{
  "data": {
    "similar": [
      {
        "grade": "BB",
        "json": "https://www.anchorterminal.com/tools/zeroclaw.json",
        "name": "ZeroClaw",
        "score": 70.2,
        "shared": [
          "assistant.proactive",
          "assistant.messaging",
          "assistant.memory",
          "assistant.accounts",
          "agent.mcp-client"
        ],
        "slug": "zeroclaw"
      },
      {
        "grade": "B",
        "json": "https://www.anchorterminal.com/tools/nanoclaw.json",
        "name": "NanoClaw",
        "score": 68.3,
        "shared": [
          "assistant.proactive",
          "assistant.messaging",
          "assistant.memory",
          "agent.mcp-client",
          "assistant.accounts"
        ],
        "slug": "nanoclaw"
      },
      {
        "grade": "B",
        "json": "https://www.anchorterminal.com/tools/hermes-agent.json",
        "name": "Hermes Agent",
        "score": 67.9,
        "shared": [
          "assistant.proactive",
          "assistant.messaging",
          "assistant.accounts",
          "assistant.memory",
          "agent.mcp-client"
        ],
        "slug": "hermes-agent"
      },
      {
        "grade": "B",
        "json": "https://www.anchorterminal.com/tools/openclaw.json",
        "name": "OpenClaw",
        "score": 67.1,
        "shared": [
          "assistant.proactive",
          "assistant.messaging",
          "assistant.accounts",
          "assistant.memory",
          "agent.mcp-client"
        ],
        "slug": "openclaw"
      },
      {
        "grade": "B",
        "json": "https://www.anchorterminal.com/tools/ironclaw.json",
        "name": "IronClaw",
        "score": 66.7,
        "shared": [
          "assistant.proactive",
          "assistant.messaging",
          "assistant.accounts",
          "assistant.memory",
          "agent.mcp-client"
        ],
        "slug": "ironclaw"
      },
      {
        "grade": "B",
        "json": "https://www.anchorterminal.com/tools/nanobot.json",
        "name": "nanobot",
        "score": 62.4,
        "shared": [
          "assistant.proactive",
          "assistant.messaging",
          "assistant.memory",
          "assistant.accounts",
          "agent.mcp-client"
        ],
        "slug": "nanobot"
      }
    ],
    "tool": {
      "slug": "grok-bot",
      "name": "Grok Bot",
      "vendor": "SpaceXAI and Cursor (Anysphere, Inc.)",
      "vendorUrl": "https://x.ai/bot",
      "kind": "platform",
      "category": "personal-assistants",
      "summary": "Hosted assistant from SpaceXAI and Cursor. Named Bots work on a persistent cloud computer with a browser, files and terminal, reached from desktop and mobile apps, Slack and X, with routines that run on a schedule.",
      "url": "https://www.anchorterminal.com/tools/grok-bot",
      "markdownUrl": "https://www.anchorterminal.com/tools/grok-bot.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/grok-bot.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/grok-bot.json",
      "license": "Proprietary",
      "transports": [],
      "packages": [],
      "auth": "mixed",
      "authNotes": "A person signs in with a Cursor account in the browser, or with Sign in with Grok for a Grok Business seat. SAML 2.0 single sign-on applies to teams, and SCIM is Enterprise only. Connectors are added from Connect apps and authenticated in the browser by OAuth, or configured with a key or token. OAuth tokens stay on Cursor's backend. For passwords, passkeys, two-factor codes, CAPTCHAs and payment confirmations the Bot hands the computer to the owner, and a secure secret request masks a value and keeps it out of the transcript and away from the model. Browser sessions then persist on the cloud computer shared by all of the user's Bots (https://docs.x.ai/grok-bot/security; https://docs.x.ai/grok-bot/approvals-security-and-privacy; https://docs.x.ai/grok-bot/team-bots). No API key or public API for the assistant was found. An Admin API for team settings is linked from the docs and was not read.",
      "pricing": "paid",
      "pricingNotes": "No separate subscription. Grok Bot is included with every paid individual Cursor plan (Pro, Pro+, Ultra) and with Cursor Teams, or through a linked individual SuperGrok, SuperGrok Plus, SuperGrok Heavy or X Premium+ subscription, or a seat on a self-serve Grok Business plan. Cursor's pricing page shows Individual at $20 a month and Teams at $40 a user a month. The Pro+ and Ultra prices sit behind tabs our reader did not see. Each tier includes weekly usage with no amount published, metered by agent steps and tokens. After that, on-demand usage is billed through Cursor up to a monthly limit the owner sets, which is not a hard stop in the middle of a run. A free trial is a usage credit with a 7-day window and never becomes a paid plan. SuperGrok Lite is not included, and a SuperGrok link cannot be undone or moved (https://cursor.com/help/grok-bot/plans; https://cursor.com/pricing; checked 2026-10-12).",
      "priceSummary": "$20 / mo",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the Grok Bot docs, the plans page or the Grok Bot Terms (checked 2026-10-12).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-12"
      },
      "docsUrl": "https://docs.x.ai/grok-bot/overview",
      "llmsTxt": "https://docs.x.ai/llms.txt",
      "capabilities": [
        "assistant.proactive",
        "assistant.accounts",
        "assistant.memory",
        "assistant.messaging",
        "agent.mcp-client"
      ],
      "tags": [
        "hosted",
        "closed-source",
        "desktop-app",
        "mobile-app",
        "computer-use",
        "scheduled-routines",
        "slack",
        "status-page",
        "iso27001",
        "soc2",
        "llms-txt",
        "paid"
      ],
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 45.2,
        "grade": "E",
        "agentReady": false,
        "rank": 893,
        "ranked": true,
        "rankOf": 986,
        "categoryRank": 12,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 50,
          "maintenance": 20,
          "payments": 25,
          "reliability": 40,
          "schema": 40,
          "security": 68,
          "transparency": 66
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "breakdown": [
          {
            "key": "reliability",
            "name": "Reliability",
            "weight": 16,
            "effectiveWeight": 20,
            "score": 40,
            "points": 8,
            "reason": "Read with the hosted lines. status.cursor.com has a Grok Bot component with 90 days of uptime history (20). The history page lists sixteen incidents that name Grok Bot between 18 August and 9 October 2026, seven of them marked major. They fell on 3 September (routine triggers, one hour), 7 September (computers unreachable for some users, 65 minutes), 16 September (six and a half hours), 17 September (two hours), 18 September (two, about three hours and under six hours) and 6 October (with Cloud Agents, restored after about two hours). Several majors (0). Product limits are published for routines (50 a Bot, five minutes apart, 20 run records), unattended approvals (about 10 minutes) and group chats (two to six Bots), but the weekly usage allowance has no number (7 of 15). The plans page says what happens when usage runs out and that the monthly limit is not a hard stop mid-run, and the docs give recover, update and reset steps for the computer and advise idempotent retries in routines, with no retry guarantees (5 of 15). No SLA was found, and the Grok Bot Terms say the documentation creates no service level (0). No beta label on the pages read, though teach-by-demonstration, cross-conversation search, Enterprise access and X tagging are described as rolling out or limited by region (8 of 10)."
          },
          {
            "key": "performance",
            "name": "Performance",
            "weight": 10,
            "effectiveWeight": 0,
            "pending": true,
            "points": 0,
            "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes."
          },
          {
            "key": "schema",
            "name": "Schema \u0026 documentation",
            "weight": 13,
            "effectiveWeight": 16.25,
            "score": 40,
            "points": 6.5,
            "reason": "Grok Bot is an app, so the API lines are read for what a person or an agent setting it up can rely on. No machine-readable contract for the assistant was found. The docs link an Admin API for team settings on cursor.com, which we did not read (0 of 25). docs.x.ai serves an llms.txt that lists every Grok Bot page, a Markdown copy of each page and a Copy for LLM button (10). The pages state purpose and limits plainly, including what Auto Review does not cover, what deleting a Bot leaves behind and that separate Bots are not a security boundary (16 of 20). The interface is natural language. Auto-review rules are free text, and the one typed format found is the secret name pattern for Team Bots (3 of 15). Example prompts on most pages and a table of @bot replies with their meaning. A troubleshooting page exists and was not read (9 of 15). No Grok Bot changelog or version history was found. The desktop app shows its version, and the Grok Bot Terms carry a last-updated date (2 of 15)."
