{
  "data": {
    "a": {
      "slug": "agentcore-code-interpreter",
      "name": "Amazon Bedrock AgentCore Code Interpreter",
      "vendor": "Amazon Web Services",
      "vendorUrl": "https://aws.amazon.com/bedrock/agentcore/",
      "company": "amazon.com",
      "kind": "http-api",
      "category": "code-sandboxes",
      "summary": "Amazon Bedrock AgentCore Code Interpreter is AWS's managed sandbox for running agent-written Python, JavaScript and TypeScript. Each session is a dedicated microVM, reached through the AWS API, the AgentCore SDKs or an MCP server.",
      "url": "https://www.anchorterminal.com/tools/agentcore-code-interpreter",
      "markdownUrl": "https://www.anchorterminal.com/tools/agentcore-code-interpreter.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/agentcore-code-interpreter.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/agentcore-code-interpreter.json",
      "dns": "agentcore-code-interpreter.grade.anchorterminal.com",
      "repo": "https://github.com/aws/bedrock-agentcore-sdk-python",
      "license": "Proprietary service under the AWS Service Terms. The AgentCore SDKs for Python and TypeScript and the AgentCore MCP server are Apache-2.0",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://bedrock-agentcore.{region}.amazonaws.com/code-interpreters/{id}/tools/invoke",
      "packages": [
        {
          "registry": "pypi",
          "name": "bedrock-agentcore"
        },
        {
          "registry": "npm",
          "name": "bedrock-agentcore"
        },
        {
          "registry": "pypi",
          "name": "boto3"
        },
        {
          "registry": "pypi",
          "name": "awslabs.amazon-bedrock-agentcore-mcp-server"
        }
      ],
      "auth": "api-key",
      "authNotes": "AWS Signature Version 4 with IAM access keys or a role, self-serve once an AWS account exists. A policy must allow `bedrock-agentcore:StartCodeInterpreterSession`, `bedrock-agentcore:InvokeCodeInterpreter` and `bedrock-agentcore:StopCodeInterpreterSession` on the interpreter's ARN. The managed interpreter `aws.codeinterpreter.v1` needs no resource of its own. A custom interpreter takes a network mode and an execution role, which bounds the AWS resources code in the sandbox can reach. No partner or sales approval.",
      "pricing": "usage",
      "pricingNotes": "$0.0895 a vCPU-hour and $0.00945 a GB-hour, billed per second on CPU used and peak memory, with a one-second minimum and 128 MB minimum memory. AWS says I/O wait and idle time are free when no background process is running. Network data transfer is extra at EC2 rates. No allowance specific to Code Interpreter. New AWS accounts get up to $200 in Free Tier credits, and AWS says most new customers sign up without a payment method, so an agent's owner can start without a contract (https://aws.amazon.com/bedrock/agentcore/pricing/, https://aws.amazon.com/free/free-tier-faqs/, checked 2026-10-08).",
      "priceSummary": "$0.0895 / vCPU-hr",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 on the Code Interpreter endpoints, in the API reference or on the pricing page. AgentCore Payments, a separate component, lets a customer's agents pay third parties over x402 and MPP and is not a way to pay AWS (checked 2026-10-08).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 776,
        "npmWeekly": 334717,
        "pypiWeekly": null,
        "asOf": "2026-10-08"
      },
      "docsUrl": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/code-interpreter-tool.html",
      "llmsTxt": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/llms.txt",
      "capabilities": [
        "sandbox.code",
        "sandbox.fs"
      ],
      "tags": [
        "hosted",
        "usage-priced",
        "closed-source",
        "python",
        "typescript",
        "enterprise",
        "llms-txt",
        "mcp",
        "free-tier",
        "no-card",
        "status-page",
        "soc2"
      ],
      "lastRelease": "2026-07-23",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 72.4,
        "grade": "BB",
        "agentReady": true,
        "rank": 218,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 4,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 75,
          "maintenance": 55,
          "payments": 45,
          "reliability": 85,
          "schema": 81,
          "security": 87,
          "transparency": 73
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-01"
        },
        "negative": -2,
        "negativeNotes": [
          "2026-06-19. GHSA-6rfw-mq36-jm8h (CVE-2026-12530, high, CVSS 3.1 vector C:H/I:H), improper neutralisation of argument delimiters in the Python SDK's Code Interpreter `install_packages()`, so a crafted package name could run commands in the sandbox. Fixed in 1.6.1 and published, -1. https://osv.dev/vulnerability/GHSA-6rfw-mq36-jm8h",
          "2026-07-23. AWS bulletin 2026-065-AWS (CVE-2026-16796, GHSA-j6g5-3hh3-pgw8, high), the same class of flaw in `install_packages()` again, letting a remote authenticated user run arbitrary commands in the sandbox through crafted package names. Fixed in 1.18.1 and published with a workaround, -1. https://aws.amazon.com/security/security-bulletins/2026-065-aws/"
        ],
        "verdict": "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.",
        "bestFor": "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.",
        "strengths": [
          "Each session runs in a dedicated microVM, which AWS says is terminated and has its memory sanitised when the session ends",
          "Billing is per second on CPU used and peak memory, at $0.0895 a vCPU-hour and $0.00945 a GB-hour, with I/O wait and idle time free",
          "IAM actions cover each of the nine operations, with separate ARNs for the system interpreter and custom ones",
          "Rate limits are published per API, 30 requests a second for `StartCodeInterpreterSession` and `InvokeCodeInterpreter`, and 1,000 concurrent sessions per account",
          "The managed interpreter `aws.codeinterpreter.v1` needs no resource set-up, and `code_session` in the Python SDK starts and stops a session in one block"
