{
  "data": {
    "a": {
      "slug": "agent-zero",
      "name": "Agent Zero",
      "vendor": "Agent Zero, s.r.o.",
      "vendorUrl": "https://www.agent-zero.ai",
      "company": "agent-zero.ai",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "Agent Zero is an open-source agent framework that runs in a Docker container with a Linux desktop, a browser, a task scheduler and memory. Its owner reaches it through a web interface, Telegram, WhatsApp or email.",
      "url": "https://www.anchorterminal.com/tools/agent-zero",
      "markdownUrl": "https://www.anchorterminal.com/tools/agent-zero.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/agent-zero.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/agent-zero.json",
      "dns": "agent-zero.grade.anchorterminal.com",
      "repo": "https://github.com/agent0ai/agent-zero",
      "license": "MIT",
      "transports": [],
      "packages": [
        {
          "registry": "oci",
          "name": "agent0ai/agent-zero"
        }
      ],
      "auth": "none",
      "authNotes": "No account. The web interface has no login until the owner sets a username and password in Settings or as `AUTH_LOGIN` and `AUTH_PASSWORD`, which are stored in `/a0/usr/.env` (https://github.com/agent0ai/agent-zero/blob/main/docs/setup/vps-deployment.md). The external API takes an `X-API-KEY` header, and the optional MCP server and A2A endpoint carry the same token in the URL path. The token is derived from the instance id and the login, so it changes when either changes (https://github.com/agent0ai/agent-zero/blob/main/docs/guides/a2a-setup.md). Model access uses provider API keys or OAuth sign-in to ChatGPT (Codex), GitHub Copilot, Google Cloud Gemini or xAI (https://github.com/agent0ai/agent-zero/blob/main/plugins/_oauth/README.md).",
      "pricing": "free",
      "pricingNotes": "Free under MIT, with nothing to buy for the software. The owner pays the model provider they configure, or nothing with a local model. A beta LLM API on the vendor's site gives a daily quota to people who stake its A0T token and is separate from the software (checked 2026-10-12).",
      "priceSummary": "Free · OSS",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-12).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 19429,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-12"
      },
      "docsUrl": "https://github.com/agent0ai/agent-zero/tree/main/docs",
      "llmsTxt": "https://www.agent-zero.ai/llms.txt",
      "capabilities": [
        "agent.harness",
        "agent.mcp-client"
      ],
      "tags": [
        "open-source",
        "self-hosted",
        "local",
        "free",
        "python",
        "mit",
        "llms-txt",
        "docker"
      ],
      "lastRelease": "2026-11-01",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 49.7,
        "grade": "D",
        "agentReady": false,
        "rank": 1168,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 50,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 62,
          "maintenance": 75,
          "payments": 90,
          "reliability": 57,
          "schema": 64,
          "security": 54,
          "transparency": 64
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-04"
        },
        "negative": -15,
        "negativeNotes": [
          "2026-08-27 to 2026-09-23. Breaking changes in minor releases of the `agent0ai/agent-zero` image with notice only in the release notes of the day. v2.11 (27 August) made LiteLLM default to Chat Completions, v2.12 (9 September) made `hist_add_ai_response` require an `llm_result`, and v2.13 (23 September) dropped `runtime=input` for remote execution with \"No compatibility alias\". Repeats fold into one term, -3 (https://www.agent-zero.ai/p/articles/agent-zero-v2-13/).",
          "2026-09-09. Two flaws recorded in the project's own security-review ledger and fixed in v2.12 the same day. An unauthenticated Telegram webhook accepted forged updates, and WhatsApp document names could overwrite files outside the media cache before the sender check ran. The ledger rates both high. Named in the release notes, with no advisory, -3 (https://github.com/agent0ai/agent-zero/blob/main/security-review/LEDGER.md).",
          "2026-03-17 to 2026-10-22. Eight CVEs against Agent Zero, counted one by one, none published by the vendor. CVE-2026-97635 (CISA, 22 October, Web UI XSS before 1.15, CVSS 4.0 8.6, fixed) 2. CVE-2026-51852 and CVE-2026-51853 (MITRE, 30 September, file browser directory traversal in 1.7 to 1.10, CISA-ADP 7.5 each, reports closed as completed) 2 each. CVE-2026-30624 (MITRE, 15 April, MCP server configuration runs arbitrary commands in 0.9.8, 8.6, no fix listed) 2. CVE-2026-47118 (VulnCheck, 27 May, image_get path traversal before 1.15, 7.1, fixed) 1. VulDB's CVE-2026-4308 (6.3, fixed in v2.9) and VulnCheck's CVE-2026-47119 (5.3, fixed) are fixed third-party Mediums and cost 0, and VulDB's CVE-2026-4307 (4.3, fix not established) is an unfixed third-party Medium, left uncounted. -9 (https://osv.dev/list?q=agent-zero, https://github.com/CVEProject/cvelistV5)."
        ],
        "verdict": "Self-hosted under the MIT licence, with seven releases from 12 August to 1 November 2026 and breaking changes listed in minor-release notes. The agent runs shell commands in its container with no approval step, the web interface has no login by default, and eight CVEs from the past year were published by third parties with no vendor advisory.",
        "bestFor": "A technical owner who wants an agent with its own Linux machine, reachable from Telegram, WhatsApp or email, with scheduled tasks and editable memory.",
        "strengths": [
          "MIT licence, with prompts, tools, plugins and settings readable and editable in one public repository",
          "Seven tagged releases from 12 August to 1 November 2026, with Breaking Changes sections in the v2.11, v2.12 and v2.13 notes",
          "Memory dashboard to search, edit, delete and bulk-delete entries, with memory kept apart for each project by default",
          "No usage telemetry found in the source. The one call home is an update check whose settings page says what it sends and turns it off",
          "Tool Access policy can allow or block each built-in and MCP tool for a project or an agent profile"
        ],
        "weaknesses": [
          "No approval step before shell commands, file changes or outgoing messages. Tool Access defaults to allow",
          "The web interface has no login until the owner sets a username, and the README command publishes port 80",
          "Eight CVEs published between 17 March and 22 October 2026, all assigned by third parties, with no vendor advisory, SECURITY.md or security.txt",
          "Infection Check, the prompt-injection audit before tool calls, ships turned off",
          "Empty allow-lists in the Telegram, WhatsApp and email integrations accept messages from anyone",
          "No public CI runs the 245 files under tests/. The only workflows publish Docker images and close inactive issues",
          "Minor releases v2.11, v2.12 and v2.13 removed or changed behaviour on release day, one with no compatibility alias"
        ],
        "agentNotes": [
          "Set a UI login and password in Settings before publishing the port or opening a tunnel. The default has none",
          "Fill `allowed_users`, `allowed_numbers` or `sender_whitelist` before enabling a channel. An empty list accepts every sender",
          "Enable the Infection Check plugin when the agent reads mail, web pages or MCP results. It ships disabled",
          "Run v2.12 or later. It fixes a Telegram webhook authentication bypass and a WhatsApp media path traversal",
          "Call `POST /api_message` with the `X-API-KEY` header. The token changes when the UI login or password changes"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 49.7
          }
        ],
        "editorialScores": {
          "ergonomics": 62,
          "maintenance": 75,
          "payments": 90,
          "reliability": 57,
          "schema": 64,
          "security": 54,
          "transparency": 66
        },
        "provenanceScore": 61,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-04",
            "maintenance": "2026-11-04",
            "payments": "2026-11-04",
            "reliability": "2026-11-04",
            "schema": "2026-11-04",
            "security": "2026-11-04",
            "transparency": "2026-11-04"
          },
          "last": "2026-11-04",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-04",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "docker run -p 80:80 -v a0_usr:/a0/usr agent0ai/agent-zero   # or: curl -fsSL https://bash.agent-zero.ai | bash"
      },
      "letme": {
        "capability": "https://letme.dev/agent.harness",
        "tool": "https://letme.dev/agent-zero"
      },
      "area": "frameworks",
      "provenance": {
        "legalEntity": "Agent Zero, s.r.o.",
        "domain": "agent-zero.ai",
        "domainRegistered": "",
        "endpointOnVendorDomain": null,
        "terms": "",
        "privacy": "",
        "statusPage": "",
        "changelog": "https://github.com/agent0ai/agent-zero/releases",
        "securityTxt": "none",
        "checked": "2026-11-04",
        "notes": [
          "The site footer names Agent Zero, s.r.o., ID no. 231 46 508, Nové sady 988/2, 602 00 Brno, Czech Republic, and the `LICENSE` file carries the same company's copyright.",
          "No terms or privacy policy for the software was found. The site's terms page covers its community platform and its cookie page covers the website, so neither is linked here and the MIT licence stands in.",
          "`/.well-known/security.txt` on www.agent-zero.ai answered 404 on 12 October 2026, and the repository still had no SECURITY.md on 4 November 2026.",
          "robots.txt on www.agent-zero.ai answered 404 again on 4 November 2026, read as no rules. agent-zero.ai redirects to www.agent-zero.ai.",
          "There is no hosted endpoint. An instance answers on its owner's own host.",
          "The domain's registration date was not looked up."