          },
          {
            "key": "ergonomics",
            "name": "Agent ergonomics",
            "weight": 13,
            "effectiveWeight": 16.25,
            "score": 50,
            "points": 8.13,
            "reason": "Read for an owner directing the assistant. Usage is metered by agent steps and tokens with a weekly allowance and an on-demand monthly limit, but there is no budget for one task, no separate Grok Bot spend cap and no model choice (10 of 25). A search palette covers Bots, messages, files and routines, each routine keeps its 20 latest runs, and notifications are set for each Bot (10 of 20). Errors show above the composer with a request ID, expired approvals are labelled, blocked plugins read Disabled by team admin, and the @bot replies are documented (12 of 20). Allow once, Always allow and Deny on each request, Ask first rules, drafts with Send and Discard, and a Test run that the docs warn performs real work. A Stop now message does not undo completed actions and nothing is described as reversible (10 of 20). Defaults lean cautious for local commands (Ask every time) and a Bot starts with no access, while network access defaults to allow-all. Apps for five platforms and no SDK (8 of 15)."
          },
          {
            "key": "security",
            "name": "Security \u0026 auth",
            "weight": 14,
            "effectiveWeight": 17.5,
            "score": 68,
            "points": 11.9,
            "reason": "Read with the tool lines, applied to the accounts the assistant holds. Bots work as the signed-in member with no identity of their own. Connector OAuth tokens stay on Cursor's backend and are never stored on the computer, passwords and two-factor steps go to the owner by takeover, and a secure secret request keeps a value away from the model. Against that, browser sessions, cookies and command-line credentials persist on one cloud computer that every Bot of the user shares, and connector scopes are not listed on the pages read (20 of 30). Approvals, Ask first and Allow automatically rules, editable drafts, a 10-minute expiry on unattended approvals and Ask every time for local commands. The FAQ says which actions need approval depends on the tool, the risk and the owner's rules, Auto Review is model-based and does not check memory writes or most settings changes, Team Bot plugins run without asking, and the terms call these controls aids only (13 of 20). A prompt-injection section says outside content is marked as untrusted, Auto Review checks actions against the request, and network policy and approvals sit beneath it, and that the risk is reduced, not removed (11 of 15). The transcript shows tool activity and computer use and routines keep run records. Audit logs, Action Recording and OpenTelemetry export are Enterprise only (8 of 15). security.txt and a disclosure address with a five-business-day acknowledgement, ISO/IEC 27001 and 42001 with Grok Bot in scope per the docs, SOC 2 Type II and AIUC-1 per Cursor's security page, yearly penetration tests, and advisories published on GitHub, none of the ten newest naming Grok Bot. No bug bounty found (16 of 20)."
          },
          {
            "key": "payments",
            "name": "Payments \u0026 pricing",
            "weight": 10,
            "effectiveWeight": 12.5,
            "score": 25,
            "points": 3.13,
            "reason": "No machine payment protocol (0). Pricing is by plan and public. Cursor's pricing page shows Individual at $20 a month and Teams at $40 a user a month with Grok Bot included, but the weekly usage amounts and the on-demand rate are not published on the pages read (10 of 20). The plans page describes a free trial as a usage credit with a 7-day window that never becomes a paid plan, and Cursor's free Hobby plan needs no card. Whether the Grok Bot trial itself needs a card is not stated (15 of 20). A person signs in through a browser, so an agent cannot start alone (0)."
          },
          {
            "key": "tasks",
            "name": "Task success",
            "weight": 10,
            "effectiveWeight": 0,
            "pending": true,
            "points": 0,
            "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored."
          },
          {
            "key": "maintenance",
            "name": "Maintenance \u0026 community",
            "weight": 7,
            "effectiveWeight": 8.75,
            "score": 20,
            "points": 1.75,
            "reason": "No dated release notes or changelog for Grok Bot were found. Cursor's changelog entries from 29 July to 6 October 2026 do not mention it, and x.ai/bot, which may carry versions, answered 403. Scored as absent, which may understate a service that had status updates through 9 October 2026 (0 of 30, and 0 of 20 for three dated entries). Support runs through support@x.ai, a Discord server, Cursor's help centre with Grok Bot articles and a status page with dated incident updates (10 of 15 for a closed service). No SDK and not an MCP server. Official apps for five platforms update themselves (5 of 15). The cloud computer's image is updated with files kept, and no public build or test record exists (5 of 10)."
          },
          {
            "key": "transparency",
            "name": "Transparency \u0026 trust",
            "weight": 7,
            "effectiveWeight": 8.75,
            "score": 66,
            "points": 5.78,
            "note": "editorial 48, provenance 84",
            "reason": "Closed source with clear terms. The Grok Bot Terms and Cursor's Terms of Service are public and dated (15 of 30). The docs give concrete periods (Action Recording kept 90 days, account data removed within 30 days, deletion within 30 days of written direction under the DPA, daily backups) and say plainly that deleting a Bot leaves files and sessions. They give no period for a deleted Bot's backend data beyond the applicable Cursor terms, the privacy policy says only as long as necessary, and there is no retention policy per organisation. Training is off with Privacy Mode, and the privacy policy says inputs are not used for training unless flagged, reported or agreed (19 of 30). No deprecation policy. The terms say the documentation is no commitment that any function, integration or model will stay, with reasonable notice only for materially adverse changes to the terms (4 of 20). Computers run in the United States with no residency commitment, the subprocessor list is on a trust portal we could not read, and the docs say no fixed set of model vendors is guaranteed (10 of 20)."