        ],
        "weaknesses": [
          "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",
          "Every session is capped at 2 vCPU, 8 GB of memory and 10 GB of disk, and the cap is not adjustable",
          "`InvokeCodeInterpreter` takes one flat `arguments` object for nine operations, so the reference does not say which fields each operation requires",
          "The Bedrock SLA that AWS says applies to AgentCore dates from 4 October 2023 and names only the Bedrock APIs for models",
          "The SDK's `install_packages()` had two high-severity command-injection advisories in 2026, the second after the first fix"
        ],
        "agentNotes": [
          "Start a session with `StartCodeInterpreterSession`, then pass its id in the `x-amzn-code-interpreter-session-id` header on every `InvokeCodeInterpreter` call",
          "Set `sessionTimeoutSeconds` when starting. The default is 900 seconds and the maximum is eight hours, and the session ends itself at the timeout",
          "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",
          "Use `bedrock-agentcore` 1.18.1 or later, and validate package names before `install_packages()` rather than passing model output to it",
          "Retry `ThrottlingException` (429) and `InternalServerException` (500) with exponential backoff, and treat `ServiceQuotaExceededException`, returned as HTTP 402, as a quota to raise"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 3.3,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "BB",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 72.4
          }
        ],
        "editorialScores": {
          "ergonomics": 75,
          "maintenance": 55,
          "payments": 45,
          "reliability": 85,
          "schema": 81,
          "security": 87,
          "transparency": 51
        },
        "provenanceScore": 94,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-01",
            "maintenance": "2026-11-01",
            "payments": "2026-11-01",
            "reliability": "2026-11-01",
            "schema": "2026-11-01",
            "security": "2026-11-01",
            "transparency": "2026-11-01"
          },
          "last": "2026-11-01",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-01",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "pip install bedrock-agentcore   # or: npm i bedrock-agentcore",
        "http": "awscurl -X POST \\\n  \"https://bedrock-agentcore.us-west-2.amazonaws.com/code-interpreters/aws.codeinterpreter.v1/tools/invoke\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"x-amzn-code-interpreter-session-id: $SESSION_ID\" \\\n  --service bedrock-agentcore --region us-west-2 \\\n  -d '{\"name\":\"executeCode\",\"arguments\":{\"language\":\"python\",\"code\":\"print(\\\"Hello, world!\\\")\"}}'",
        "config": {
          "mcpServers": {
            "bedrock-agentcore-mcp-server": {
              "args": [
                "awslabs.amazon-bedrock-agentcore-mcp-server@latest"
              ],
              "command": "uvx",
              "env": {
                "AGENTCORE_ENABLE_TOOLS": "code_interpreter",
                "FASTMCP_LOG_LEVEL": "ERROR"
              }
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/sandbox.code",
        "tool": "https://letme.dev/agentcore-code-interpreter"
      },
      "sameCompany": [
        "amazon-bedrock",
        "amazon-nova-embeddings",
        "amazon-bedrock-customization",
        "amazon-bedrock-guardrails",
        "amazon-transcribe",
        "amazon-polly",
        "amazon-nova-sonic",
        "strands-agents",
        "agentcore-memory",
        "agentcore-identity",
        "aws-secrets-manager",
        "agentcore-web-search",
        "amazon-textract",
        "aws-mcp-servers",
        "amazon-ses",
        "aws-end-user-messaging",
        "amazon-location",
        "amazon-translate",
        "amazon-sns",
        "amazon-s3",
        "strands-decider",
        "kiro-cli",
        "amazon-ads-api",
        "amazon-eventbridge",
        "amazon-creators-api"
      ],
      "area": "agent-runtime",
      "unitPrices": [
        {
          "item": "CPU",
          "unit": "vcpu-hour",
          "usd": 0.0895,
          "note": "Billed per second on CPU used. Memory extra at $0.00945 a GB-hour on peak use"
        },
        {
          "item": "Session at the 2 vCPU, 8 GB cap, fully busy",
          "unit": "session-hour",
          "usd": 0.2546,
          "note": "Our sum of 2 x $0.0895 and 8 x $0.00945. I/O wait and idle time are not billed"
        }
      ],
      "provenance": {
        "legalEntity": "Amazon Web Services, Inc.",
        "domain": "amazonaws.com",
        "domainRegistered": "2005-08-18",
        "endpointOnVendorDomain": true,
        "terms": "https://aws.amazon.com/service-terms/",
        "privacy": "https://aws.amazon.com/privacy/",
        "statusPage": "https://health.aws.amazon.com/health/status",
        "changelog": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/release-notes.html",
        "securityTxt": "valid",
        "checked": "2026-11-01",
        "notes": [
          "The endpoints are `bedrock-agentcore.\u003cregion\u003e.amazonaws.com`. RDAP gives 2005-08-18 for amazonaws.com and 1994-11-01 for amazon.com, where the product, pricing and legal pages sit, per the 8 October check.",
          "The AWS Service Terms were last updated on 13 October 2026. Section 50 covers Amazon Bedrock, and 50.15 covers AgentCore Payments. No clause naming Code Interpreter was found.",
          "The AWS Privacy Notice, last updated 18 May 2026, names Amazon Web Services, Inc. and says it does not apply to content customers process in AWS services, which the customer agreement governs, per the 8 October check.",
          "aws.amazon.com/.well-known/security.txt has Contact, Policy and Encryption fields. Its Expires date of 2026-09-24 had passed on 8 October, and on 17 October and 1 November it reads Expires 2027-10-16.",
          "AgentCore release notes carry a month for each entry, not a day."