        ],
        "score": 61
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/agent-zero.json",
      "live": {
        "slug": "agent-zero",
        "versions": [
          {
            "registry": "github",
            "name": "agent0ai/agent-zero",
            "version": "v2.16",
            "released": "2026-11-17",
            "seenAt": "2026-11-18T17:24:29.260972053Z"
          }
        ],
        "githubStars": 19914,
        "securityTxt": {
          "url": "https://agent-zero.ai/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-18T16:31:46.773038105Z"
        },
        "llmsTxt": {
          "url": "https://www.agent-zero.ai/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-18T16:12:54.320011063Z"
        },
        "domain": {
          "domain": "agent-zero.ai",
          "registered": "2025-01-26",
          "source": "https://rdap.identitydigital.services/rdap/domain/agent-zero.ai",
          "checkedAt": "2026-11-15T15:23:05.280627052Z"
        },
        "github": {
          "repo": "agent0ai/agent-zero",
          "checkedAt": "2026-11-16T11:40:33.941832038Z",
          "stars": 19876,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-11-16T09:58:16Z",
          "openIssues": 60,
          "openPRs": 111,
          "issuesOpened90d": 73,
          "issuesClosed90d": 93,
          "prsMerged90d": 31,
          "ci": {
            "branch": "main",
            "runs": 50,
            "success": 46,
            "failure": 3,
            "other": 1,
            "latest": "success",
            "latestAt": "2026-11-01T23:52:44Z"
          },
          "replies": {
            "sampled": 25,
            "unanswered": 22,
            "medianDays": 0.6
          }
        },
        "updatedAt": "2026-11-18T17:24:29.260972053Z"
      }
    },
    "answer": "boxes.dev scores 53.2 (D) on agent readiness against Agent Zero's 49.7 (D), and leads in 1 of 7 scored categories. Agent Zero leads on reliability, schema \u0026 documentation, payments \u0026 pricing and maintenance \u0026 community.",
    "b": {
      "slug": "boxes-dev",
      "name": "boxes.dev",
      "vendor": "Boxes, Inc.",
      "vendorUrl": "https://boxes.dev",
      "company": "boxes.dev",
      "kind": "mcp",
      "category": "agent-harnesses",
      "summary": "boxes.dev runs Claude Code and Codex on cloud Linux devboxes that copy a developer's environment. Tasks start from the desktop and mobile apps, the `dvb` CLI, Slack, Linear, schedules, an automation API or a remote MCP server.",
      "url": "https://www.anchorterminal.com/tools/boxes-dev",
      "markdownUrl": "https://www.anchorterminal.com/tools/boxes-dev.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/boxes-dev.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/boxes-dev.json",
      "dns": "boxes-dev.grade.anchorterminal.com",
      "license": "Proprietary. The service runs under the Common Paper Cloud Service Agreement 2.1, and the `@boxes-dev/cli` package is marked UNLICENSED",
      "transports": [
        "streamable-http",
        "http"
      ],
      "remoteUrl": "https://api.boxes.dev/mcp",
      "packages": [
        {
          "registry": "npm",
          "name": "@boxes-dev/cli"
        }
      ],
      "auth": "mixed",
      "authNotes": "The remote MCP server uses OAuth through mcp.boxes.dev, with scopes `threads:read`, `threads:write`, `events:subscribe` and `settings:write` and a per-project grant chosen by the user. Automation endpoints use a bearer secret generated per automation in the desktop app. Account sign-in is Google or Apple.",
      "pricing": "freemium",
      "pricingNotes": "Trial free with 20 box-hours. Starter $19, Pro $99 and Max $249 a seat a month with 50, 300 and 750 box-hours, then $0.40 a box-hour. A box-hour is one hour awake on a 4 vCPU, 8 GiB devbox. Sleeping devboxes are free. Some teams must add a payment method before the trial.",
      "priceSummary": "$0.40 / unit",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 on the pricing, plans, automation API or MCP connection pages (checked 2026-11-18). Paid plans bill a payment method on file monthly.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://boxes.dev/help",
      "llmsTxt": "https://boxes.dev/llms.txt",
      "capabilities": [
        "agent.harness",
        "agent.multi-agent",
        "sandbox.persist"
      ],
      "tags": [
        "hosted",
        "cloud-agent",
        "closed-source",
        "mcp",
        "remote-mcp",
        "oauth",
        "llms-txt",
        "cli",
        "free-tier",
        "idempotency",
        "yc"
      ],
      "lastRelease": "2026-11-17",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 53.2,
        "grade": "D",
        "agentReady": false,
        "rank": 1055,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 45,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 60,
          "maintenance": 48,
          "payments": 50,
          "reliability": 32,
          "schema": 57,
          "security": 69,
          "transparency": 60
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "warnings": [
          {
            "kind": "operator-unidentified",
            "name": "Operator not identified",
            "text": "Boxes' terms name Boxes, Inc. under California law with only an email address for notices, and no place of registration, registration number or street address. OpenCorporates refused our reader (403), so no register entry was found.",
            "deduct": 0,
            "capGrade": "B",
            "since": "2026-11-18",
            "sources": [
              "https://boxes.dev/terms",
              "https://boxes.dev/privacy"
            ]
          }
        ],
        "verdict": "An outside agent can start Claude Code or Codex tasks on cloud devboxes through an OAuth MCP server with four scopes, or an automation endpoint with idempotency keys. No status page, SLA or tool schema could be read, and every route starts with a person setting up a project in the app.",
        "bestFor": "Developers who want Claude Code or Codex running on cloud copies of their dev environment, started from Slack, Linear, a schedule, an API call or another assistant.",
        "strengths": [
          "OAuth MCP server with four scopes and a per-project grant, and approvals stay in the boxes.dev apps",
          "Automation runs take an `Idempotency-Key` and return the original run on a retry",
          "Named error codes for capacity and unavailable targets, with the action to take",
          "Public plan prices and $0.40 per box-hour for extra usage, with a 20 box-hour trial",
          "Valid security.txt and a disclosure policy with safe harbour"
        ],
        "weaknesses": [
          "No status page, incident history or SLA found",
          "No OpenAPI document, and the MCP tool list needs an OAuth token to read",
          "Every route needs a person to sign up and set up a project in the desktop app first",
          "The API status endpoint reports launch progress only, not the agent's result",
          "No changelog and no deprecation policy for the API or MCP server"
        ],
        "agentNotes": [
          "Send a new `Idempotency-Key` for each intended run, and the same key and body when you retry an uncertain request",
          "Wait for status `thread_ready` before you use a returned `devboxId` as a target",
          "If you get 409 `active_fork_limit_reached`, free an awake devbox or wait. The plan's awake-devbox cap is full",
          "Read the thread in boxes.dev for the agent's answer. The status URL does not return it",
          "Ask for `threads:read` only unless the task needs to start agents or change settings"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 53.2
          }
        ],
        "editorialScores": {
          "ergonomics": 60,
          "maintenance": 48,
          "payments": 50,
          "reliability": 32,
          "schema": 57,
          "security": 69,
          "transparency": 54
        },
        "provenanceScore": 66,
        "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",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "npm install -g @boxes-dev/cli \u0026\u0026 dvb setup",
        "claudeCode": "claude mcp add boxes-dev --transport http https://api.boxes.dev/mcp",
        "config": {
          "mcpServers": {
            "boxes-dev": {
              "url": "https://api.boxes.dev/mcp"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/agent.harness",
        "tool": "https://letme.dev/boxes-dev"
      },
      "area": "frameworks",
      "unitPrices": [
        {
          "item": "Box-hour beyond the plan allowance",
          "unit": "compute-unit",
          "usd": 0.4,
          "note": "One hour awake on a 4 vCPU, 8 GiB devbox. Larger devboxes use more box-hours an hour"
        },
        {
          "item": "Pro plan",
          "unit": "seat-month",
          "usd": 99,
          "note": "300 box-hours included per seat"
        }
      ],
      "provenance": {
        "legalEntity": "Boxes, Inc.",
        "domain": "boxes.dev",
        "domainRegistered": "",
        "endpointOnVendorDomain": true,
        "terms": "https://boxes.dev/terms",
        "privacy": "https://boxes.dev/privacy",
        "statusPage": "",
        "changelog": "",
        "securityTxt": "valid",
        "checked": "2026-11-18",
        "notes": [
          "boxes.dev/robots.txt allows all agents. api.boxes.dev/robots.txt answered 404, so it publishes no rules. trust.boxes.dev/robots.txt answered 200 with no rules.",
          "The terms (last updated 20 October 2026) adopt the Common Paper Cloud Service Agreement Standard Terms 2.1, delete its machine-learning section, choose California law and give founders@boxes.dev as the notice address.",
          "The privacy policy is dated 21 October 2026. Contact privacy@boxes.dev.",
          "security.txt names security@boxes.dev, points to boxes.dev/security and expires on 2 June 2027.",
          "No status page found. The domain's registration date was not looked up."