          }
        ],
        "assessment": {
          "date": "2026-10-12",
          "basis": "public evidence",
          "confidence": "medium",
          "notes": {
            "ergonomics": "Read for an owner directing the assistant. Usage is metered by agent steps and tokens with a weekly allowance and an on-demand monthly limit, but there is no budget for one task, no separate Grok Bot spend cap and no model choice (10 of 25). A search palette covers Bots, messages, files and routines, each routine keeps its 20 latest runs, and notifications are set for each Bot (10 of 20). Errors show above the composer with a request ID, expired approvals are labelled, blocked plugins read Disabled by team admin, and the @bot replies are documented (12 of 20). Allow once, Always allow and Deny on each request, Ask first rules, drafts with Send and Discard, and a Test run that the docs warn performs real work. A Stop now message does not undo completed actions and nothing is described as reversible (10 of 20). Defaults lean cautious for local commands (Ask every time) and a Bot starts with no access, while network access defaults to allow-all. Apps for five platforms and no SDK (8 of 15).",
            "maintenance": "No dated release notes or changelog for Grok Bot were found. Cursor's changelog entries from 29 July to 6 October 2026 do not mention it, and x.ai/bot, which may carry versions, answered 403. Scored as absent, which may understate a service that had status updates through 9 October 2026 (0 of 30, and 0 of 20 for three dated entries). Support runs through support@x.ai, a Discord server, Cursor's help centre with Grok Bot articles and a status page with dated incident updates (10 of 15 for a closed service). No SDK and not an MCP server. Official apps for five platforms update themselves (5 of 15). The cloud computer's image is updated with files kept, and no public build or test record exists (5 of 10).",
            "payments": "No machine payment protocol (0). Pricing is by plan and public. Cursor's pricing page shows Individual at $20 a month and Teams at $40 a user a month with Grok Bot included, but the weekly usage amounts and the on-demand rate are not published on the pages read (10 of 20). The plans page describes a free trial as a usage credit with a 7-day window that never becomes a paid plan, and Cursor's free Hobby plan needs no card. Whether the Grok Bot trial itself needs a card is not stated (15 of 20). A person signs in through a browser, so an agent cannot start alone (0).",
            "reliability": "Read with the hosted lines. status.cursor.com has a Grok Bot component with 90 days of uptime history (20). The history page lists sixteen incidents that name Grok Bot between 18 August and 9 October 2026, seven of them marked major. They fell on 3 September (routine triggers, one hour), 7 September (computers unreachable for some users, 65 minutes), 16 September (six and a half hours), 17 September (two hours), 18 September (two, about three hours and under six hours) and 6 October (with Cloud Agents, restored after about two hours). Several majors (0). Product limits are published for routines (50 a Bot, five minutes apart, 20 run records), unattended approvals (about 10 minutes) and group chats (two to six Bots), but the weekly usage allowance has no number (7 of 15). The plans page says what happens when usage runs out and that the monthly limit is not a hard stop mid-run, and the docs give recover, update and reset steps for the computer and advise idempotent retries in routines, with no retry guarantees (5 of 15). No SLA was found, and the Grok Bot Terms say the documentation creates no service level (0). No beta label on the pages read, though teach-by-demonstration, cross-conversation search, Enterprise access and X tagging are described as rolling out or limited by region (8 of 10).",
            "schema": "Grok Bot is an app, so the API lines are read for what a person or an agent setting it up can rely on. No machine-readable contract for the assistant was found. The docs link an Admin API for team settings on cursor.com, which we did not read (0 of 25). docs.x.ai serves an llms.txt that lists every Grok Bot page, a Markdown copy of each page and a Copy for LLM button (10). The pages state purpose and limits plainly, including what Auto Review does not cover, what deleting a Bot leaves behind and that separate Bots are not a security boundary (16 of 20). The interface is natural language. Auto-review rules are free text, and the one typed format found is the secret name pattern for Team Bots (3 of 15). Example prompts on most pages and a table of @bot replies with their meaning. A troubleshooting page exists and was not read (9 of 15). No Grok Bot changelog or version history was found. The desktop app shows its version, and the Grok Bot Terms carry a last-updated date (2 of 15).",
            "security": "Read with the tool lines, applied to the accounts the assistant holds. Bots work as the signed-in member with no identity of their own. Connector OAuth tokens stay on Cursor's backend and are never stored on the computer, passwords and two-factor steps go to the owner by takeover, and a secure secret request keeps a value away from the model. Against that, browser sessions, cookies and command-line credentials persist on one cloud computer that every Bot of the user shares, and connector scopes are not listed on the pages read (20 of 30). Approvals, Ask first and Allow automatically rules, editable drafts, a 10-minute expiry on unattended approvals and Ask every time for local commands. The FAQ says which actions need approval depends on the tool, the risk and the owner's rules, Auto Review is model-based and does not check memory writes or most settings changes, Team Bot plugins run without asking, and the terms call these controls aids only (13 of 20). A prompt-injection section says outside content is marked as untrusted, Auto Review checks actions against the request, and network policy and approvals sit beneath it, and that the risk is reduced, not removed (11 of 15). The transcript shows tool activity and computer use and routines keep run records. Audit logs, Action Recording and OpenTelemetry export are Enterprise only (8 of 15). security.txt and a disclosure address with a five-business-day acknowledgement, ISO/IEC 27001 and 42001 with Grok Bot in scope per the docs, SOC 2 Type II and AIUC-1 per Cursor's security page, yearly penetration tests, and advisories published on GitHub, none of the ten newest naming Grok Bot. No bug bounty found (16 of 20).",
            "transparency": "Closed source with clear terms. The Grok Bot Terms and Cursor's Terms of Service are public and dated (15 of 30). The docs give concrete periods (Action Recording kept 90 days, account data removed within 30 days, deletion within 30 days of written direction under the DPA, daily backups) and say plainly that deleting a Bot leaves files and sessions. They give no period for a deleted Bot's backend data beyond the applicable Cursor terms, the privacy policy says only as long as necessary, and there is no retention policy per organisation. Training is off with Privacy Mode, and the privacy policy says inputs are not used for training unless flagged, reported or agreed (19 of 30). No deprecation policy. The terms say the documentation is no commitment that any function, integration or model will stay, with reasonable notice only for materially adverse changes to the terms (4 of 20). Computers run in the United States with no residency commitment, the subprocessor list is on a trust portal we could not read, and the docs say no fixed set of model vendors is guaranteed (10 of 20)."
          },
          "sources": [
            {
              "what": "Grok Bot overview",
              "url": "https://docs.x.ai/grok-bot/overview",
              "seen": "2026-10-12"
            },
            {
              "what": "approvals, security and privacy (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/approvals-security-and-privacy.md",
              "seen": "2026-10-12"
            },
            {
              "what": "Grok Bot security (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/security.md",
              "seen": "2026-10-12"
            },
            {
              "what": "security FAQ (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/security-faq.md",
              "seen": "2026-10-12"
            },
            {
              "what": "computer and apps (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/computer-and-apps.md",
              "seen": "2026-10-12"
            },
            {
              "what": "skills and routines (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/skills-routines-and-automations.md",
              "seen": "2026-10-12"
            },
            {
              "what": "message and collaborate (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/chat-and-collaboration.md",
              "seen": "2026-10-12"
            },
            {
              "what": "create and manage Bots (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/bots.md",
              "seen": "2026-10-12"
            },
            {
              "what": "Team Bots (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/team-bots.md",
              "seen": "2026-10-12"
            },
            {
              "what": "teams and enterprises (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/teams-and-enterprises.md",
              "seen": "2026-10-12"
            },
            {
              "what": "settings and notifications (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/settings-and-notifications.md",
              "seen": "2026-10-12"
            },
            {
              "what": "FAQ (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/faq.md",
              "seen": "2026-10-12"
            },
            {
              "what": "Tag @bot on X (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/tag-on-x.md",
              "seen": "2026-10-12"
            },
            {
              "what": "get started (Markdown copy)",
              "url": "https://docs.x.ai/grok-bot/get-started.md",
              "seen": "2026-10-12"
            },
            {
              "what": "docs llms.txt",
              "url": "https://docs.x.ai/llms.txt",
              "seen": "2026-10-12"
            },
            {
              "what": "docs robots.txt (HTTP 200, allow all, ai-input=yes)",
              "url": "https://docs.x.ai/robots.txt",
              "seen": "2026-10-12"