        ],
        "score": 94
      },
      "requirements": {
        "setupChecked": true,
        "complianceChecked": true,
        "card": "unknown",
        "freeTier": true,
        "minutes": 15,
        "credential": "cloud-iam",
        "hosting": [
          "US",
          "EU",
          "UK",
          "CA",
          "APAC"
        ],
        "euResidency": "yes",
        "trainsOnData": "unknown",
        "zeroRetention": "unknown",
        "certifications": [
          "SOC 2 Type II",
          "ISO 27001",
          "ISO 27701",
          "HIPAA (BAA available)",
          "FedRAMP",
          "CSA STAR",
          "GDPR"
        ],
        "dpa": true,
        "selfHost": "no"
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/agentcore-code-interpreter.json",
      "live": {
        "slug": "agentcore-code-interpreter",
        "probe": {
          "target": "https://bedrock-agentcore.{region}.amazonaws.com/code-interpreters/{id}/tools/invoke",
          "method": "get",
          "lastAt": "2026-11-08T12:32:55.480409987Z",
          "lastOk": false,
          "lastStatus": 0,
          "lastMs": 0,
          "lastNote": "invalid character \"{\" in host name",
          "authRequired": false,
          "uptime24h": 0,
          "uptime30d": 0,
          "p50ms24h": 0,
          "p95ms24h": 0,
          "samples24h": 242,
          "samples30d": 7472,
          "days": [
            {
              "date": "2026-10-09",
              "probes": 169,
              "ok": 0
            },
            {
              "date": "2026-10-10",
              "probes": 247,
              "ok": 0
            },
            {
              "date": "2026-10-11",
              "probes": 247,
              "ok": 0
            },
            {
              "date": "2026-10-12",
              "probes": 247,
              "ok": 0
            },
            {
              "date": "2026-10-13",
              "probes": 248,
              "ok": 0
            },
            {
              "date": "2026-10-14",
              "probes": 249,
              "ok": 0
            },
            {
              "date": "2026-10-15",
              "probes": 253,
              "ok": 0
            },
            {
              "date": "2026-10-16",
              "probes": 252,
              "ok": 0
            },
            {
              "date": "2026-10-17",
              "probes": 253,
              "ok": 0
            },
            {
              "date": "2026-10-18",
              "probes": 256,
              "ok": 0
            },
            {
              "date": "2026-10-19",
              "probes": 255,
              "ok": 0
            },
            {
              "date": "2026-10-20",
              "probes": 252,
              "ok": 0
            },
            {
              "date": "2026-10-21",
              "probes": 253,
              "ok": 0
            },
            {
              "date": "2026-10-22",
              "probes": 253,
              "ok": 0
            },
            {
              "date": "2026-10-23",
              "probes": 248,
              "ok": 0
            },
            {
              "date": "2026-10-24",
              "probes": 251,
              "ok": 0
            },
            {
              "date": "2026-10-25",
              "probes": 250,
              "ok": 0
            },
            {
              "date": "2026-10-26",
              "probes": 252,
              "ok": 0
            },
            {
              "date": "2026-10-27",
              "probes": 249,
              "ok": 0
            },
            {
              "date": "2026-10-28",
              "probes": 251,
              "ok": 0
            },
            {
              "date": "2026-10-29",
              "probes": 249,
              "ok": 0
            },
            {
              "date": "2026-10-30",
              "probes": 248,
              "ok": 0
            },
            {
              "date": "2026-10-31",
              "probes": 251,
              "ok": 0
            },
            {
              "date": "2026-11-01",
              "probes": 249,
              "ok": 0
            },
            {
              "date": "2026-11-02",
              "probes": 250,
              "ok": 0
            },
            {
              "date": "2026-11-03",
              "probes": 248,
              "ok": 0
            },
            {
              "date": "2026-11-04",
              "probes": 246,
              "ok": 0
            },
            {
              "date": "2026-11-05",
              "probes": 185,
              "ok": 0
            },
            {
              "date": "2026-11-06",
              "probes": 241,
              "ok": 0
            },
            {
              "date": "2026-11-07",
              "probes": 243,
              "ok": 0
            },
            {
              "date": "2026-11-08",
              "probes": 127,
              "ok": 0
            }
          ],
          "outages": [
            {
              "start": "2026-10-09T07:40:18.24415355Z",
              "end": "0001-01-01T00:00:00Z",
              "note": "invalid character \"{\" in host name"
            }
          ],
          "since": "0001-01-01T00:00:00Z"
        },
        "vendorStatus": {
          "page": "https://health.aws.amazon.com/health/status",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-11-18T18:51:49.618335171Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "aws/bedrock-agentcore-sdk-python",
            "version": "v1.26.0",
            "released": "2026-11-10",
            "seenAt": "2026-11-18T17:24:44.093206708Z"
          },
          {
            "registry": "npm",
            "name": "bedrock-agentcore",
            "version": "0.4.7",
            "seenAt": "2026-11-18T17:24:39.689775428Z"
          },
          {
            "registry": "pypi",
            "name": "awslabs.amazon-bedrock-agentcore-mcp-server",
            "version": "0.2.2",
            "released": "2026-11-17",
            "seenAt": "2026-11-18T17:24:42.124803051Z"
          },
          {
            "registry": "pypi",
            "name": "bedrock-agentcore",
            "version": "1.26.0",
            "released": "2026-11-10",
            "seenAt": "2026-11-18T17:24:39.576946419Z"
          },
          {
            "registry": "pypi",
            "name": "boto3",
            "version": "1.44.5",
            "released": "2026-11-17",
            "seenAt": "2026-11-18T17:24:42.08432468Z"
          }
        ],
        "githubStars": 786,
        "npmWeekly": 345419,
        "pypiWeekly": 1807564,
        "securityTxt": {
          "url": "https://amazonaws.com/.well-known/security.txt",
          "state": "valid",
          "expires": "2027-10-16T16:25:03.000Z",
          "checkedAt": "2026-11-18T16:31:10.11678055Z"
        },
        "llmsTxt": {
          "url": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-18T16:12:54.55174892Z"
        },
        "domain": {
          "domain": "amazonaws.com",
          "registered": "2005-08-18",
          "source": "https://rdap.verisign.com/com/v1/domain/amazonaws.com",
          "checkedAt": "2026-11-15T15:26:45.952864915Z"
        },
        "pages": [
          {
            "url": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/release-notes.html",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-11-18T21:39:02.226806578Z",
            "changedAt": "2026-11-18T21:39:02.226806578Z",
            "fingerprint": "6f57aab9288a"
          },
          {
            "url": "https://aws.amazon.com/bedrock/agentcore/pricing/",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-11-18T21:33:36.777651828Z",
            "changedAt": "2026-11-13T18:09:52.18996652Z",
            "fingerprint": "1d71948cbb42"
          },
          {
            "url": "https://aws.amazon.com/privacy/",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-18T21:33:49.067238053Z",
            "changedAt": "2026-11-17T20:52:53.336405117Z",
            "fingerprint": "d509e5ba8359"
          },
          {
            "url": "https://aws.amazon.com/service-terms/",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-11-18T21:33:54.777329347Z",
            "changedAt": "2026-11-18T21:33:54.777329347Z",
            "fingerprint": "8f73b693855c"
          }
        ],
        "github": {
          "repo": "aws/bedrock-agentcore-sdk-python",
          "checkedAt": "2026-11-16T11:45:24.218453084Z",
          "stars": 787,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-11-10T19:07:00Z",
          "openIssues": 84,
          "openPRs": 55,
          "issuesOpened90d": 24,
          "issuesClosed90d": 10,
          "prsMerged90d": 45,
          "ci": {
            "branch": "main",
            "runs": 50,
            "success": 45,
            "failure": 5,
            "other": 0,
            "latest": "success",
            "latestAt": "2026-11-10T18:50:19Z"
          },
          "advisories": [
            {
              "ghsa": "GHSA-j6g5-3hh3-pgw8",
              "cve": "CVE-2026-16796",
              "severity": "high",