        ],
        "score": 66
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/boxes-dev.json",
      "live": {
        "slug": "boxes-dev",
        "probe": {
          "target": "https://api.boxes.dev/mcp",
          "method": "mcp-initialize",
          "lastAt": "2026-11-18T21:50:36.474275251Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 453,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 453,
          "p95ms24h": 1740,
          "samples24h": 3,
          "samples30d": 3,
          "days": [
            {
              "date": "2026-11-18",
              "probes": 3,
              "ok": 3
            }
          ],
          "since": "2026-11-18T21:37:40.384341882Z"
        },
        "updatedAt": "2026-11-18T21:50:36.474275251Z"
      },
      "streak": {
        "days": 0,
        "from": "2026-11-18",
        "sinceWatching": true,
        "best": 0
      }
    },
    "edges": [
      {
        "by": 40,
        "category": "payments",
        "leads": "agent-zero",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "Read with the self-hosted rule. No payment protocol in the source (0). Free under MIT with nothing to buy for the software, so 20, 20 and 20 on the last three lines. It starts with one Docker command and no account. Model usage is billed by whichever provider the owner configures, or costs nothing with a local model. The vendor's site also describes a beta LLM API whose daily quota depends on staking its A0T token. That is separate from the software and not scored. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.",
          "b": "No x402, MPP or L402 (0). Plan prices are public ($19, $99 and $249 a seat a month) and extra usage is $0.40 a box-hour, with a box-hour defined as one hour of a 4 vCPU, 8 GiB devbox (30). A free trial of 20 box-hours. The help page says some teams must add a payment method before starting, so a card-free start is not certain (20 of 30). A person signs in with Google or Apple and approves the OAuth grant or creates the automation secret in the desktop app (0). 0+30+20+0 = 50."
        },
        "scores": {
          "a": 90,
          "b": 50
        }
      },
      {
        "by": 27,
        "category": "maintenance",
        "leads": "agent-zero",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "v2.15 was tagged on 1 November 2026, 3 days before this check (30). Seven releases from 6 August, v2.9 on 12 August to v2.15, read from the clone's tags (20). Of the 40 newest open items read on 12 October, 16 are issues and 14 of those have no comment. Three security reports filed as issues were closed as completed, one in five days and two after three months. GitHub's issue pages weren't read on 4 November, so this is per the 12 October check (10 of 25). The Docker image, the desktop Launcher, the install scripts and the A0 CLI connector come from the same organisation, and the v2.14 notes point the README's Launcher links to v1.9 (10 of 15). A Docker publish workflow builds images from tags, and the v2.14 notes raise dependency security floors for aiohttp, anyio, urllib3, filelock, fsspec and multidict. No public test CI (5 of 10). 30 + 20 + 10 + 10 + 5 = 75.",
          "b": "Closed service. CLI `@boxes-dev/cli` 1.0.1134 published on 17 November 2026 (30). Only one dated product update was found, on 27 October 2026, and earlier CLI versions' dates were not read, so three releases in 90 days are not established (0). A support address, an in-app chat and a blog, with no public tracker or changelog (8 of 25). A CLI but no SDK, and no entry in the official MCP registry was looked for (5 of 15). The CLI is published from GitHub Actions with npm trusted publishing and signatures (5 of 10). 30+0+8+5+5 = 48."
        },
        "scores": {
          "a": 75,
          "b": 48
        }
      },
      {
        "by": 25,
        "category": "reliability",
        "leads": "agent-zero",
        "name": "Reliability",
        "reasons": {
          "a": "Read with the local-software lines, as software the owner runs. Installs from the `agent0ai/agent-zero` Docker image, an install script, or a desktop Launcher with builds for macOS, Linux and Windows on x86 and ARM64. The README says it runs wherever Docker runs. The image registry page was not read (17 of 20). The repository holds 245 files under tests/ on 4 November, and its only two workflows still publish Docker images and close inactive issues. The publish workflow runs no tests, so no public CI run shows them passing (5 of 25, a partial kept). 139 open issues and pull requests on 12 October 2026, per that check (GitHub's pages and API weren't read on 4 November). Open reports from September include a crash of `run_ui` after a failed memory consolidation (#1909), a browser worker that hangs the agent turn (#1923) and truncated backups (#1904), each with no reply or one, and a workflow closes anything inactive for 90 days (11 of 25). Release notes for v2.11, v2.12 and v2.13 carry a Breaking Changes section, but breaking changes ship in minor versions, so the numbering is not semver (9 of 15). v2.15, past 1.0 (15).",
          "b": "Hosted reading, for the remote MCP server at api.boxes.dev/mcp and the automation run endpoints. No status page found. The site footer says \"All systems normal\" with no link, and the trust centre at trust.boxes.dev draws in a script our reader could not run (0). No readable incident history (5). No request rate limits found. Plans cap awake devboxes (3 on the trial, 5 to 25 on paid plans), and the API answers 409 `active_fork_limit_reached` at the cap (5 of 15). The automation API takes an `Idempotency-Key` and returns the original run on a retry with `idempotentReplay: true`, and the MCP connection retries a lost start or message with the same request key. No `Retry-After` or backoff guidance found (12 of 15). No SLA found (0). Neither the MCP connection nor the automation API is marked beta, and the product launched in June 2026 per its own blog (10). 0+5+5+12+0+10 = 32."
        },
        "scores": {
          "a": 57,
          "b": 32
        }
      },
      {
        "by": 15,
        "category": "security",
        "leads": "boxes-dev",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Harness reading of the framework checklist, the one the Goose calibration dossier uses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No usage telemetry was found in the source. An update check, on by default, posts the version and a 20-character SHA-256 hash of a random per-install id to api.agent-zero.ai. The Update Checker settings page says only that ID and the version are sent and has an off switch. Something still leaves the machine by default, so the partial is kept (22). The agent works inside a Docker container built on Kali Linux and runs as root there. Tool Access can block tools by project or profile and defaults to allow, host access through the A0 CLI is scoped by read, write and execute permissions, and no approval step was found before a shell command, a file deletion or an outgoing message. The web interface has no login until a username is set (10). Infection Check audits the agent's reasoning with a second model before each tool call and ships disabled. Scanners check plugins, skills and MCP servers before install. The channel allow-lists accept every sender when empty, and the email filter matches the claimed From address only, which the plugin README states (7). Chat logs, visible tool steps and Time Travel snapshots, with no per-call audit log. Per-process log files were removed in v2.5 (9). No SECURITY.md on 4 November, security.txt answered 404 on 12 October, and none of the eight CVEs published from 17 March to 22 October 2026 came from the vendor (VulDB, VulnCheck, MITRE and CISA assigned them). A security-review ledger in the repository records two findings, and the v2.12 notes name both fixes (6, a partial kept).",
          "b": "OAuth for the MCP server, with protected-resource metadata naming mcp.boxes.dev and four scopes (`threads:read`, `threads:write`, `events:subscribe`, `settings:write`), a per-project grant and removal from settings. Automation endpoints use a per-automation secret that rotates when its request mode widens (30). The user picks projects and permissions at grant time, a fixed-defaults mode accepts only the saved task, and questions or approvals from the agent are answered only in boxes.dev, never through the MCP connection (15). Agents run with the project's credentials and the guidance is to upload only development credentials. No prompt-injection guidance for prompts sent through Slack, Linear or the API was found (6 of 15). Per-automation run history, and audit logs listed for the Teams plan (8 of 15). A valid security.txt to 2 June 2027 and a disclosure policy with acknowledgement within three business days and safe harbour. No bug bounty and no certification found (10 of 20). 30+15+6+8+10 = 69."