            },
            {
              "what": "plans and billing",
              "url": "https://cursor.com/help/grok-bot/plans",
              "seen": "2026-10-12"
            },
            {
              "what": "Cursor pricing",
              "url": "https://cursor.com/pricing",
              "seen": "2026-10-12"
            },
            {
              "what": "Grok Bot Terms, last updated 3 September 2026",
              "url": "https://cursor.com/en-US/terms/grok-bot",
              "seen": "2026-10-12"
            },
            {
              "what": "Cursor Terms of Service, last updated 3 September 2026",
              "url": "https://cursor.com/terms-of-service",
              "seen": "2026-10-12"
            },
            {
              "what": "Cursor privacy policy, last updated 11 October 2026",
              "url": "https://cursor.com/privacy",
              "seen": "2026-10-12"
            },
            {
              "what": "Cursor security page, last updated 25 August 2026",
              "url": "https://cursor.com/security",
              "seen": "2026-10-12"
            },
            {
              "what": "delete your Grok Bot account",
              "url": "https://cursor.com/help/grok-bot/delete-account",
              "seen": "2026-10-12"
            },
            {
              "what": "Cursor changelog, pages 1 and 2",
              "url": "https://cursor.com/changelog",
              "seen": "2026-10-12"
            },
            {
              "what": "security.txt",
              "url": "https://cursor.com/.well-known/security.txt",
              "seen": "2026-10-12"
            },
            {
              "what": "cursor.com robots.txt (HTTP 200)",
              "url": "https://cursor.com/robots.txt",
              "seen": "2026-10-12"
            },
            {
              "what": "status page",
              "url": "https://status.cursor.com/",
              "seen": "2026-10-12"
            },
            {
              "what": "status history, August to October 2026",
              "url": "https://status.cursor.com/history",
              "seen": "2026-10-12"
            },
            {
              "what": "Cursor security advisories on GitHub, first page",
              "url": "https://github.com/cursor/cursor/security/advisories",
              "seen": "2026-10-12"
            },
            {
              "what": "RDAP record for cursor.com",
              "url": "https://rdap.verisign.com/com/v1/domain/cursor.com",
              "seen": "2026-10-12"
            },
            {
              "what": "x.ai robots.txt (HTTP 200, ai-input=yes). The product page x.ai/bot then answered 403",
              "url": "https://x.ai/robots.txt",
              "seen": "2026-10-12"
            }
          ],
          "openQuestions": [
            "Kind. We chose `platform`, the brief's kind for a desktop, web or phone app, because Grok Bot is reached through its own apps, Slack and X and has no API an outside agent calls. `metrics.kind` is `remote` and it is graded as a hosted service",
            "Vendor. The lead named xAI. The docs are on docs.x.ai and name SpaceXAI, while accounts, billing, hosting, terms, privacy policy and status page are Cursor's (Anysphere, Inc.). No page read states how the companies are related",
            "The lead said access comes through eligible Cursor and SuperGrok plans. The plans page confirms that and adds X Premium+ and self-serve Grok Business seats",
            "Unchecked: a Business Insider report of 10 October 2026 named in the lead. We did not read it, nothing on the vendor pages read mentions an incident of that kind, and no deduction is taken",
            "Unchecked: x.ai/bot (downloads and product page), the x.ai legal index and the third-party bot terms at x.ai/legal/bot-sharing-terms. x.ai/bot answered HTTP 403 and we sent x.ai nothing more",
            "Unchecked: status.x.ai, which the docs header links, answered HTTP 403. Reliability is scored on status.cursor.com, which has the Grok Bot component",
            "Unchecked: release dates. No Grok Bot changelog or version history was found, so `lastRelease` is null and Maintenance scores recency as absent",
            "Unchecked: the list of connectors in Connect apps and their scopes. Cursor's changelog of 3 August 2026 announces Gmail, Google Drive and Calendar plugins for Cursor, and the Grok Bot docs mention email and Slack drafts, an X plugin, Jira and Linear, without a full list",
            "Unchecked: the subprocessor list and certificates on trust.cursor.com (a script-drawn portal whose robots.txt request returned the portal page), the DPA, and Cursor's privacy overview on training data",
            "Unchecked: the Pro+ and Ultra prices (behind tabs on the pricing page), the weekly usage amounts and the on-demand rate",
            "Unchecked: these docs pages, left unread to keep to the page limit. Mobile, files and results, use cases, troubleshooting, identity and access, private networks, proxies, manage computers, and the Admin API on cursor.com",
            "Unchecked: whether Auto Review is on by default for an individual account. The docs describe behaviour with Auto Review on and say Enterprise admins can enforce it",
            "Whether single memories can be viewed, exported or deleted. The docs read describe what a Bot remembers and say to correct stale assumptions in conversation",
            "Cursor's Terms of Service bar scraping, probing and scanning the Service and restrict sharing benchmark results. This matters before any probe or task suite is run",
            "We read 16 pages on docs.x.ai, one over the brief's limit of about fifteen"
          ]
        },
        "negative": 0,
        "verdict": "Connector tokens stay on Cursor's backend and each user gets a separate microVM, with approvals, drafts and a review model before risky actions. All of a user's Bots share one computer and its sign-ins, the review model skips memory writes, and the status page shows seven major Grok Bot incidents since 3 September 2026.",
        "bestFor": "A person or team already paying for Cursor or SuperGrok who wants named assistants that keep working on a cloud computer, with routines and Slack or X entry points, and who will write approval rules.",
        "strengths": [
          "Connector OAuth tokens stay on Cursor's backend. Bots call tools without receiving them, and tokens are never stored on the cloud computer",
          "Each user's work runs in a dedicated Firecracker microVM. A Bot has no identity of its own and holds no more access than the signed-in member",
          "Approvals from routines, triggers or other Bots expire after about 10 minutes and the action does not run",
          "Email and Slack messages can appear as editable drafts with Send and Discard buttons, and passwords, two-factor codes and payment confirmations are handed to the owner",
          "Markdown copies of every docs page and an llms.txt, with a security page that states what the controls do not cover"
        ],
        "weaknesses": [
          "All of one user's Bots share one cloud computer, with its files, browser sessions and command-line credentials. The docs say separate Bots are not a security boundary",
          "The review model does not check memory writes or most settings changes, and the Grok Bot Terms call approval controls aids only",
          "Deleting a Bot leaves shared files and browser sessions on the computer. No way to view or delete single memories was found in the docs read",
          "Seven incidents marked major named Grok Bot on status.cursor.com between 3 September and 6 October 2026, the longest about six and a half hours",
          "Audit logs, Action Recording, network allowlists and enforced review rules are Enterprise only. Other teams default to allow-all network access",
          "Cursor chooses the model with no picker and no fixed set of model vendors, and no Grok Bot changelog was found"
        ],
        "agentNotes": [
          "State in each request what the Bot may change and where it must stop. Which actions pause for approval depends on the tool, the risk and the owner's Auto-review rules",
          "Add narrow Ask first rules for sending, publishing, purchasing and deleting. Ask first wins over Allow automatically when both match",
          "Treat any sign-in or file on the cloud computer as available to every Bot on the account. Give a workload its own Cursor user when it needs separate credentials",
          "Run Test run with safe inputs. A test run performs real work and can call connected tools",
          "To remove access, pause routines, sign out of sites on the computer, uninstall connectors and revoke them at the source service. Deleting the Bot is not enough"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "E",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 45.2
          }
        ],
        "editorialScores": {
          "ergonomics": 50,
          "maintenance": 20,
          "payments": 25,
          "reliability": 40,
          "schema": 40,
          "security": 68,
          "transparency": 48
        },
        "provenanceScore": 84
      },
      "connect": {},
      "letme": {
        "capability": "https://letme.dev/assistant.proactive",
        "tool": "https://letme.dev/grok-bot"
      },
      "sameCompany": [
        "cursor-cli"
      ],
      "notable": [
        "Grok Bot is documented on docs.x.ai, whose pages are titled SpaceXSI Docs and name SpaceXAI in the text, while sign-in, billing, hosting, terms, privacy policy and status page are Cursor's (Anysphere, Inc.) (https://docs.x.ai/grok-bot/overview; https://cursor.com/en-US/terms/grok-bot)",
        "Each Bot works on a persistent cloud computer with a browser, filesystem and terminal. The computers run in Cursor's cloud, in the United States today, with no on-premises or bring-your-own-image option (https://docs.x.ai/grok-bot/security)",
        "Every Bot on an account uses the same computer. Browser cookies, signed-in sessions, files and command-line credentials are shared across them (https://docs.x.ai/grok-bot/computer-and-apps)",
        "Auto Review is a separate review model that evaluates shell commands, plugin calls, computer use, changes to routines and triggers, and delegation. It can let an action proceed, require approval or deny it. The docs say it does not review every side effect, naming memory writes and most settings changes (https://docs.x.ai/grok-bot/security)",