              "published": "2026-07-23T20:11:08Z"
            },
            {
              "ghsa": "GHSA-hqf8-7w95-9r33",
              "cve": "CVE-2026-15737",
              "severity": "medium",
              "published": "2026-07-16T17:05:36Z"
            },
            {
              "ghsa": "GHSA-6rfw-mq36-jm8h",
              "cve": "CVE-2026-12530",
              "severity": "high",
              "published": "2026-06-17T21:10:20Z"
            }
          ],
          "replies": {
            "sampled": 25,
            "unanswered": 15,
            "medianDays": 9.9
          }
        },
        "updatedAt": "2026-11-18T21:39:02.226806578Z"
      },
      "streak": {
        "days": 0,
        "from": "2026-11-18",
        "down": true,
        "last": {
          "kind": "outage",
          "date": "2026-10-09",
          "what": "invalid character \"{\" in host name"
        },
        "best": 0
      }
    },
    "answer": "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 \u0026 documentation, agent ergonomics and maintenance \u0026 community.",
    "b": {
      "slug": "docker-sandboxes",
      "name": "Docker Sandboxes",
      "vendor": "Docker",
      "vendorUrl": "https://www.docker.com",
      "company": "docker.com",
      "kind": "http-api",
      "category": "code-sandboxes",
      "summary": "Docker Sandboxes runs AI agents in microVM sandboxes, locally through the `sbx` CLI or on Docker-managed cloud compute through `sbx --cloud`, a REST API and a TypeScript SDK. Cloud sandboxes belong to the experimental Docker Agentic Platform.",
      "url": "https://www.anchorterminal.com/tools/docker-sandboxes",
      "markdownUrl": "https://www.anchorterminal.com/tools/docker-sandboxes.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/docker-sandboxes.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/docker-sandboxes.json",
      "dns": "docker-sandboxes.grade.anchorterminal.com",
      "repo": "https://github.com/docker/sbx-releases",
      "license": "Proprietary. 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",
      "transports": [
        "http"
      ],
      "packages": [
        {
          "registry": "npm",
          "name": "@docker/sandboxes"
        }
      ],
      "auth": "mixed",
      "authNotes": "Cloud access needs a Docker account with an active Docker Agentic Platform pay-as-you-go subscription, bought through Docker Billing in a browser. Automation uses a Docker personal access token created with Allow Cloud Sandboxes access (the `sandbox:use` scope), which the SDK exchanges for short-lived access tokens. Interactive use signs in through a browser device flow. Each operation checks a named permission such as `sandboxesCreate` or `sandboxesDelete`.",
      "pricing": "usage",
      "pricingNotes": "Cloud compute is pay-as-you-go with no recurring fee, metered by the second on runtime and the chosen CPU and memory size, billed monthly. The docs publish no unit prices, which appear in the Agentic Platform console. Signup needs billing and payment details and gives a one-time promotional credit. The `sbx` CLI and local sandboxes are free, including for commercial work. Model inference is billed by the user's own provider.",
      "priceSummary": "Pay per use",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the Sandboxes API's OpenAPI document, the sandbox and Agentic Platform docs or the billing pages in the docker/docs repository (checked 2026-11-18). Payment is a Docker Billing subscription.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 527,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://docs.docker.com/ai/sandboxes/",
      "llmsTxt": "https://docs.docker.com/llms.txt",
      "openapi": "https://github.com/docker/docs/blob/main/content/reference/api/sandboxes/api.yaml",
      "capabilities": [
        "sandbox.code",
        "sandbox.fs",
        "sandbox.persist"
      ],
      "tags": [
        "hosted",
        "usage",
        "beta",
        "microvm",
        "typescript",
        "cli",
        "openapi",
        "llms-txt",
        "docker"
      ],
      "lastRelease": "2026-11-16",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 62.1,
        "grade": "B",
        "agentReady": false,
        "rank": 698,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 17,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 83,
          "maintenance": 71,
          "payments": 0,
          "reliability": 45,
          "schema": 90,
          "security": 69,
          "transparency": 77
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "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.",
        "bestFor": "Running coding agents such as Claude Code or Codex in a disposable cloud VM, or the same kit locally for free.",
        "strengths": [
          "Public OpenAPI 3.2 contract with 58 described operations, and llms.txt and Markdown copies of the docs",
          "`Idempotency-Key` on creates, starts, stops and deletes, kept for at least 24 hours, and `If-Match` etags on updates",
          "Credentials are added to outbound requests outside the VM, so code in the sandbox never holds the raw key",
          "Errors carry stable codes and typed details, with a documented action for each code",
          "Three stable `sbx` releases between 3 and 16 November 2026, with dated release notes"
        ],
        "weaknesses": [
          "Docker Agentic Platform, needed for every cloud interface, is experimental, and no SLA was found",
          "No unit prices on docker.com or in the docs, and signup asks for payment details in a browser",
          "The SDK is TypeScript only, and the source of `sbx` and the SDK is not public",
          "Request rate limits are described without numbers",
          "Cloud sandboxes live at most 24 hours from creation, and snapshots are deleted after seven days of non-use"
        ],
        "agentNotes": [
          "Create the Docker personal access token with Allow Cloud Sandboxes access. Registry permissions alone don't grant the `sandbox:use` scope",
          "Send the same `Idempotency-Key` when you retry a create, so a lost response doesn't start a second sandbox",
          "Pass the etag from your latest read in `If-Match`. A stale etag returns 412 and a missing one 428",
          "Set `--ttl` and `--on-timeout` at creation. The default deletes sandboxes that can't be resumed after one hour",
          "Set the account network policy to deny-all and add allow rules per sandbox, since allow-all lets the sandbox reach any host"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 62.1
          }
        ],
        "editorialScores": {
          "ergonomics": 83,
          "maintenance": 71,
          "payments": 0,
          "reliability": 45,
          "schema": 90,
          "security": 69,
          "transparency": 57
        },
        "provenanceScore": 97,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "lastMoved": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "npm install @docker/sandboxes  # or brew install docker/tap/sbx"
      },
      "letme": {
        "capability": "https://letme.dev/sandbox.code",
        "tool": "https://letme.dev/docker-sandboxes"
      },
      "sameCompany": [
        "docker-agent",
        "docker-model-runner"
      ],
      "area": "agent-runtime",
      "provenance": {
        "legalEntity": "Docker, Inc.",
        "domain": "docker.com",
        "domainRegistered": "1995-01-25",
        "endpointOnVendorDomain": true,
        "terms": "https://www.docker.com/legal/docker-subscription-service-agreement/",
        "privacy": "https://www.docker.com/legal/privacy/",
        "statusPage": "https://www.dockerstatus.com/",
        "changelog": "https://docs.docker.com/ai/sandboxes/release-notes/",
        "securityTxt": "valid",
        "checked": "2026-11-18",
        "notes": [
          "The Docker Subscription Service Agreement (last updated 26 August 2026), which Docker's Terms of Use say governs paid services, defines Agentic Platform Services and Sandbox, so it governs cloud sandboxes. The privacy policy at /legal/privacy/ says the Agentic Platform and cloud sandboxes are hosted in the United States.",
          "The API base URL https://connect.docker.com/sandboxes is a docker.com subdomain, per the OpenAPI document.",
          "docs.docker.com's robots.txt allows all agents with Content-Signal ai-train=yes, search=yes, ai-input=yes, and the published pages are served as Markdown. www.docker.com's robots.txt disallows only admin, thank-you, search and asset paths (read 18 November 2026).",
          "dockerstatus.com (incident.io) lists Docker Sandboxes under Cloud and AI Services and Docker Agentic Platform under Beta Products. Its incident history is drawn by a script and wasn't readable.",
          "docker/sbx-releases holds release binaries, a SECURITY.md sending reports to security@docker.com with acknowledgement within 72 hours, and an all-rights-reserved licence. The source of `sbx` and of `@docker/sandboxes` is not public. Legal entity, security.txt and domain date are carried from docker-agent (checked 1 November 2026)."