        },
        "scores": {
          "a": 54,
          "b": 69
        }
      },
      {
        "by": 7,
        "category": "schema",
        "leads": "agent-zero",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "Harness reading of the lines, as the Goose calibration dossier does. No OpenAPI file. The connectivity page lists five external endpoints and the `X-API-KEY` header, then sends readers to the source or DeepWiki for request and response details. Each API handler and tool has a `.dox.md` contract file in the repository, and the MCP client JSON shape is documented (10 of 25). llms.txt at www.agent-zero.ai, and AGENTS.md contract files across the repository (10). Guides say which path to use for a need, with tables that separate the browser, the host connector, MCP and A2A (14 of 20). The v2.12 notes say 15 bundled tools gained argument descriptions in non-strict schemas, and plugin settings are typed YAML with commented examples (8 of 15). Guides carry worked examples and a troubleshooting page, with no documented error responses for the external API (9 of 15). Dated notes on every GitHub release and a release article for each version on the site, with no version prefix on API routes (13 of 15).",
          "b": "No OpenAPI document, and the MCP tool list could not be read because the endpoint answers 401 before `initialize` without an OAuth token. The automation API's request and response fields are documented in prose tables (5 of 25). llms.txt with every help page listed (10). The help pages say when to target a new devbox, an existing devbox or an existing thread, when to steer a busy agent and when to wake a devbox first (16). Field tables with enum values such as `backend` (`codex` or `claude`), `delivery` (`steer` or `next`) and four run statuses, and unknown fields are rejected. The MCP schemas themselves were not seen (9 of 15). curl examples and named errors such as 409 `devbox_unavailable`, 409 `thread_unavailable` and 503 `devbox_wake_failed`, with what each means (12). `/v1` in the API path on the home page, a single dated product update of 27 October 2026 and no changelog (5 of 15). 5+10+16+9+12+5 = 57."
        },
        "scores": {
          "a": 64,
          "b": 57
        }
      }
    ],
    "facts": [
      {
        "a": "Agent harness",
        "b": "MCP server",
        "name": "Kind"
      },
      {
        "a": "Agent Zero, s.r.o.",
        "b": "Boxes, Inc.",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "https://api.boxes.dev/mcp",
        "name": "Hosted endpoint"
      },
      {
        "a": "",
        "b": "Streamable HTTP, HTTP",
        "name": "Transports"
      },
      {
        "a": "None",
        "b": "OAuth or key",
        "name": "Auth"
      },
      {
        "a": "Free",
        "b": "Freemium",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "MIT",
        "b": "Proprietary. The service runs under the Common Paper Cloud Service Agreement 2.1, and the `@boxes-dev/cli` package is marked UNLICENSED",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-11-01",
        "b": "2026-11-17",
        "name": "Last release"
      },
      {
        "a": "no document linked",
        "b": "2026-10-20",
        "name": "Terms last updated"
      },
      {
        "a": "no document linked",
        "b": "2026-10-21",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Customer content may train models"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "19k stars",
        "b": "none",
        "name": "Popularity"
      }
    ],
    "faq": [
      {
        "answer": "boxes.dev scores 53.2 (D) on agent readiness against Agent Zero's 49.7 (D), and leads in 1 of 7 scored categories. Agent Zero leads on reliability, schema \u0026 documentation, payments \u0026 pricing and maintenance \u0026 community.",
        "question": "Which is better for AI agents, Agent Zero or boxes.dev?"
      },
      {
        "answer": "No hosted endpoint is listed for Agent Zero. boxes.dev has a hosted endpoint at https://api.boxes.dev/mcp.",
        "question": "Can an agent call Agent Zero and boxes.dev without installing anything?"
      },
      {
        "answer": "Agent Zero is open source (MIT). No open-source release is listed for boxes.dev.",
        "question": "Are Agent Zero and boxes.dev open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 57 against 32",
          "Schema \u0026 documentation, 64 against 57",
          "Payments \u0026 pricing, 90 against 50",
          "Maintenance \u0026 community, 75 against 48"
        ],
        "also": [
          "No key needed to call it",
          "Open source"
        ],
        "goodFor": "A technical owner who wants an agent with its own Linux machine, reachable from Telegram, WhatsApp or email, with scheduled tasks and editable memory.",
        "slug": "agent-zero",
        "watchFor": "No approval step before shell commands, file changes or outgoing messages. Tool Access defaults to allow"
      },
      {
        "aheadOn": [
          "Security \u0026 auth, 69 against 54"
        ],
        "also": [
          "A hosted endpoint, with nothing to install",
          "No incidents deducted, where Agent Zero loses 15 points for them"
        ],
        "goodFor": "Developers who want Claude Code or Codex running on cloud copies of their dev environment, started from Slack, Linear, a schedule, an API call or another assistant.",
        "slug": "boxes-dev",
        "watchFor": "No status page, incident history or SLA found"
      }
    ],
    "history": {
      "agent-zero": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 3.7,
          "from": 46,
          "fromGrade": "D",
          "to": 49.7,
          "toGrade": "D"
        },
        {
          "causes": [
            "correction"
          ],
          "date": "2026-11-04",
          "delta": -8.6,
          "from": 54.6,
          "fromGrade": "C",
          "to": 46,
          "toGrade": "D"
        },
        {
          "causes": [
            "evidence"
          ],
          "date": "2026-10-28",
          "delta": 0.3,
          "from": 54.3,
          "fromGrade": "C",
          "to": 54.6,
          "toGrade": "C"
        }
      ],
      "boxes-dev": null
    },
    "job": {
      "capability": "agent.harness",
      "name": "Agent harnesses"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-aider.json",
        "title": "Agent Zero vs Aider",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-aider"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-amp.json",
        "title": "Agent Zero vs Amp",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-amp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-antigravity-cli.json",
        "title": "Agent Zero vs Antigravity CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-antigravity-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-auggie.json",
        "title": "Agent Zero vs Auggie CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-auggie"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-axlr.json",
        "title": "Agent Zero vs AXLR",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-axlr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-claude-code.json",
        "title": "Agent Zero vs Claude Code",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-claude-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-click-agents.json",
        "title": "Agent Zero vs Click",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-click-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-cline.json",
        "title": "Agent Zero vs Cline",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-cline"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-conductor.json",
        "title": "Agent Zero vs Conductor",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-conductor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-crush.json",
        "title": "Agent Zero vs Crush",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-cursor-cli.json",
        "title": "Agent Zero vs Cursor CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-cursor-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-harness.json",
        "title": "Agent Zero vs DeepSeek Harness (dsh)",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-harness"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-superagent.json",
        "title": "Agent Zero vs dsh-superagent (DeepSeek)",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-superagent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-devin.json",
        "title": "Agent Zero vs Devin",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-devin"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-droid-cli.json",
        "title": "Agent Zero vs Droid CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-droid-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi.json",
        "title": "Agent Zero vs Pi",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-emdash.json",
        "title": "Agent Zero vs Emdash",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-emdash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-friday-work.json",
        "title": "Agent Zero vs Friday",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-friday-work"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-gemini-cli.json",
        "title": "Agent Zero vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-github-copilot-cli.json",
        "title": "Agent Zero vs GitHub Copilot CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-github-copilot-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-goose.json",
        "title": "Agent Zero vs goose",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-goose"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2.json",
        "title": "Agent Zero vs Harness²",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-harnessrouter.json",
        "title": "Agent Zero vs HarnessRouter",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-harnessrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-jules.json",
        "title": "Agent Zero vs Jules",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-junie.json",
        "title": "Agent Zero vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-junie"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-kilo-code-cli.json",
        "title": "Agent Zero vs Kilo Code CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-kilo-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-kimi-code-cli.json",