        "An approval requested by work that started without the owner (a routine, a trigger or a message from another Bot) expires after about 10 minutes and the action does not run (https://docs.x.ai/grok-bot/approvals-security-and-privacy)",
        "Routines run on a schedule or after an event such as a Slack message or a GitHub notification. A Bot can own up to 50 routines, schedules must be at least five minutes apart, and the app keeps the 20 most recent runs of each (https://docs.x.ai/grok-bot/skills-routines-and-automations)",
        "Tagging @bot in a post on X hands the post to the owner's main Bot as a task, and X's first-use notice says tagged requests start work automatically. Not available for X accounts based in Australia, the United Kingdom, the European Union, Iceland, Liechtenstein or Norway (https://docs.x.ai/grok-bot/tag-on-x)",
        "A Team Bot can have its own Slack app that teammates DM or @mention. Plugins added to a Team Bot are used in every conversation without asking anyone first, with each teammate's own account where the plugin signs in by OAuth (https://docs.x.ai/grok-bot/team-bots)",
        "Teams without a network policy default to allow-all, and Network Controls are Enterprise only. Hosted computers leave through static egress IP ranges shared across customers (https://docs.x.ai/grok-bot/security)",
        "The Grok Bot Terms (last updated 3 September 2026) say approval and automated-review controls are aids only, may not prevent every unintended or harmful action, and do not reverse completed actions. The customer is solely responsible for all agentic actions (https://cursor.com/en-US/terms/grok-bot)",
        "The Grok Bot Terms say the service may retain customer data, files, browser sessions, credentials, memory and routines in a persistent cloud environment, and that deleting a Bot may not delete shared files, sessions, credentials or routines (https://cursor.com/en-US/terms/grok-bot)",
        "Deleting the Cursor account removes Grok Bot agents, chats, computers and connected plugins, with all data removed within 30 days. Grok Bot cannot be deleted without deleting the Cursor account (https://cursor.com/help/grok-bot/delete-account)",
        "Cursor manages model selection. There is no model picker, the serving mix can change with no fixed vendor set guaranteed, and the Enterprise model allowlist is not guaranteed to be followed (https://docs.x.ai/grok-bot/security)",
        "Grok Bot requires cloud data storage and does not support Cursor's Legacy Privacy Mode. With Privacy Mode enabled, the docs say customer data is not used for training (https://docs.x.ai/grok-bot/approvals-security-and-privacy; https://docs.x.ai/grok-bot/teams-and-enterprises)",
        "status.cursor.com has a Grok Bot component. Sixteen incidents named Grok Bot between 18 August and 9 October 2026, seven of them marked major (https://status.cursor.com/history)",
        "Anysphere holds ISO/IEC 27001 and ISO/IEC 42001 certificates issued by Schellman, with Grok Bot in the current ISO scope per the docs. Cursor's security page also lists a SOC 2 Type II attestation and AIUC-1 (https://docs.x.ai/grok-bot/security; https://cursor.com/security)",
        "Cursor's Terms of Service bar scraping the Service, probing or scanning it, and giving third parties benchmark results without the information needed to replicate the tests. Recorded as a fact that matters before any probe is run (https://cursor.com/terms-of-service)",
        "x.ai/bot, the downloads page the docs link, and status.x.ai both answered our reader with HTTP 403 on 12 October 2026, so the download page, the x.ai legal index and the third-party bot terms were not read"
      ],
      "area": "frameworks",
      "details": [
        {
          "label": "What it does without asking",
          "value": "Runs routines on a schedule or after an event, works in the background on the cloud computer, starts a task from an @bot tag on X, and lets Bots message each other and pass tasks on. Which actions stop for approval depends on the tool, the risk and the owner's Auto-review rules. No fixed list of always-gated actions was found (https://docs.x.ai/grok-bot/faq)"
        },
        {
          "label": "Approval controls",
          "value": "Allow once, Always allow and Deny on each request. Personal Ask first and Allow automatically rules, with Ask first winning. Editable drafts for email and Slack messages. Unattended approvals expire after about 10 minutes. Local commands on the owner's own machine ask every time by default. Enterprise admins can enforce Auto-review and add team rules (https://docs.x.ai/grok-bot/approvals-security-and-privacy)"
        },
        {
          "label": "Accounts and credentials",
          "value": "Connectors are installed as plugins and authenticated in the browser. OAuth tokens stay on Cursor's backend and are not given to the Bot or stored on the computer. Sites without a connector are used through the browser, where the owner signs in by taking control, and those sessions persist on the shared computer. Connector scopes are not listed on the pages read (https://docs.x.ai/grok-bot/security; https://docs.x.ai/grok-bot/computer-and-apps)"
        },
        {
          "label": "Memory",
          "value": "A Bot keeps stable preferences, role context and summaries of prior work, separate for each Bot. A duplicate does not copy learned memory. Team Bots keep team memory plus private notes for each person. Auto Review does not check memory writes. No screen to view or delete single memories is described on the pages read (https://docs.x.ai/grok-bot/bots; https://docs.x.ai/grok-bot/team-bots)"
        },
        {
          "label": "Deletion",
          "value": "Deleting a Bot removes its profile, conversation and routines, not the shared files or browser sessions. Account deletion removes agents, chats, computers and plugins within 30 days. Under the DPA, data is deleted or returned within 30 days of written direction after the service ends. No retention policy per organisation (https://docs.x.ai/grok-bot/security; https://cursor.com/help/grok-bot/delete-account)"
        },
        {
          "label": "Where it runs",
          "value": "One Firecracker microVM per user in Cursor's cloud, in the United States today, with no written residency commitment by default. Cursor picks the model. Its status page names Grok, Anthropic and OpenAI models among those it serves, and the docs guarantee no fixed vendor set (https://docs.x.ai/grok-bot/security; https://status.cursor.com/history)"
        },
        {
          "label": "Channels",
          "value": "Desktop app for macOS, Windows and Linux, mobile app for iPhone, iPad and Android, with text, dictation, voice chat and voice memos. Tagging @bot on X. Slack for Team Bots. No SMS, WhatsApp, Telegram or email channel is described on the pages read (https://docs.x.ai/grok-bot/faq)"
        },
        {
          "label": "Cost",
          "value": "No separate subscription. Included with paid individual Cursor plans (the pricing page shows Individual at $20 a month) and Cursor Teams ($40 a user a month), or through a linked SuperGrok, SuperGrok Plus, SuperGrok Heavy or X Premium+ subscription. Weekly included usage with no published amount, then on-demand usage billed through Cursor (https://cursor.com/help/grok-bot/plans; https://cursor.com/pricing)"
        },
        {
          "label": "MCP client",
          "value": "Connectors follow the team's Cursor MCP policy. Team Bots accept custom MCP servers over remote HTTPS or as a command run on the conversation's computer (https://docs.x.ai/grok-bot/team-bots)"
        },
        {
          "label": "Logging",
          "value": "The transcript shows tool activity, computer use, files and approval requests. Audit logs, Action Recording (off by default, 90-day retention) and OpenTelemetry export are Enterprise only (https://docs.x.ai/grok-bot/security)"
        },
        {
          "label": "Status",
          "value": "status.cursor.com, with a Grok Bot component. Sixteen incidents named Grok Bot from 18 August to 9 October 2026, seven marked major (checked 2026-10-12)"
        }
      ],
      "unitPrices": [
        {
          "item": "Cursor Individual plan, as shown on the pricing page",
          "unit": "month",
          "usd": 20,
          "note": "Includes Grok Bot with weekly usage. On-demand usage extra"
        },
        {
          "item": "Cursor Teams plan",
          "unit": "seat-month",
          "usd": 40,
          "note": "Includes Grok Bot for every member. On-demand usage on by default"
        }
      ],
      "provenance": {
        "legalEntity": "Anysphere, Inc.",
        "domain": "cursor.com",
        "domainRegistered": "1995-12-20",
        "endpointOnVendorDomain": null,
        "terms": "https://cursor.com/en-US/terms/grok-bot",
        "privacy": "https://cursor.com/privacy",
        "statusPage": "https://status.cursor.com",
        "changelog": "",
        "securityTxt": "valid",
        "checked": "2026-10-12",
        "notes": [
          "The Grok Bot Terms (last updated 3 September 2026) supplement the agreement that governs the customer's use of the Services and define the Provider as the entity under that agreement. For a Cursor account that agreement is Cursor's Terms of Service (last updated 3 September 2026), which name Anysphere, Inc., 2261 Market Street STE 86466, San Francisco, CA 94114 (https://cursor.com/terms-of-service).",
          "The product docs are on docs.x.ai, titled SpaceXSI Docs, and name SpaceXAI. The Grok Bot Terms say they create no contractual relationship between the customer and any affiliate of the Provider. No page read states how the two companies are related.",
          "The privacy policy (last updated 11 October 2026) is Anysphere's and says it does not apply where Anysphere processes data for commercial customers as a processor.",
          "cursor.com/.well-known/security.txt gives a GitHub security page and security-reports@cursor.com as contacts and has no Expires field.",
          "The docs name api2.cursor.sh and *.cursorvm.com as the hosts the app and the cloud computer use. There is no endpoint an outside agent calls.",
          "RDAP for cursor.com gives a registration date of 1995-12-20.",
          "No changelog for Grok Bot was found. Cursor's changelog entries from 29 July to 6 October 2026 do not mention it.",
          "docs.x.ai's robots.txt allows every path with Content-Signal ai-input=yes. x.ai's robots.txt does the same, but x.ai/bot and status.x.ai answered HTTP 403."