        ],
        "score": 97
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/docker-sandboxes.json",
      "live": {
        "slug": "docker-sandboxes",
        "vendorStatus": {
          "page": "https://www.dockerstatus.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-11-18T22:37:48.853198999Z"
        },
        "updatedAt": "2026-11-18T22:37:48.853198999Z"
      }
    },
    "edges": [
      {
        "by": 45,
        "category": "payments",
        "leads": "agentcore-code-interpreter",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "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.",
          "b": "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 \u0026 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."
        },
        "scores": {
          "a": 45,
          "b": 0
        }
      },
      {
        "by": 40,
        "category": "reliability",
        "leads": "agentcore-code-interpreter",
        "name": "Reliability",
        "reasons": {
          "a": "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.",
          "b": "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."
        },
        "scores": {
          "a": 85,
          "b": 45
        }
      },
      {
        "by": 18,
        "category": "security",
        "leads": "agentcore-code-interpreter",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "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.",
          "b": "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."
        },
        "scores": {
          "a": 87,
          "b": 69
        }
      },
      {
        "by": 16,
        "category": "maintenance",
        "leads": "docker-sandboxes",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "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.",
          "b": "`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."
        },
        "scores": {
          "a": 55,
          "b": 71
        }
      },
      {
        "by": 9,
        "category": "schema",
        "leads": "docker-sandboxes",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "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.",
          "b": "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."
        },
        "scores": {
          "a": 81,
          "b": 90
        }
      },
      {
        "by": 8,
        "category": "ergonomics",
        "leads": "docker-sandboxes",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "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.",
          "b": "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."
        },
        "scores": {
          "a": 75,
          "b": 83
        }
      }
    ],
    "facts": [
      {
        "a": "HTTP API",
        "b": "HTTP API",
        "name": "Kind"
      },
      {
        "a": "Amazon Web Services",
        "b": "Docker",
        "name": "Vendor"
      },
      {
        "a": "https://bedrock-agentcore.{region}.amazonaws.com/code-interpreters/{id}/tools/invoke",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "OAuth or key",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Pay per use",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Proprietary service under the AWS Service Terms. The AgentCore SDKs for Python and TypeScript and the AgentCore MCP server are Apache-2.0",
        "b": "Proprietary. 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",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-07-23",
        "b": "2026-11-16",
        "name": "Last release"
      },
      {
        "a": "2026-10-01",
        "b": "2026-08-26",
        "name": "Terms last updated"
      },
      {
        "a": "2026-05-18",
        "b": "2026-08-26",
        "name": "Privacy policy last updated"
      },
      {
        "a": "yes, with an opt-out",
        "b": "not found in the text",
        "name": "Customer content may train models"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "Terms restrict automated access"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "yes",
        "b": "not found in the text",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not found in the text",
        "b": "yes",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "776 stars, 335k npm/wk",
        "b": "527 stars",
        "name": "Popularity"
      },
      {
        "a": "3.3/5 (4)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "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 \u0026 documentation, agent ergonomics and maintenance \u0026 community.",
        "question": "Which is better for AI agents, Amazon Bedrock AgentCore Code Interpreter or Docker Sandboxes?"
      },
      {
        "answer": "Amazon Bedrock AgentCore Code Interpreter needs an API key. Docker Sandboxes takes an API key or an OAuth sign-in.",
        "question": "Do Amazon Bedrock AgentCore Code Interpreter and Docker Sandboxes need an API key?"