        "title": "Agent Zero vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-kimi-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-kiro-cli.json",
        "title": "Agent Zero vs Kiro CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-kiro-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-letta.json",
        "title": "Agent Zero vs Letta",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-letta"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-mini-swe-agent.json",
        "title": "Agent Zero vs mini-swe-agent",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-mini-swe-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-minimax-code.json",
        "title": "Agent Zero vs MiniMax Code",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-minimax-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-mistral-vibe-cli.json",
        "title": "Agent Zero vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-muse-code.json",
        "title": "Agent Zero vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-openai-agents-api.json",
        "title": "Agent Zero vs OpenAI Agents API",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-openai-agents-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-openai-codex.json",
        "title": "Agent Zero vs OpenAI Codex",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-openai-codex"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-opencode.json",
        "title": "Agent Zero vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-openhands.json",
        "title": "Agent Zero vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-openmausbot.json",
        "title": "Agent Zero vs OpenMausBot",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-openmausbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-orca.json",
        "title": "Agent Zero vs Orca",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-orca"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-paseo.json",
        "title": "Agent Zero vs Paseo",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-paseo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-prime-agent.json",
        "title": "Agent Zero vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-qoder-cli.json",
        "title": "Agent Zero vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-qwen-code.json",
        "title": "Agent Zero vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-reflection-mirror.json",
        "title": "Agent Zero vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-rovo-dev-cli.json",
        "title": "Agent Zero vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-sculptor.json",
        "title": "Agent Zero vs Sculptor",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-sculptor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-t3-code.json",
        "title": "Agent Zero vs T3 Code",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-t3-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-traycer.json",
        "title": "Agent Zero vs Traycer",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-traycer"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-unstoppable.json",
        "title": "Agent Zero vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-unstoppable"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-verdent.json",
        "title": "Agent Zero vs Verdent",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-verdent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-vibe-trading.json",
        "title": "Agent Zero vs Vibe-Trading",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-vibe-trading"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-warp.json",
        "title": "Agent Zero vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/aider-vs-boxes-dev.json",
        "title": "Aider vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/aider-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amp-vs-boxes-dev.json",
        "title": "Amp vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/amp-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-boxes-dev.json",
        "title": "Antigravity CLI vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/auggie-vs-boxes-dev.json",
        "title": "Auggie CLI vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-boxes-dev.json",
        "title": "AXLR vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-claude-code.json",
        "title": "boxes.dev vs Claude Code",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-claude-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-click-agents.json",
        "title": "boxes.dev vs Click",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-click-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-cline.json",
        "title": "boxes.dev vs Cline",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-cline"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-conductor.json",
        "title": "boxes.dev vs Conductor",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-conductor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-crush.json",
        "title": "boxes.dev vs Crush",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-cursor-cli.json",
        "title": "boxes.dev vs Cursor CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-cursor-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-harness.json",
        "title": "boxes.dev vs DeepSeek Harness (dsh)",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-harness"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-superagent.json",
        "title": "boxes.dev vs dsh-superagent (DeepSeek)",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-superagent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-devin.json",
        "title": "boxes.dev vs Devin",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-devin"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-droid-cli.json",
        "title": "boxes.dev vs Droid CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-droid-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-earendil-pi.json",
        "title": "boxes.dev vs Pi",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-earendil-pi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-emdash.json",
        "title": "boxes.dev vs Emdash",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-emdash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-friday-work.json",
        "title": "boxes.dev vs Friday",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-friday-work"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-gemini-cli.json",
        "title": "boxes.dev vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-github-copilot-cli.json",
        "title": "boxes.dev vs GitHub Copilot CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-github-copilot-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-goose.json",
        "title": "boxes.dev vs goose",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-goose"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-harness2.json",
        "title": "boxes.dev vs Harness²",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-harnessrouter.json",
        "title": "boxes.dev vs HarnessRouter",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-harnessrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-jules.json",
        "title": "boxes.dev vs Jules",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-junie.json",
        "title": "boxes.dev vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-junie"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-kilo-code-cli.json",
        "title": "boxes.dev vs Kilo Code CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-kilo-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-kimi-code-cli.json",
        "title": "boxes.dev vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-kimi-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-kiro-cli.json",
        "title": "boxes.dev vs Kiro CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-kiro-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-letta.json",
        "title": "boxes.dev vs Letta",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-letta"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-mini-swe-agent.json",
        "title": "boxes.dev vs mini-swe-agent",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-mini-swe-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-minimax-code.json",
        "title": "boxes.dev vs MiniMax Code",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-minimax-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-mistral-vibe-cli.json",
        "title": "boxes.dev vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-muse-code.json",
        "title": "boxes.dev vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-openai-agents-api.json",
        "title": "boxes.dev vs OpenAI Agents API",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-openai-agents-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-openai-codex.json",
        "title": "boxes.dev vs OpenAI Codex",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-openai-codex"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-opencode.json",
        "title": "boxes.dev vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-openhands.json",
        "title": "boxes.dev vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-openmausbot.json",
        "title": "boxes.dev vs OpenMausBot",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-openmausbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-orca.json",
        "title": "boxes.dev vs Orca",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-orca"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-paseo.json",
        "title": "boxes.dev vs Paseo",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-paseo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-prime-agent.json",
        "title": "boxes.dev vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-qoder-cli.json",
        "title": "boxes.dev vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-qwen-code.json",
        "title": "boxes.dev vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-reflection-mirror.json",
        "title": "boxes.dev vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-rovo-dev-cli.json",
