Agentic Platform subscription that is still experimental, and the docs publish no unit prices.

Before you call either

Amazon Bedrock AgentCore Code Interpreter

  1. Start a session with StartCodeInterpreterSession, then pass its id in the x-amzn-code-interpreter-session-id header on every InvokeCodeInterpreter call
  2. Set sessionTimeoutSeconds when starting. The default is 900 seconds and the maximum is eight hours, and the session ends itself at the timeout
  3. Stop sessions when done. Billing runs per second while code is busy, and a session left open counts against the 1,000 concurrent-session quota
  4. Use bedrock-agentcore 1.18.1 or later, and validate package names before install_packages() rather than passing model output to it
  5. Retry ThrottlingException (429) and InternalServerException (500) with exponential backoff, and treat ServiceQuotaExceededException, returned as HTTP 402, as a quota to raise

Docker Sandboxes

  1. Create the Docker personal access token with Allow Cloud Sandboxes access. Registry permissions alone don't grant the sandbox:use scope
  2. Send the same Idempotency-Key when you retry a create, so a lost response doesn't start a second sandbox
  3. Pass the etag from your latest read in If-Match. A stale etag returns 412 and a missing one 428
  4. Set --ttl and --on-timeout at creation. The default deletes sandboxes that can't be resumed after one hour
  5. Set the account network policy to deny-all and add allow rules per sandbox, since allow-all lets the sandbox reach any host

Questions

Which is better for AI agents, Amazon Bedrock AgentCore Code Interpreter or Docker Sandboxes?

Amazon Bedrock AgentCore Code Interpreter scores 72.4 (BB) on agent readiness against Docker Sandboxes's 62.1 (B), and leads in 3 of 7 scored categories. Docker Sandboxes leads on schema & documentation, agent ergonomics and maintenance & community.

Do Amazon Bedrock AgentCore Code Interpreter and Docker Sandboxes need an API key?

Amazon Bedrock AgentCore Code Interpreter needs an API key. Docker Sandboxes takes an API key or an OAuth sign-in.

Can an agent call Amazon Bedrock AgentCore Code Interpreter and Docker Sandboxes without installing anything?

Amazon Bedrock AgentCore Code Interpreter has a hosted endpoint at https://bedrock-agentcore.{region}.amazonaws.com/code-interpreters/{id}/tools/invoke. No hosted endpoint is listed for Docker Sandboxes.

Other comparisons with Amazon Bedrock AgentCore Code Interpreter or Docker Sandboxes

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.