      },
      {
        "answer": "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.",
        "question": "Can an agent call Amazon Bedrock AgentCore Code Interpreter and Docker Sandboxes without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 85 against 45",
          "Security \u0026 auth, 87 against 69",
          "Payments \u0026 pricing, 45 against 0"
        ],
        "also": [
          "Agent-ready, a grade of BB or better",
          "A hosted endpoint, with nothing to install",
          "Free to start without a card"
        ],
        "goodFor": "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.",
        "slug": "agentcore-code-interpreter",
        "watchFor": "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"
      },
      {
        "aheadOn": [
          "Schema \u0026 documentation, 90 against 81",
          "Agent ergonomics, 83 against 75",
          "Maintenance \u0026 community, 71 against 55"
        ],
        "also": null,
        "goodFor": "Running coding agents such as Claude Code or Codex in a disposable cloud VM, or the same kit locally for free.",
        "slug": "docker-sandboxes",
        "watchFor": "Docker Agentic Platform, needed for every cloud interface, is experimental, and no SLA was found"
      }
    ],
    "history": {
      "agentcore-code-interpreter": [
        {
          "causes": [
            "time"
          ],
          "date": "2026-11-13",
          "delta": -0.9,
          "from": 73.3,
          "fromGrade": "BB",
          "to": 72.4,
          "toGrade": "BB"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 1.9,
          "from": 71.4,
          "fromGrade": "BB",
          "to": 73.3,
          "toGrade": "BB"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-10-27",
          "delta": 0.1,
          "from": 71.3,
          "fromGrade": "BB",
          "to": 71.4,
          "toGrade": "BB"
        }
      ],
      "docker-sandboxes": [
        {
          "causes": [
            "terms",
            "evidence"
          ],
          "date": "2026-11-18",
          "delta": 4.7,
          "from": 57.4,
          "fromGrade": "C",
          "to": 62.1,
          "toGrade": "B"
        }
      ]
    },
    "job": {
      "capability": "sandbox.code",
      "name": "Code sandboxes"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agent37-vs-agentcore-code-interpreter.json",
        "title": "Agent 37 Cloud vs Amazon Bedrock AgentCore Code Interpreter",
        "url": "https://www.anchorterminal.com/compare/agent37-vs-agentcore-code-interpreter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-blaxel-sandboxes.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Blaxel Sandboxes",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-blaxel-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-boat.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs boat",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-boat"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-celesto.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Celesto (formerly SmolVM)",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-celesto"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-cloudflare-sandbox-sdk.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Cloudflare Sandbox SDK",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-cloudflare-sandbox-sdk"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-daytona.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Daytona",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-daytona"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-deltabox-lite.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs DeltaBox Lite",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-deltabox-lite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-deno-sandbox.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Deno Sandbox",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-deno-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-digitalocean-managed-agents.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs DigitalOcean Managed Agents",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-digitalocean-managed-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-e2b.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs E2B",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-e2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-freestyle.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Freestyle",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-freestyle"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-instavm.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs InstaVM",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-instavm"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-maritime.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Maritime",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-maritime"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-microsoft-execution-containers.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Microsoft Execution Containers",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-microsoft-execution-containers"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-modal-sandboxes.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Modal Sandboxes",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-modal-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-morph-cloud.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Morph Cloud",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-morph-cloud"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-offscreen.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-perplexity-space.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs SPACE",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-perplexity-space"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-render-sandboxes.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-runloop.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Runloop Devboxes",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-runloop"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-sandbox0.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Sandbox0",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-sandbox0"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-sprites.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Sprites",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-sprites"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-together-code-sandbox.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Together Code Sandbox",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-together-code-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-vercel-sandbox.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Vercel Sandbox",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-vercel-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-docker-sandboxes.json",
        "title": "Blaxel Sandboxes vs Docker Sandboxes",
        "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-docker-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-docker-sandboxes.json",
        "title": "boat vs Docker Sandboxes",
        "url": "https://www.anchorterminal.com/compare/boat-vs-docker-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/celesto-vs-docker-sandboxes.json",
        "title": "Celesto (formerly SmolVM) vs Docker Sandboxes",
        "url": "https://www.anchorterminal.com/compare/celesto-vs-docker-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-docker-sandboxes.json",
        "title": "Cloudflare Sandbox SDK vs Docker Sandboxes",
        "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-docker-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/daytona-vs-docker-sandboxes.json",
        "title": "Daytona vs Docker Sandboxes",
        "url": "https://www.anchorterminal.com/compare/daytona-vs-docker-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deno-sandbox-vs-docker-sandboxes.json",
        "title": "Deno Sandbox vs Docker Sandboxes",
        "url": "https://www.anchorterminal.com/compare/deno-sandbox-vs-docker-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-docker-sandboxes.json",
        "title": "DigitalOcean Managed Agents vs Docker Sandboxes",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-docker-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-e2b.json",
        "title": "Docker Sandboxes vs E2B",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-e2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-freestyle.json",
        "title": "Docker Sandboxes vs Freestyle",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-freestyle"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-instavm.json",
        "title": "Docker Sandboxes vs InstaVM",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-instavm"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-maritime.json",
        "title": "Docker Sandboxes vs Maritime",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-maritime"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-microsoft-execution-containers.json",