        "title": "boxes.dev vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-sculptor.json",
        "title": "boxes.dev vs Sculptor",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-sculptor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-t3-code.json",
        "title": "boxes.dev vs T3 Code",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-t3-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-traycer.json",
        "title": "boxes.dev vs Traycer",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-traycer"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-unstoppable.json",
        "title": "boxes.dev vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-unstoppable"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-verdent.json",
        "title": "boxes.dev vs Verdent",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-verdent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-vibe-trading.json",
        "title": "boxes.dev vs Vibe-Trading",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-vibe-trading"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-warp.json",
        "title": "boxes.dev vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-relay-vs-boxes-dev.json",
        "title": "Agent Relay vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/agent-relay-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-clawboo.json",
        "title": "boxes.dev vs Clawboo",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-clawboo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-cli-manager.json",
        "title": "boxes.dev vs CLI Manager",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-cli-manager"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-harness-autonomous.json",
        "title": "boxes.dev vs Harness",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-herdr.json",
        "title": "boxes.dev vs herdr",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-paperclip.json",
        "title": "boxes.dev vs Paperclip",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-paperclip"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-parallax-agents.json",
        "title": "boxes.dev vs Parallax",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-parallax-agents"
      }
    ],
    "panel": null,
    "scores": [
      {
        "agent-zero": 57,
        "boxes-dev": 32,
        "by": 25,
        "edge": "agent-zero",
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "agent-zero": 64,
        "boxes-dev": 57,
        "by": 7,
        "edge": "agent-zero",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "agent-zero": 62,
        "boxes-dev": 60,
        "by": 2,
        "edge": "agent-zero",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "agent-zero": 54,
        "boxes-dev": 69,
        "by": 15,
        "edge": "boxes-dev",
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "agent-zero": 90,
        "boxes-dev": 50,
        "by": 40,
        "edge": "agent-zero",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "agent-zero": 75,
        "boxes-dev": 48,
        "by": 27,
        "edge": "agent-zero",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "agent-zero": 64,
        "boxes-dev": 60,
        "by": 4,
        "edge": "agent-zero",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "boxes.dev scores 53.2 (D) on agent readiness against Agent Zero's 49.7 (D), and leads in 1 of 7 scored categories. Agent Zero leads on reliability, schema \u0026 documentation, payments \u0026 pricing and maintenance \u0026 community. Both do agent harnesses.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "agent-zero": "Self-hosted under the MIT licence, with seven releases from 12 August to 1 November 2026 and breaking changes listed in minor-release notes. The agent runs shell commands in its container with no approval step, the web interface has no login by default, and eight CVEs from the past year were published by third parties with no vendor advisory.",
      "boxes-dev": "An outside agent can start Claude Code or Codex tasks on cloud devboxes through an OAuth MCP server with four scopes, or an automation endpoint with idempotency keys. No status page, SLA or tool schema could be read, and every route starts with a person setting up a project in the app."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/agent-zero-vs-boxes-dev",
    "json": "https://www.anchorterminal.com/compare/agent-zero-vs-boxes-dev.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/agent-zero-vs-boxes-dev.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/agent-zero-vs-boxes-dev.min.md"
  },
  "markdown": "boxes.dev scores 53.2 (D) on agent readiness against Agent Zero's 49.7 (D), and leads in 1 of 7 scored categories. Agent Zero leads on reliability, schema \u0026 documentation, payments \u0026 pricing and maintenance \u0026 community. Both do agent harnesses.\n\n- Agent Zero: grade D, 49.7/100, rank #1168 of 1557. Markdown https://www.anchorterminal.com/tools/agent-zero.md · JSON https://www.anchorterminal.com/api/v1/tools/agent-zero.json\n- boxes.dev: grade D, 53.2/100, rank #1055 of 1557. Markdown https://www.anchorterminal.com/tools/boxes-dev.md · JSON https://www.anchorterminal.com/api/v1/tools/boxes-dev.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1767 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### Agent Zero (D)\n\nGood for: A technical owner who wants an agent with its own Linux machine, reachable from Telegram, WhatsApp or email, with scheduled tasks and editable memory.\n\nAhead on:\n- Reliability, 57 against 32\n- Schema \u0026 documentation, 64 against 57\n- Payments \u0026 pricing, 90 against 50\n- Maintenance \u0026 community, 75 against 48\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: No approval step before shell commands, file changes or outgoing messages. Tool Access defaults to allow\n\n### boxes.dev (D)\n\nGood for: Developers who want Claude Code or Codex running on cloud copies of their dev environment, started from Slack, Linear, a schedule, an API call or another assistant.\n\nAhead on:\n- Security \u0026 auth, 69 against 54\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- No incidents deducted, where Agent Zero loses 15 points for them\n\nWatch for: No status page, incident history or SLA found\n\n\n## Why the edge\n\n### Payments \u0026 pricing: Agent Zero +40\n\n- Agent Zero (90): Read with the self-hosted rule. No payment protocol in the source (0). Free under MIT with nothing to buy for the software, so 20, 20 and 20 on the last three lines. It starts with one Docker command and no account. Model usage is billed by whichever provider the owner configures, or costs nothing with a local model. The vendor's site also describes a beta LLM API whose daily quota depends on staking its A0T token. That is separate from the software and not scored. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.\n- boxes.dev (50): No x402, MPP or L402 (0). Plan prices are public ($19, $99 and $249 a seat a month) and extra usage is $0.40 a box-hour, with a box-hour defined as one hour of a 4 vCPU, 8 GiB devbox (30). A free trial of 20 box-hours. The help page says some teams must add a payment method before starting, so a card-free start is not certain (20 of 30). A person signs in with Google or Apple and approves the OAuth grant or creates the automation secret in the desktop app (0). 0+30+20+0 = 50.\n\n### Maintenance \u0026 community: Agent Zero +27\n\n- Agent Zero (75): v2.15 was tagged on 1 November 2026, 3 days before this check (30). Seven releases from 6 August, v2.9 on 12 August to v2.15, read from the clone's tags (20). Of the 40 newest open items read on 12 October, 16 are issues and 14 of those have no comment. Three security reports filed as issues were closed as completed, one in five days and two after three months. GitHub's issue pages weren't read on 4 November, so this is per the 12 October check (10 of 25). The Docker image, the desktop Launcher, the install scripts and the A0 CLI connector come from the same organisation, and the v2.14 notes point the README's Launcher links to v1.9 (10 of 15). A Docker publish workflow builds images from tags, and the v2.14 notes raise dependency security floors for aiohttp, anyio, urllib3, filelock, fsspec and multidict. No public test CI (5 of 10). 30 + 20 + 10 + 10 + 5 = 75.\n- boxes.dev (48): Closed service. CLI `@boxes-dev/cli` 1.0.1134 published on 17 November 2026 (30). Only one dated product update was found, on 27 October 2026, and earlier CLI versions' dates were not read, so three releases in 90 days are not established (0). A support address, an in-app chat and a blog, with no public tracker or changelog (8 of 25). A CLI but no SDK, and no entry in the official MCP registry was looked for (5 of 15). The CLI is published from GitHub Actions with npm trusted publishing and signatures (5 of 10). 30+0+8+5+5 = 48.\n\n### Reliability: Agent Zero +25\n\n- Agent Zero (57): Read with the local-software lines, as software the owner runs. Installs from the `agent0ai/agent-zero` Docker image, an install script, or a desktop Launcher with builds for macOS, Linux and Windows on x86 and ARM64. The README says it runs wherever Docker runs. The image registry page was not read (17 of 20). The repository holds 245 files under tests/ on 4 November, and its only two workflows still publish Docker images and close inactive issues. The publish workflow runs no tests, so no public CI run shows them passing (5 of 25, a partial kept). 139 open issues and pull requests on 12 October 2026, per that check (GitHub's pages and API weren't read on 4 November). Open reports from September include a crash of `run_ui` after a failed memory consolidation (#1909), a browser worker that hangs the agent turn (#1923) and truncated backups (#1904), each with no reply or one, and a workflow closes anything inactive for 90 days (11 of 25). Release notes for v2.11, v2.12 and v2.13 carry a Breaking Changes section, but breaking changes ship in minor versions, so the numbering is not semver (9 of 15). v2.15, past 1.0 (15).