        ],
        "score": 84,
        "checks": [
          {
            "check": "Legal entity named",
            "value": "Anysphere, Inc.",
            "points": 20,
            "max": 20,
            "state": "ok"
          },
          {
            "check": "Domain age",
            "value": "cursor.com, registered 1995-12-20 (30 years)",
            "points": 15,
            "max": 15,
            "state": "ok"
          },
          {
            "check": "Endpoint on the vendor's domain",
            "value": "no hosted endpoint",
            "points": 0,
            "max": 0,
            "state": "na"
          },
          {
            "check": "Terms of service",
            "value": "read, states 4 of the 7 things a reader expects",
            "points": 7.4,
            "max": 10,
            "state": "part"
          },
          {
            "check": "Privacy policy",
            "value": "read, states 7 of the 8 things a reader expects",
            "points": 9.3,
            "max": 10,
            "state": "part"
          },
          {
            "check": "Status page",
            "value": "status.cursor.com",
            "points": 10,
            "max": 10,
            "state": "ok"
          },
          {
            "check": "Changelog",
            "value": "not found",
            "points": 0,
            "max": 10,
            "state": "no"
          },
          {
            "check": "security.txt",
            "value": "valid",
            "points": 10,
            "max": 10,
            "state": "ok"
          }
        ],
        "policies": [
          {
            "kind": "terms",
            "url": "https://cursor.com/en-US/terms/grok-bot",
            "state": "read",
            "readAt": "2026-10-12",
            "statedDate": "2026-09-03",
            "words": 2361,
            "points": 7.4,
            "max": 10,
            "expected": [
              {
                "key": "terms.date",
                "label": "Gives the date it was last updated",
                "found": true,
                "quote": "Last updated September 3, 2026",
                "says": "Last updated 2026-09-03"
              },
              {
                "key": "terms.law",
                "label": "Names the governing law or courts",
                "found": false
              },
              {
                "key": "terms.liability",
                "label": "States a limit on its liability",
                "found": false
              },
              {
                "key": "terms.termination",
                "label": "Says how the agreement or account can be ended",
                "found": false
              },
              {
                "key": "terms.changes",
                "label": "Says how changes to the terms are announced",
                "found": true,
                "quote": "Customer’s continued use of Grok Bot after the Update Notice Period constitutes acceptance of the updated Grok Bot Terms.",
                "says": "Says it gives notice of a change"
              },
              {
                "key": "terms.use",
                "label": "Lists what users may not do",
                "found": true,
                "quote": "These Grok Bot Terms (“Grok Bot Terms”) supplement the agreement governing Customer’s use of the Services, which include the product identified as Grok Bot (“Grok Bot”), including any applicable Order Forms, data processing addendum, acceptable use policy, and incorporated terms (collectively, the “Agreement”)."
              },
              {
                "key": "terms.sla",
                "label": "Refers to a service level or uptime commitment",
                "found": true,
                "quote": "The Documentation does not create a service level, warranty, or commitment that any feature, integration, model, or configuration will remain available."
              }
            ],
            "notes": [
              {
                "date": "2026-10-08",
                "text": "The customer is solely responsible for charges, commitments, communications and other consequences of agentic actions that the customer or its users authorised or initiated.",
                "quote": "Customer is solely responsible for charges, commitments, communications, and other consequences resulting from Agentic Actions authorized or initiated by Customer or its Users."
              },
              {
                "date": "2026-10-08",
                "text": "Deleting a bot may leave shared files, sessions, credentials and routines in the persistent cloud environment.",
                "quote": "Deleting a Bot may not delete shared files, sessions, credentials, or routines."
              },
              {
                "date": "2026-10-08",
                "text": "The vendor may remove content or disable agentic actions without prior notice when delay would pose a risk to safety, security or third parties.",
                "quote": "Provider may remove content or disable Agentic Actions that Provider reasonably determines violate the Agreement, the applicable acceptable use policy, or applicable law, without prior notice when delay would pose a risk to safety, security, or third parties."
              }
            ]
          },
          {
            "kind": "privacy",
            "url": "https://cursor.com/privacy",
            "state": "read",
            "readAt": "2026-10-08",
            "statedDate": "2026-09-29",
            "words": 4956,
            "points": 9.3,
            "max": 10,
            "expected": [
              {
                "key": "privacy.date",
                "label": "Gives the date it was last updated",
                "found": true,
                "quote": "Last updated September 29, 2026",
                "says": "Last updated 2026-09-29"
              },
              {
                "key": "privacy.collected",
                "label": "Says what personal data is collected",
                "found": true,
                "quote": "Note: For information about how we collect and use training information to develop our models that power the Service, and your choices with respect to that information, please see our Privacy Overview."
              },
              {
                "key": "privacy.retention",
                "label": "Says how long data is kept",
                "found": true,
                "quote": "The appropriate retention period varies depending on the purpose for which the personal data was collected, its sensitivity, potential risks associated with its use or exposure, and any applicable legal requirements."
              },
              {
                "key": "privacy.processors",
                "label": "Says who else receives the data",
                "found": true,
                "quote": "We and our service providers utilize cookies, pixels, scripts, or similar technologies to operate and manage the Service and improve your experience."
              },
              {
                "key": "privacy.sale",
                "label": "Says whether personal data is sold or shared for advertising",
                "found": false
              },
              {
                "key": "privacy.rights",
                "label": "Says what rights people have over their data",
                "found": true,
                "quote": "These may include the right to access, delete, correct, or transfer your personal data;"
              },
              {
                "key": "privacy.contact",
                "label": "Gives a privacy contact",
                "found": true,
                "quote": "We encourage you to contact us at hi@cursor.com if you have any questions about this Privacy Policy.",
                "says": "hi@cursor.com"
              },
              {
                "key": "privacy.transfers",
                "label": "Says where data is transferred or stored",
                "found": true,
                "quote": "For users in the European Economic Area, (“EEA”), when you access our Service, your personal data may be transferred to our United States servers to other countries outside the EEA and the UK.",
                "says": "Data goes to the United States"
              }
            ],
            "notes": [
              {
                "date": "2026-10-08",
                "text": "Inputs and suggestions are not used for model training unless they are flagged for security review, reported by the user or explicitly agreed to.",
                "quote": "We do not use Inputs or Suggestions to train our models, or permit third parties to use them for training, unless: (1) they are flagged for security review (in which case we may analyze them to improve our ability to detect and enforce our Terms of Service), (2) you explicitly report them to us"
              },
              {
                "date": "2026-10-08",
                "text": "The policy does not apply where Anysphere processes personal data as a data processor for commercial customers, such as an account an employer set up.",
                "quote": "Please note that this Privacy Policy does not apply where Anysphere acts as a data processor and processes personal data on behalf of commercial customers using our commercial services, for example, if your employer has provisioned a Cursor account for you to use at work."