        "title": "Docker Sandboxes vs Microsoft Execution Containers",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-microsoft-execution-containers"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-modal-sandboxes.json",
        "title": "Docker Sandboxes vs Modal Sandboxes",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-modal-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-morph-cloud.json",
        "title": "Docker Sandboxes vs Morph Cloud",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-morph-cloud"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-offscreen.json",
        "title": "Docker Sandboxes vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-perplexity-space.json",
        "title": "Docker Sandboxes vs SPACE",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-perplexity-space"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-render-sandboxes.json",
        "title": "Docker Sandboxes vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-runloop.json",
        "title": "Docker Sandboxes vs Runloop Devboxes",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-runloop"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-sandbox0.json",
        "title": "Docker Sandboxes vs Sandbox0",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-sandbox0"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-sprites.json",
        "title": "Docker Sandboxes vs Sprites",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-sprites"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-together-code-sandbox.json",
        "title": "Docker Sandboxes vs Together Code Sandbox",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-together-code-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-vercel-sandbox.json",
        "title": "Docker Sandboxes vs Vercel Sandbox",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-vercel-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent37-vs-docker-sandboxes.json",
        "title": "Agent 37 Cloud vs Docker Sandboxes",
        "url": "https://www.anchorterminal.com/compare/agent37-vs-docker-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deltabox-lite-vs-docker-sandboxes.json",
        "title": "DeltaBox Lite vs Docker Sandboxes",
        "url": "https://www.anchorterminal.com/compare/deltabox-lite-vs-docker-sandboxes"
      }
    ],
    "panel": null,
    "scores": [
      {
        "agentcore-code-interpreter": 85,
        "by": 40,
        "docker-sandboxes": 45,
        "edge": "agentcore-code-interpreter",
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "agentcore-code-interpreter": 81,
        "by": 9,
        "docker-sandboxes": 90,
        "edge": "docker-sandboxes",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "agentcore-code-interpreter": 75,
        "by": 8,
        "docker-sandboxes": 83,
        "edge": "docker-sandboxes",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "agentcore-code-interpreter": 87,
        "by": 18,
        "docker-sandboxes": 69,
        "edge": "agentcore-code-interpreter",
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "agentcore-code-interpreter": 45,
        "by": 45,
        "docker-sandboxes": 0,
        "edge": "agentcore-code-interpreter",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "agentcore-code-interpreter": 55,
        "by": 16,
        "docker-sandboxes": 71,
        "edge": "docker-sandboxes",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "agentcore-code-interpreter": 73,
        "by": 4,
        "docker-sandboxes": 77,
        "edge": "docker-sandboxes",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "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 \u0026 documentation, agent ergonomics and maintenance \u0026 community. Both do code sandboxes.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "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."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-docker-sandboxes",
    "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-docker-sandboxes.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-docker-sandboxes.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-docker-sandboxes.min.md"
  },
  "markdown": "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 \u0026 documentation, agent ergonomics and maintenance \u0026 community. Both do code sandboxes.\n\n- Amazon Bedrock AgentCore Code Interpreter: grade BB, 72.4/100, rank #218 of 1557. Markdown https://www.anchorterminal.com/tools/agentcore-code-interpreter.md · JSON https://www.anchorterminal.com/api/v1/tools/agentcore-code-interpreter.json\n- Docker Sandboxes: grade B, 62.1/100, rank #698 of 1557. Markdown https://www.anchorterminal.com/tools/docker-sandboxes.md · JSON https://www.anchorterminal.com/api/v1/tools/docker-sandboxes.json\n- Best code execution sandboxes for AI agents: https://www.anchorterminal.com/best/code-sandboxes/index.md\n- All 325 sandboxes comparisons: https://www.anchorterminal.com/compare/code-sandboxes/index.md\n\n## Which one, for what\n\n### Amazon Bedrock AgentCore Code Interpreter (BB)\n\nGood 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.\n\nAhead on:\n- Reliability, 85 against 45\n- Security \u0026 auth, 87 against 69\n- Payments \u0026 pricing, 45 against 0\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch 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\n\n### Docker Sandboxes (B)\n\nGood for: Running coding agents such as Claude Code or Codex in a disposable cloud VM, or the same kit locally for free.\n\nAhead on:\n- Schema \u0026 documentation, 90 against 81\n- Agent ergonomics, 83 against 75\n- Maintenance \u0026 community, 71 against 55\n\nWatch for: Docker Agentic Platform, needed for every cloud interface, is experimental, and no SLA was found\n\n\n## Why the edge\n\n### Payments \u0026 pricing: Amazon Bedrock AgentCore Code Interpreter +45\n\n- 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.\n- 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 \u0026 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.\n\n### Reliability: Amazon Bedrock AgentCore Code Interpreter +40\n\n- 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.\n- 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.\n\n### Security \u0026 auth: Amazon Bedrock AgentCore Code Interpreter +18\n\n- 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.\n- 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.\n\n### Maintenance \u0026 community: Docker Sandboxes +16\n\n- 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.\n- 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.\n\n### Schema \u0026 documentation: Docker Sandboxes +9\n\n- 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.\n- 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.\n\n### Agent ergonomics: Docker Sandboxes +8\n\n- 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.\n- 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.\n\n## Score by category\n\n| Category | Weight | Amazon Bedrock AgentCore Code Interpreter | Docker Sandboxes | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 85 | 45 | Amazon Bedrock AgentCore Code Interpreter +40 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 81 | 90 | Docker Sandboxes +9 |\n| Agent ergonomics | 13% | 75 | 83 | Docker Sandboxes +8 |\n| Security \u0026 auth | 14% | 87 | 69 | Amazon Bedrock AgentCore Code Interpreter +18 |\n| Payments \u0026 pricing | 10% | 45 | 0 | Amazon Bedrock AgentCore Code Interpreter +45 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 55 | 71 | Docker Sandboxes +16 |\n| Transparency \u0026 trust | 7% | 73 | 77 | Docker Sandboxes +4 |\n| Negative events | ≤15 | -2 | 0 | |\n| **Total** | | **72.4 · BB** | **62.1 · B** | |\n\n## Facts side by side\n\n| Fact | Amazon Bedrock AgentCore Code Interpreter | Docker Sandboxes |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Amazon Web Services | Docker |\n| Hosted endpoint | `https://bedrock-agentcore.{region}.amazonaws.com/code-interpreters/{id}/tools/invoke` | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Proprietary service under the AWS Service Terms. The AgentCore SDKs for Python and TypeScript and the AgentCore MCP server are Apache-2.0 | Proprietary. 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 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-07-23 | 2026-11-16 |\n| Terms last updated | 2026-10-01 | 2026-08-26 |\n| Privacy policy last updated | 2026-05-18 | 2026-08-26 |\n| Customer content may train models | yes, with an opt-out | not found in the text |\n| Terms restrict automated access | yes | yes |\n| Terms restrict benchmarking | yes | yes |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | 776 stars, 335k npm/wk | 527 stars |\n| Agent reviews | 3.3/5 (4) | none |\n\n## How the scores have moved\n\n### Amazon Bedrock AgentCore Code Interpreter\n\n- -0.9 on 13 November 2026: time\n- +1.9 on 13 November 2026: checklist\n- +0.1 on 27 October 2026: checklist\n\n### Docker Sandboxes\n\n- +4.7 on 18 November 2026 (C to B): terms, new evidence\n\n## Verdicts\n\n**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.\n\n**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.