\n- boxes.dev (32): Hosted reading, for the remote MCP server at api.boxes.dev/mcp and the automation run endpoints. No status page found. The site footer says \"All systems normal\" with no link, and the trust centre at trust.boxes.dev draws in a script our reader could not run (0). No readable incident history (5). No request rate limits found. Plans cap awake devboxes (3 on the trial, 5 to 25 on paid plans), and the API answers 409 `active_fork_limit_reached` at the cap (5 of 15). The automation API takes an `Idempotency-Key` and returns the original run on a retry with `idempotentReplay: true`, and the MCP connection retries a lost start or message with the same request key. No `Retry-After` or backoff guidance found (12 of 15). No SLA found (0). Neither the MCP connection nor the automation API is marked beta, and the product launched in June 2026 per its own blog (10). 0+5+5+12+0+10 = 32.\n\n### Security \u0026 auth: boxes.dev +15\n\n- Agent Zero (54): Harness reading of the framework checklist, the one the Goose calibration dossier uses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No usage telemetry was found in the source. An update check, on by default, posts the version and a 20-character SHA-256 hash of a random per-install id to api.agent-zero.ai. The Update Checker settings page says only that ID and the version are sent and has an off switch. Something still leaves the machine by default, so the partial is kept (22). The agent works inside a Docker container built on Kali Linux and runs as root there. Tool Access can block tools by project or profile and defaults to allow, host access through the A0 CLI is scoped by read, write and execute permissions, and no approval step was found before a shell command, a file deletion or an outgoing message. The web interface has no login until a username is set (10). Infection Check audits the agent's reasoning with a second model before each tool call and ships disabled. Scanners check plugins, skills and MCP servers before install. The channel allow-lists accept every sender when empty, and the email filter matches the claimed From address only, which the plugin README states (7). Chat logs, visible tool steps and Time Travel snapshots, with no per-call audit log. Per-process log files were removed in v2.5 (9). No SECURITY.md on 4 November, security.txt answered 404 on 12 October, and none of the eight CVEs published from 17 March to 22 October 2026 came from the vendor (VulDB, VulnCheck, MITRE and CISA assigned them). A security-review ledger in the repository records two findings, and the v2.12 notes name both fixes (6, a partial kept).\n- boxes.dev (69): OAuth for the MCP server, with protected-resource metadata naming mcp.boxes.dev and four scopes (`threads:read`, `threads:write`, `events:subscribe`, `settings:write`), a per-project grant and removal from settings. Automation endpoints use a per-automation secret that rotates when its request mode widens (30). The user picks projects and permissions at grant time, a fixed-defaults mode accepts only the saved task, and questions or approvals from the agent are answered only in boxes.dev, never through the MCP connection (15). Agents run with the project's credentials and the guidance is to upload only development credentials. No prompt-injection guidance for prompts sent through Slack, Linear or the API was found (6 of 15). Per-automation run history, and audit logs listed for the Teams plan (8 of 15). A valid security.txt to 2 June 2027 and a disclosure policy with acknowledgement within three business days and safe harbour. No bug bounty and no certification found (10 of 20). 30+15+6+8+10 = 69.\n\n### Schema \u0026 documentation: Agent Zero +7\n\n- Agent Zero (64): Harness reading of the lines, as the Goose calibration dossier does. No OpenAPI file. The connectivity page lists five external endpoints and the `X-API-KEY` header, then sends readers to the source or DeepWiki for request and response details. Each API handler and tool has a `.dox.md` contract file in the repository, and the MCP client JSON shape is documented (10 of 25). llms.txt at www.agent-zero.ai, and AGENTS.md contract files across the repository (10). Guides say which path to use for a need, with tables that separate the browser, the host connector, MCP and A2A (14 of 20). The v2.12 notes say 15 bundled tools gained argument descriptions in non-strict schemas, and plugin settings are typed YAML with commented examples (8 of 15). Guides carry worked examples and a troubleshooting page, with no documented error responses for the external API (9 of 15). Dated notes on every GitHub release and a release article for each version on the site, with no version prefix on API routes (13 of 15).\n- boxes.dev (57): No OpenAPI document, and the MCP tool list could not be read because the endpoint answers 401 before `initialize` without an OAuth token. The automation API's request and response fields are documented in prose tables (5 of 25). llms.txt with every help page listed (10). The help pages say when to target a new devbox, an existing devbox or an existing thread, when to steer a busy agent and when to wake a devbox first (16). Field tables with enum values such as `backend` (`codex` or `claude`), `delivery` (`steer` or `next`) and four run statuses, and unknown fields are rejected. The MCP schemas themselves were not seen (9 of 15). curl examples and named errors such as 409 `devbox_unavailable`, 409 `thread_unavailable` and 503 `devbox_wake_failed`, with what each means (12). `/v1` in the API path on the home page, a single dated product update of 27 October 2026 and no changelog (5 of 15). 5+10+16+9+12+5 = 57.\n\n## Score by category\n\n| Category | Weight | Agent Zero | boxes.dev | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 57 | 32 | Agent Zero +25 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 64 | 57 | Agent Zero +7 |\n| Agent ergonomics | 13% | 62 | 60 | Agent Zero +2 |\n| Security \u0026 auth | 14% | 54 | 69 | boxes.dev +15 |\n| Payments \u0026 pricing | 10% | 90 | 50 | Agent Zero +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 75 | 48 | Agent Zero +27 |\n| Transparency \u0026 trust | 7% | 64 | 60 | Agent Zero +4 |\n| Negative events | ≤15 | -15 | 0 | |\n| **Total** | | **49.7 · D** | **53.2 · D** | |\n\n## Facts side by side\n\n| Fact | Agent Zero | boxes.dev |\n| --- | --- | --- |\n| Kind | Agent harness | MCP server |\n| Vendor | Agent Zero, s.r.o. | Boxes, Inc. |\n| Hosted endpoint | no (local only) | `https://api.boxes.dev/mcp` |\n| Transports |  | Streamable HTTP, HTTP |\n| Auth | None | OAuth or key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | MIT | Proprietary. The service runs under the Common Paper Cloud Service Agreement 2.1, and the `@boxes-dev/cli` package is marked UNLICENSED |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-11-01 | 2026-11-17 |\n| Terms last updated | no document linked | 2026-10-20 |\n| Privacy policy last updated | no document linked | 2026-10-21 |\n| Customer content may train models | not read yet | not found in the text |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n| Popularity | 19k stars | none |\n\n## How the scores have moved\n\n### Agent Zero\n\n- +3.7 on 13 November 2026: checklist\n- -8.6 on 4 November 2026 (C to D): correction\n- +0.3 on 28 October 2026: new evidence\n\n### boxes.dev\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Agent Zero.** Self-hosted under the MIT licence, with seven releases from 12 August to 1 November 2026 and breaking changes listed in minor-release notes. The agent runs shell commands in its container with no approval step, the web interface has no login by default, and eight CVEs from the past year were published by third parties with no vendor advisory.\n\n**boxes.dev.** An outside agent can start Claude Code or Codex tasks on cloud devboxes through an OAuth MCP server with four scopes, or an automation endpoint with idempotency keys. No status page, SLA or tool schema could be read, and every route starts with a person setting up a project in the app.\n\n## Before you call either\n\n### Agent Zero\n\n1. Set a UI login and password in Settings before publishing the port or opening a tunnel. The default has none\n2. Fill `allowed_users`, `allowed_numbers` or `sender_whitelist` before enabling a channel. An empty list accepts every sender\n3. Enable the Infection Check plugin when the agent reads mail, web pages or MCP results. It ships disabled\n4. Run v2.12 or later. It fixes a Telegram webhook authentication bypass and a WhatsApp media path traversal\n5. Call `POST /api_message` with the `X-API-KEY` header. The token changes when the UI login or password changes\n\n### boxes.dev\n\n1. Send a new `Idempotency-Key` for each intended run, and the same key and body when you retry an uncertain request\n2. Wait for status `thread_ready` before you use a returned `devboxId` as a target\n3. If you get 409 `active_fork_limit_reached`, free an awake devbox or wait. The plan's awake-devbox cap is full\n4. Read the thread in boxes.dev for the agent's answer. The status URL does not return it\n5. Ask for `threads:read` only unless the task needs to start agents or change settings\n\n## Questions\n\n### Which is better for AI agents, Agent Zero or boxes.dev?\n\nboxes.dev scores 53.2 (D) on agent readiness against Agent Zero's 49.7 (D), and leads in 1 of 7 scored categories. Agent Zero leads on reliability, schema \u0026 documentation, payments \u0026 pricing and maintenance \u0026 community.\n\n### Can an agent call Agent Zero and boxes.dev without installing anything?\n\nNo hosted endpoint is listed for Agent Zero. boxes.dev has a hosted endpoint at https://api.boxes.dev/mcp.\n\n### Are Agent Zero and boxes.dev open source?\n\nAgent Zero is open source (MIT). No open-source release is listed for boxes.dev.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/agent-zero-vs-boxes-dev.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agent-zero-vs-boxes-dev.