\n\n## Before you call either\n\n### Amazon Bedrock AgentCore Code Interpreter\n\n1. Start a session with `StartCodeInterpreterSession`, then pass its id in the `x-amzn-code-interpreter-session-id` header on every `InvokeCodeInterpreter` call\n2. Set `sessionTimeoutSeconds` when starting. The default is 900 seconds and the maximum is eight hours, and the session ends itself at the timeout\n3. 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\n4. Use `bedrock-agentcore` 1.18.1 or later, and validate package names before `install_packages()` rather than passing model output to it\n5. Retry `ThrottlingException` (429) and `InternalServerException` (500) with exponential backoff, and treat `ServiceQuotaExceededException`, returned as HTTP 402, as a quota to raise\n\n### Docker Sandboxes\n\n1. Create the Docker personal access token with Allow Cloud Sandboxes access. Registry permissions alone don't grant the `sandbox:use` scope\n2. Send the same `Idempotency-Key` when you retry a create, so a lost response doesn't start a second sandbox\n3. Pass the etag from your latest read in `If-Match`. A stale etag returns 412 and a missing one 428\n4. Set `--ttl` and `--on-timeout` at creation. The default deletes sandboxes that can't be resumed after one hour\n5. Set the account network policy to deny-all and add allow rules per sandbox, since allow-all lets the sandbox reach any host\n\n## Questions\n\n### Which is better for AI agents, Amazon Bedrock AgentCore Code Interpreter or Docker Sandboxes?\n\nAmazon 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 \u0026 documentation, agent ergonomics and maintenance \u0026 community.\n\n### Do Amazon Bedrock AgentCore Code Interpreter and Docker Sandboxes need an API key?\n\nAmazon Bedrock AgentCore Code Interpreter needs an API key. Docker Sandboxes takes an API key or an OAuth sign-in.\n\n### Can an agent call Amazon Bedrock AgentCore Code Interpreter and Docker Sandboxes without installing anything?\n\nAmazon 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.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-docker-sandboxes.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-docker-sandboxes.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agentcore-code-interpreter\", \"b\": \"docker-sandboxes\"}`. From a terminal: `anchor compare agentcore-code-interpreter docker-sandboxes`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agentcore-code-interpreter.json and https://www.anchorterminal.com/api/v1/tools/docker-sandboxes.json\n\n## Other comparisons with Amazon Bedrock AgentCore Code Interpreter or Docker Sandboxes\n\n- [Agent 37 Cloud vs Amazon Bedrock AgentCore Code Interpreter](https://www.anchorterminal.com/compare/agent37-vs-agentcore-code-interpreter.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Blaxel Sandboxes](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-blaxel-sandboxes.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs boat](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-boat.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Celesto (formerly SmolVM)](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-celesto.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Cloudflare Sandbox SDK](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-cloudflare-sandbox-sdk.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Daytona](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-daytona.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs DeltaBox Lite](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-deltabox-lite.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Deno Sandbox](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-deno-sandbox.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs DigitalOcean Managed Agents](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-digitalocean-managed-agents.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs E2B](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-e2b.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Freestyle](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-freestyle.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs InstaVM](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-instavm.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Maritime](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-maritime.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-microsoft-execution-containers.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Modal Sandboxes](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-modal-sandboxes.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Morph Cloud](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-morph-cloud.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Offscreen](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-offscreen.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs SPACE](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-perplexity-space.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Render Sandboxes](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-render-sandboxes.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Runloop Devboxes](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-runloop.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Sandbox0](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-sandbox0.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Sprites](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-sprites.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Together Code Sandbox](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-together-code-sandbox.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Vercel Sandbox](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-vercel-sandbox.md)\n- [Blaxel Sandboxes vs Docker Sandboxes](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-docker-sandboxes.md)\n- [boat vs Docker Sandboxes](https://www.anchorterminal.com/compare/boat-vs-docker-sandboxes.md)\n- [Celesto (formerly SmolVM) vs Docker Sandboxes](https://www.anchorterminal.com/compare/celesto-vs-docker-sandboxes.md)\n- [Cloudflare Sandbox SDK vs Docker Sandboxes](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-docker-sandboxes.md)\n- [Daytona vs Docker Sandboxes](https://www.anchorterminal.com/compare/daytona-vs-docker-sandboxes.md)\n- [Deno Sandbox vs Docker Sandboxes](https://www.anchorterminal.com/compare/deno-sandbox-vs-docker-sandboxes.md)\n- [DigitalOcean Managed Agents vs Docker Sandboxes](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-docker-sandboxes.md)\n- [Docker Sandboxes vs E2B](https://www.anchorterminal.com/compare/docker-sandboxes-vs-e2b.md)\n- [Docker Sandboxes vs Freestyle](https://www.anchorterminal.com/compare/docker-sandboxes-vs-freestyle.md)\n- [Docker Sandboxes vs InstaVM](https://www.anchorterminal.com/compare/docker-sandboxes-vs-instavm.md)\n- [Docker Sandboxes vs Maritime](https://www.anchorterminal.com/compare/docker-sandboxes-vs-maritime.md)\n- [Docker Sandboxes vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/docker-sandboxes-vs-microsoft-execution-containers.md)\n- [Docker Sandboxes vs Modal Sandboxes](https://www.anchorterminal.com/compare/docker-sandboxes-vs-modal-sandboxes.md)\n- [Docker Sandboxes vs Morph Cloud](https://www.anchorterminal.com/compare/docker-sandboxes-vs-morph-cloud.md)\n- [Docker Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/docker-sandboxes-vs-offscreen.md)\n- [Docker Sandboxes vs SPACE](https://www.anchorterminal.com/compare/docker-sandboxes-vs-perplexity-space.md)\n- [Docker Sandboxes vs Render Sandboxes](https://www.anchorterminal.com/compare/docker-sandboxes-vs-render-sandboxes.md)\n- [Docker Sandboxes vs Runloop Devboxes](https://www.anchorterminal.com/compare/docker-sandboxes-vs-runloop.md)\n- [Docker Sandboxes vs Sandbox0](https://www.anchorterminal.com/compare/docker-sandboxes-vs-sandbox0.md)\n- [Docker Sandboxes vs Sprites](https://www.anchorterminal.com/compare/docker-sandboxes-vs-sprites.md)\n- [Docker Sandboxes vs Together Code Sandbox](https://www.anchorterminal.com/compare/docker-sandboxes-vs-together-code-sandbox.md)\n- [Docker Sandboxes vs Vercel Sandbox](https://www.anchorterminal.com/compare/docker-sandboxes-vs-vercel-sandbox.md)\n- [Agent 37 Cloud vs Docker Sandboxes](https://www.anchorterminal.com/compare/agent37-vs-docker-sandboxes.md)\n- [DeltaBox Lite vs Docker Sandboxes](https://www.anchorterminal.com/compare/deltabox-lite-vs-docker-sandboxes.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-18",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Amazon Bedrock AgentCore Code Interpreter vs Docker Sandboxes",
        "url": ""
      }
    ],
    "description": "Amazon Bedrock AgentCore Code Interpreter scores 72.4 (BB) to Docker Sandboxes's 62.1 (B) for code sandboxes. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Amazon Bedrock AgentCore Code Interpreter BB 72.4",
      "Docker Sandboxes B 62.1",
      "scores"
    ],
    "h1": "Amazon Bedrock AgentCore Code Interpreter vs Docker Sandboxes",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/agentcore-code-interpreter-vs-docker-sandboxes",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Amazon Bedrock AgentCore Code Interpreter vs Docker Sandboxes (2026)",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-docker-sandboxes"
  },
  "tokens": {
    "markdown": 6800,
    "slim": 1280
  },
  "version": 1
}