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agent-zero\", \"b\": \"boxes-dev\"}`. From a terminal: `anchor compare agent-zero boxes-dev`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agent-zero.json and https://www.anchorterminal.com/api/v1/tools/boxes-dev.json\n\n## Other comparisons with Agent Zero or boxes.dev\n\n- [Agent Zero vs Aider](https://www.anchorterminal.com/compare/agent-zero-vs-aider.md)\n- [Agent Zero vs Amp](https://www.anchorterminal.com/compare/agent-zero-vs-amp.md)\n- [Agent Zero vs Antigravity CLI](https://www.anchorterminal.com/compare/agent-zero-vs-antigravity-cli.md)\n- [Agent Zero vs Auggie CLI](https://www.anchorterminal.com/compare/agent-zero-vs-auggie.md)\n- [Agent Zero vs AXLR](https://www.anchorterminal.com/compare/agent-zero-vs-axlr.md)\n- [Agent Zero vs Claude Code](https://www.anchorterminal.com/compare/agent-zero-vs-claude-code.md)\n- [Agent Zero vs Click](https://www.anchorterminal.com/compare/agent-zero-vs-click-agents.md)\n- [Agent Zero vs Cline](https://www.anchorterminal.com/compare/agent-zero-vs-cline.md)\n- [Agent Zero vs Conductor](https://www.anchorterminal.com/compare/agent-zero-vs-conductor.md)\n- [Agent Zero vs Crush](https://www.anchorterminal.com/compare/agent-zero-vs-crush.md)\n- [Agent Zero vs Cursor CLI](https://www.anchorterminal.com/compare/agent-zero-vs-cursor-cli.md)\n- [Agent Zero vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-harness.md)\n- [Agent Zero vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/agent-zero-vs-deepseek-superagent.md)\n- [Agent Zero vs Devin](https://www.anchorterminal.com/compare/agent-zero-vs-devin.md)\n- [Agent Zero vs Droid CLI](https://www.anchorterminal.com/compare/agent-zero-vs-droid-cli.md)\n- [Agent Zero vs Pi](https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi.md)\n- [Agent Zero vs Emdash](https://www.anchorterminal.com/compare/agent-zero-vs-emdash.md)\n- [Agent Zero vs Friday](https://www.anchorterminal.com/compare/agent-zero-vs-friday-work.md)\n- [Agent Zero vs Gemini CLI](https://www.anchorterminal.com/compare/agent-zero-vs-gemini-cli.md)\n- [Agent Zero vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/agent-zero-vs-github-copilot-cli.md)\n- [Agent Zero vs goose](https://www.anchorterminal.com/compare/agent-zero-vs-goose.md)\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Agent Zero vs HarnessRouter](https://www.anchorterminal.com/compare/agent-zero-vs-harnessrouter.md)\n- [Agent Zero vs Jules](https://www.anchorterminal.com/compare/agent-zero-vs-jules.md)\n- [Agent Zero vs Junie CLI](https://www.anchorterminal.com/compare/agent-zero-vs-junie.md)\n- [Agent Zero vs Kilo Code CLI](https://www.anchorterminal.com/compare/agent-zero-vs-kilo-code-cli.md)\n- [Agent Zero vs Kimi Code CLI](https://www.anchorterminal.com/compare/agent-zero-vs-kimi-code-cli.md)\n- [Agent Zero vs Kiro CLI](https://www.anchorterminal.com/compare/agent-zero-vs-kiro-cli.md)\n- [Agent Zero vs Letta](https://www.anchorterminal.com/compare/agent-zero-vs-letta.md)\n- [Agent Zero vs mini-swe-agent](https://www.anchorterminal.com/compare/agent-zero-vs-mini-swe-agent.md)\n- [Agent Zero vs MiniMax Code](https://www.anchorterminal.com/compare/agent-zero-vs-minimax-code.md)\n- [Agent Zero vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/agent-zero-vs-mistral-vibe-cli.md)\n- [Agent Zero vs Muse Code](https://www.anchorterminal.com/compare/agent-zero-vs-muse-code.md)\n- [Agent Zero vs OpenAI Agents API](https://www.anchorterminal.com/compare/agent-zero-vs-openai-agents-api.md)\n- [Agent Zero vs OpenAI Codex](https://www.anchorterminal.com/compare/agent-zero-vs-openai-codex.md)\n- [Agent Zero vs OpenCode](https://www.anchorterminal.com/compare/agent-zero-vs-opencode.md)\n- [Agent Zero vs OpenHands](https://www.anchorterminal.com/compare/agent-zero-vs-openhands.md)\n- [Agent Zero vs OpenMausBot](https://www.anchorterminal.com/compare/agent-zero-vs-openmausbot.md)\n- [Agent Zero vs Orca](https://www.anchorterminal.com/compare/agent-zero-vs-orca.md)\n- [Agent Zero vs Paseo](https://www.anchorterminal.com/compare/agent-zero-vs-paseo.md)\n- [Agent Zero vs Prime Agent](https://www.anchorterminal.com/compare/agent-zero-vs-prime-agent.md)\n- [Agent Zero vs Qoder CLI](https://www.anchorterminal.com/compare/agent-zero-vs-qoder-cli.md)\n- [Agent Zero vs Qwen Code](https://www.anchorterminal.com/compare/agent-zero-vs-qwen-code.md)\n- [Agent Zero vs Mirror CLI](https://www.anchorterminal.com/compare/agent-zero-vs-reflection-mirror.md)\n- [Agent Zero vs Rovo Dev CLI](https://www.anchorterminal.com/compare/agent-zero-vs-rovo-dev-cli.md)\n- [Agent Zero vs Sculptor](https://www.anchorterminal.com/compare/agent-zero-vs-sculptor.md)\n- [Agent Zero vs T3 Code](https://www.anchorterminal.com/compare/agent-zero-vs-t3-code.md)\n- [Agent Zero vs Traycer](https://www.anchorterminal.com/compare/agent-zero-vs-traycer.md)\n- [Agent Zero vs Unstoppable](https://www.anchorterminal.com/compare/agent-zero-vs-unstoppable.md)\n- [Agent Zero vs Verdent](https://www.anchorterminal.com/compare/agent-zero-vs-verdent.md)\n- [Agent Zero vs Vibe-Trading](https://www.anchorterminal.com/compare/agent-zero-vs-vibe-trading.md)\n- [Agent Zero vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/agent-zero-vs-warp.md)\n- [Aider vs boxes.dev](https://www.anchorterminal.com/compare/aider-vs-boxes-dev.md)\n- [Amp vs boxes.dev](https://www.anchorterminal.com/compare/amp-vs-boxes-dev.md)\n- [Antigravity CLI vs boxes.dev](https://www.anchorterminal.com/compare/antigravity-cli-vs-boxes-dev.md)\n- [Auggie CLI vs boxes.dev](https://www.anchorterminal.com/compare/auggie-vs-boxes-dev.md)\n- [AXLR vs boxes.dev](https://www.anchorterminal.com/compare/axlr-vs-boxes-dev.md)\n- [boxes.dev vs Claude Code](https://www.anchorterminal.com/compare/boxes-dev-vs-claude-code.md)\n- [boxes.dev vs Click](https://www.anchorterminal.com/compare/boxes-dev-vs-click-agents.md)\n- [boxes.dev vs Cline](https://www.anchorterminal.com/compare/boxes-dev-vs-cline.md)\n- [boxes.dev vs Conductor](https://www.anchorterminal.com/compare/boxes-dev-vs-conductor.md)\n- [boxes.dev vs Crush](https://www.anchorterminal.com/compare/boxes-dev-vs-crush.md)\n- [boxes.dev vs Cursor CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-cursor-cli.md)\n- [boxes.dev vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-harness.md)\n- [boxes.dev vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-superagent.md)\n- [boxes.dev vs Devin](https://www.anchorterminal.com/compare/boxes-dev-vs-devin.md)\n- [boxes.dev vs Droid CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-droid-cli.md)\n- [boxes.dev vs Pi](https://www.anchorterminal.com/compare/boxes-dev-vs-earendil-pi.md)\n- [boxes.dev vs Emdash](https://www.anchorterminal.com/compare/boxes-dev-vs-emdash.md)\n- [boxes.dev vs Friday](https://www.anchorterminal.com/compare/boxes-dev-vs-friday-work.md)\n- [boxes.dev vs Gemini CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-gemini-cli.md)\n- [boxes.dev vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-github-copilot-cli.md)\n- [boxes.dev vs goose](https://www.anchorterminal.com/compare/boxes-dev-vs-goose.md)\n- [boxes.dev vs Harness²](https://www.anchorterminal.com/compare/boxes-dev-vs-harness2.md)\n- [boxes.dev vs HarnessRouter](https://www.anchorterminal.com/compare/boxes-dev-vs-harnessrouter.md)\n- [boxes.dev vs Jules](https://www.anchorterminal.com/compare/boxes-dev-vs-jules.md)\n- [boxes.dev vs Junie CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-junie.md)\n- [boxes.dev vs Kilo Code CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-kilo-code-cli.md)\n- [boxes.dev vs Kimi Code CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-kimi-code-cli.md)\n- [boxes.dev vs Kiro CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-kiro-cli.md)\n- [boxes.dev vs Letta](https://www.anchorterminal.com/compare/boxes-dev-vs-letta.md)\n- [boxes.dev vs mini-swe-agent](https://www.anchorterminal.com/compare/boxes-dev-vs-mini-swe-agent.md)\n- [boxes.dev vs MiniMax Code](https://www.anchorterminal.com/compare/boxes-dev-vs-minimax-code.md)\n- [boxes.dev vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-mistral-vibe-cli.md)\n- [boxes.dev vs Muse Code](https://www.anchorterminal.com/compare/boxes-dev-vs-muse-code.md)\n- [boxes.dev vs OpenAI Agents API](https://www.anchorterminal.com/compare/boxes-dev-vs-openai-agents-api.md)\n- [boxes.dev vs OpenAI Codex](https://www.anchorterminal.com/compare/boxes-dev-vs-openai-codex.md)\n- [boxes.dev vs OpenCode](https://www.anchorterminal.com/compare/boxes-dev-vs-opencode.md)\n- [boxes.dev vs OpenHands](https://www.anchorterminal.com/compare/boxes-dev-vs-openhands.md)\n- [boxes.dev vs OpenMausBot](https://www.anchorterminal.com/compare/boxes-dev-vs-openmausbot.md)\n- [boxes.dev vs Orca](https://www.anchorterminal.com/compare/boxes-dev-vs-orca.md)\n- [boxes.dev vs Paseo](https://www.anchorterminal.com/compare/boxes-dev-vs-paseo.md)\n- [boxes.dev vs Prime Agent](https://www.anchorterminal.com/compare/boxes-dev-vs-prime-agent.md)\n- [boxes.dev vs Qoder CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-qoder-cli.md)\n- [boxes.dev vs Qwen Code](https://www.anchorterminal.com/compare/boxes-dev-vs-qwen-code.md)\n- [boxes.dev vs Mirror CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-reflection-mirror.md)\n- [boxes.dev vs Rovo Dev CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-rovo-dev-cli.md)\n- [boxes.dev vs Sculptor](https://www.anchorterminal.com/compare/boxes-dev-vs-sculptor.md)\n- [boxes.dev vs T3 Code](https://www.anchorterminal.com/compare/boxes-dev-vs-t3-code.md)\n- [boxes.dev vs Traycer](https://www.anchorterminal.com/compare/boxes-dev-vs-traycer.md)\n- [boxes.dev vs Unstoppable](https://www.anchorterminal.com/compare/boxes-dev-vs-unstoppable.md)\n- [boxes.dev vs Verdent](https://www.anchorterminal.com/compare/boxes-dev-vs-verdent.md)\n- [boxes.dev vs Vibe-Trading](https://www.anchorterminal.com/compare/boxes-dev-vs-vibe-trading.md)\n- [boxes.dev vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/boxes-dev-vs-warp.md)\n- [Agent Relay vs boxes.dev](https://www.anchorterminal.com/compare/agent-relay-vs-boxes-dev.md)\n- [boxes.dev vs Clawboo](https://www.anchorterminal.com/compare/boxes-dev-vs-clawboo.md)\n- [boxes.dev vs CLI Manager](https://www.anchorterminal.com/compare/boxes-dev-vs-cli-manager.md)\n- [boxes.dev vs Harness](https://www.anchorterminal.com/compare/boxes-dev-vs-harness-autonomous.md)\n- [boxes.dev vs herdr](https://www.anchorterminal.com/compare/boxes-dev-vs-herdr.md)\n- [boxes.dev vs Paperclip](https://www.anchorterminal.com/compare/boxes-dev-vs-paperclip.md)\n- [boxes.dev vs Parallax](https://www.anchorterminal.com/compare/boxes-dev-vs-parallax-agents.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": "Agent Zero vs boxes.dev",
        "url": ""
      }
    ],
    "description": "boxes.dev scores 53.2 (D) to Agent Zero's 49.7 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Agent Zero D 49.7",
      "boxes.dev D 53.2",
      "scores"
    ],
    "h1": "Agent Zero vs boxes.dev",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/agent-zero-vs-boxes-dev",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Agent Zero vs boxes.dev for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/agent-zero-vs-boxes-dev"
  },
  "tokens": {
    "markdown": 6950,
    "slim": 1030
  },
  "version": 1
}