              }
            ]
          }
        ]
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/grok-bot.json",
      "live": {
        "slug": "grok-bot",
        "vendorStatus": {
          "page": "https://status.cursor.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-10-12T18:56:36.692375788Z"
        },
        "updatedAt": "2026-10-12T18:56:36.692375788Z"
      }
    },
    "verify": {
      "accepts": "a page on cursor.com or x.ai or one of their subdomains",
      "badgeUrl": "https://www.anchorterminal.com/badges/grok-bot.svg",
      "body": {
        "slug": "grok-bot",
        "url": "the page with the badge or the link"
      },
      "docs": "https://www.anchorterminal.com/builders/#verify",
      "effect": "none, it never changes a grade, rank or review",
      "endpoint": "https://www.anchorterminal.com/api/v1/verify",
      "listingUrl": "https://www.anchorterminal.com/tools/grok-bot",
      "mcpTool": "verify_listing",
      "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it",
      "snippets": {
        "html": "\u003ca href=\"https://www.anchorterminal.com/tools/grok-bot\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/grok-bot.svg\" alt=\"Grok Bot on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e",
        "markdown": "[![Grok Bot on Anchor Terminal](https://www.anchorterminal.com/badges/grok-bot.svg)](https://www.anchorterminal.com/tools/grok-bot)",
        "link": "\u003ca href=\"https://www.anchorterminal.com/tools/grok-bot\"\u003eGrok Bot on Anchor Terminal\u003c/a\u003e"
      }
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/tools/grok-bot",
    "json": "https://www.anchorterminal.com/tools/grok-bot.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/tools/grok-bot.md",
    "slim": "https://www.anchorterminal.com/tools/grok-bot.min.md"
  },
  "markdown": "## Overview\n\n**Grade E · 45.2/100 · rank #893 of 986 · #12 in Personal assistants · not agent-ready · confidence medium**\n\n\nMore from SpaceXAI and Cursor, listed separately because each is its own product: [Cursor CLI](https://www.anchorterminal.com/tools/cursor-cli.md) (Agent harnesses).\n\n## Assessment\n\nConnector tokens stay on Cursor's backend and each user gets a separate microVM, with approvals, drafts and a review model before risky actions. All of a user's Bots share one computer and its sign-ins, the review model skips memory writes, and the status page shows seven major Grok Bot incidents since 3 September 2026.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | SpaceXAI and Cursor (Anysphere, Inc.) (https://x.ai/bot) |\n| Kind | Platform |\n| Category | Personal assistants (https://www.anchorterminal.com/categories/personal-assistants) |\n| Auth | OAuth or key · A person signs in with a Cursor account in the browser, or with Sign in with Grok for a Grok Business seat. SAML 2.0 single sign-on applies to teams, and SCIM is Enterprise only. Connectors are added from Connect apps and authenticated in the browser by OAuth, or configured with a key or token. OAuth tokens stay on Cursor's backend. For passwords, passkeys, two-factor codes, CAPTCHAs and payment confirmations the Bot hands the computer to the owner, and a secure secret request masks a value and keeps it out of the transcript and away from the model. Browser sessions then persist on the cloud computer shared by all of the user's Bots (https://docs.x.ai/grok-bot/security; https://docs.x.ai/grok-bot/approvals-security-and-privacy; https://docs.x.ai/grok-bot/team-bots). No API key or public API for the assistant was found. An Admin API for team settings is linked from the docs and was not read. |\n| Pricing | Paid ($20 / mo) · No separate subscription. Grok Bot is included with every paid individual Cursor plan (Pro, Pro+, Ultra) and with Cursor Teams, or through a linked individual SuperGrok, SuperGrok Plus, SuperGrok Heavy or X Premium+ subscription, or a seat on a self-serve Grok Business plan. Cursor's pricing page shows Individual at $20 a month and Teams at $40 a user a month. The Pro+ and Ultra prices sit behind tabs our reader did not see. Each tier includes weekly usage with no amount published, metered by agent steps and tokens. After that, on-demand usage is billed through Cursor up to a monthly limit the owner sets, which is not a hard stop in the middle of a run. A free trial is a usage credit with a 7-day window and never becomes a paid plan. SuperGrok Lite is not included, and a SuperGrok link cannot be undone or moved (https://cursor.com/help/grok-bot/plans; https://cursor.com/pricing; checked 2026-10-12). |\n| x402 | No · No x402, MPP or L402 in the Grok Bot docs, the plans page or the Grok Bot Terms (checked 2026-10-12). |\n| Licence | Proprietary |\n| Docs | https://docs.x.ai/grok-bot/overview |\n| llms.txt | https://docs.x.ai/llms.txt |\n| What it does without asking | Runs routines on a schedule or after an event, works in the background on the cloud computer, starts a task from an @bot tag on X, and lets Bots message each other and pass tasks on. Which actions stop for approval depends on the tool, the risk and the owner's Auto-review rules. No fixed list of always-gated actions was found (https://docs.x.ai/grok-bot/faq) |\n| Approval controls | Allow once, Always allow and Deny on each request. Personal Ask first and Allow automatically rules, with Ask first winning. Editable drafts for email and Slack messages. Unattended approvals expire after about 10 minutes. Local commands on the owner's own machine ask every time by default. Enterprise admins can enforce Auto-review and add team rules (https://docs.x.ai/grok-bot/approvals-security-and-privacy) |\n| Accounts and credentials | Connectors are installed as plugins and authenticated in the browser. OAuth tokens stay on Cursor's backend and are not given to the Bot or stored on the computer. Sites without a connector are used through the browser, where the owner signs in by taking control, and those sessions persist on the shared computer. Connector scopes are not listed on the pages read (https://docs.x.ai/grok-bot/security; https://docs.x.ai/grok-bot/computer-and-apps) |\n| Memory | A Bot keeps stable preferences, role context and summaries of prior work, separate for each Bot. A duplicate does not copy learned memory. Team Bots keep team memory plus private notes for each person. Auto Review does not check memory writes. No screen to view or delete single memories is described on the pages read (https://docs.x.ai/grok-bot/bots; https://docs.x.ai/grok-bot/team-bots) |\n| Deletion | Deleting a Bot removes its profile, conversation and routines, not the shared files or browser sessions. Account deletion removes agents, chats, computers and plugins within 30 days. Under the DPA, data is deleted or returned within 30 days of written direction after the service ends. No retention policy per organisation (https://docs.x.ai/grok-bot/security; https://cursor.com/help/grok-bot/delete-account) |\n| Where it runs | One Firecracker microVM per user in Cursor's cloud, in the United States today, with no written residency commitment by default. Cursor picks the model. Its status page names Grok, Anthropic and OpenAI models among those it serves, and the docs guarantee no fixed vendor set (https://docs.x.ai/grok-bot/security; https://status.cursor.com/history) |\n| Channels | Desktop app for macOS, Windows and Linux, mobile app for iPhone, iPad and Android, with text, dictation, voice chat and voice memos. Tagging @bot on X. Slack for Team Bots. No SMS, WhatsApp, Telegram or email channel is described on the pages read (https://docs.x.ai/grok-bot/faq) |\n| Cost | No separate subscription. Included with paid individual Cursor plans (the pricing page shows Individual at $20 a month) and Cursor Teams ($40 a user a month), or through a linked SuperGrok, SuperGrok Plus, SuperGrok Heavy or X Premium+ subscription. Weekly included usage with no published amount, then on-demand usage billed through Cursor (https://cursor.com/help/grok-bot/plans; https://cursor.com/pricing) |\n| MCP client | Connectors follow the team's Cursor MCP policy. Team Bots accept custom MCP servers over remote HTTPS or as a command run on the conversation's computer (https://docs.x.ai/grok-bot/team-bots) |\n| Logging | The transcript shows tool activity, computer use, files and approval requests. Audit logs, Action Recording (off by default, 90-day retention) and OpenTelemetry export are Enterprise only (https://docs.x.ai/grok-bot/security) |\n| Status | status.cursor.com, with a Grok Bot component. Sixteen incidents named Grok Bot from 18 August to 9 October 2026, seven marked major (checked 2026-10-12) |\n| Capabilities | assistant.proactive, assistant.accounts, assistant.memory, assistant.messaging, agent.mcp-client |\n| Tags | hosted, closed-source, desktop-app, mobile-app, computer-use, scheduled-routines, slack, status-page, iso27001, soc2, llms-txt, paid |\n| JSON | https://www.anchorterminal.com/api/v1/tools/grok-bot.json |\n\n## Score breakdown (methodology v0.4, October 2026 research run)\n\nAssessed 2026-10-12 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 40 | 8.0 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 40 | 6.5 |\n| Agent ergonomics | 13% | 16.2 | 50 | 8.1 |\n| Security \u0026 auth | 14% | 17.5 | 68 | 11.9 |\n| Payments \u0026 pricing | 10% | 12.5 | 25 | 3.1 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 20 | 1.8 |\n| Transparency \u0026 trust (editorial 48, provenance 84) | 7% | 8.8 | 66 | 5.8 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **45.2 → E** |\n\n### Why each score\n\n- Reliability 40: Read with the hosted lines. status.cursor.com has a Grok Bot component with 90 days of uptime history (20). The history page lists sixteen incidents that name Grok Bot between 18 August and 9 October 2026, seven of them marked major. They fell on 3 September (routine triggers, one hour), 7 September (computers unreachable for some users, 65 minutes), 16 September (six and a half hours), 17 September (two hours), 18 September (two, about three hours and under six hours) and 6 October (with Cloud Agents, restored after about two hours). Several majors (0). Product limits are published for routines (50 a Bot, five minutes apart, 20 run records), unattended approvals (about 10 minutes) and group chats (two to six Bots), but the weekly usage allowance has no number (7 of 15). The plans page says what happens when usage runs out and that the monthly limit is not a hard stop mid-run, and the docs give recover, update and reset steps for the computer and advise idempotent retries in routines, with no retry guarantees (5 of 15). No SLA was found, and the Grok Bot Terms say the documentation creates no service level (0). No beta label on the pages read, though teach-by-demonstration, cross-conversation search, Enterprise access and X tagging are described as rolling out or limited by region (8 of 10).\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 40: Grok Bot is an app, so the API lines are read for what a person or an agent setting it up can rely on. No machine-readable contract for the assistant was found. The docs link an Admin API for team settings on cursor.com, which we did not read (0 of 25). docs.x.ai serves an llms.txt that lists every Grok Bot page, a Markdown copy of each page and a Copy for LLM button (10). The pages state purpose and limits plainly, including what Auto Review does not cover, what deleting a Bot leaves behind and that separate Bots are not a security boundary (16 of 20). The interface is natural language. Auto-review rules are free text, and the one typed format found is the secret name pattern for Team Bots (3 of 15). Example prompts on most pages and a table of @bot replies with their meaning. A troubleshooting page exists and was not read (9 of 15). No Grok Bot changelog or version history was found. The desktop app shows its version, and the Grok Bot Terms carry a last-updated date (2 of 15).\n- Agent ergonomics 50: Read for an owner directing the assistant. Usage is metered by agent steps and tokens with a weekly allowance and an on-demand monthly limit, but there is no budget for one task, no separate Grok Bot spend cap and no model choice (10 of 25). A search palette covers Bots, messages, files and routines, each routine keeps its 20 latest runs, and notifications are set for each Bot (10 of 20). Errors show above the composer with a request ID, expired approvals are labelled, blocked plugins read Disabled by team admin, and the @bot replies are documented (12 of 20). Allow once, Always allow and Deny on each request, Ask first rules, drafts with Send and Discard, and a Test run that the docs warn performs real work. A Stop now message does not undo completed actions and nothing is described as reversible (10 of 20). Defaults lean cautious for local commands (Ask every time) and a Bot starts with no access, while network access defaults to allow-all. Apps for five platforms and no SDK (8 of 15).\n- Security \u0026 auth 68: Read with the tool lines, applied to the accounts the assistant holds. Bots work as the signed-in member with no identity of their own. Connector OAuth tokens stay on Cursor's backend and are never stored on the computer, passwords and two-factor steps go to the owner by takeover, and a secure secret request keeps a value away from the model. Against that, browser sessions, cookies and command-line credentials persist on one cloud computer that every Bot of the user shares, and connector scopes are not listed on the pages read (20 of 30). Approvals, Ask first and Allow automatically rules, editable drafts, a 10-minute expiry on unattended approvals and Ask every time for local commands. The FAQ says which actions need approval depends on the tool, the risk and the owner's rules, Auto Review is model-based and does not check memory writes or most settings changes, Team Bot plugins run without asking, and the terms call these controls aids only (13 of 20). A prompt-injection section says outside content is marked as untrusted, Auto Review checks actions against the request, and network policy and approvals sit beneath it, and that the risk is reduced, not removed (11 of 15). The transcript shows tool activity and computer use and routines keep run records. Audit logs, Action Recording and OpenTelemetry export are Enterprise only (8 of 15). security.txt and a disclosure address with a five-business-day acknowledgement, ISO/IEC 27001 and 42001 with Grok Bot in scope per the docs, SOC 2 Type II and AIUC-1 per Cursor's security page, yearly penetration tests, and advisories published on GitHub, none of the ten newest naming Grok Bot. No bug bounty found (16 of 20).\n- Payments \u0026 pricing 25: No machine payment protocol (0). Pricing is by plan and public. Cursor's pricing page shows Individual at $20 a month and Teams at $40 a user a month with Grok Bot included, but the weekly usage amounts and the on-demand rate are not published on the pages read (10 of 20). The plans page describes a free trial as a usage credit with a 7-day window that never becomes a paid plan, and Cursor's free Hobby plan needs no card. Whether the Grok Bot trial itself needs a card is not stated (15 of 20). A person signs in through a browser, so an agent cannot start alone (0).\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 20: No dated release notes or changelog for Grok Bot were found. Cursor's changelog entries from 29 July to 6 October 2026 do not mention it, and x.ai/bot, which may carry versions, answered 403. Scored as absent, which may understate a service that had status updates through 9 October 2026 (0 of 30, and 0 of 20 for three dated entries). Support runs through support@x.ai, a Discord server, Cursor's help centre with Grok Bot articles and a status page with dated incident updates (10 of 15 for a closed service). No SDK and not an MCP server. Official apps for five platforms update themselves (5 of 15). The cloud computer's image is updated with files kept, and no public build or test record exists (5 of 10).\n- Transparency \u0026 trust 66: Closed source with clear terms. The Grok Bot Terms and Cursor's Terms of Service are public and dated (15 of 30). The docs give concrete periods (Action Recording kept 90 days, account data removed within 30 days, deletion within 30 days of written direction under the DPA, daily backups) and say plainly that deleting a Bot leaves files and sessions. They give no period for a deleted Bot's backend data beyond the applicable Cursor terms, the privacy policy says only as long as necessary, and there is no retention policy per organisation. Training is off with Privacy Mode, and the privacy policy says inputs are not used for training unless flagged, reported or agreed (19 of 30). No deprecation policy. The terms say the documentation is no commitment that any function, integration or model will stay, with reasonable notice only for materially adverse changes to the terms (4 of 20). Computers run in the United States with no residency commitment, the subprocessor list is on a trust portal we could not read, and the docs say no fixed set of model vendors is guaranteed (10 of 20).\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (25 items): https://www.anchorterminal.com/fixes/grok-bot.md (JSON https://www.anchorterminal.com/fixes/grok-bot.json)\n\n### What we couldn't check\n\n- Kind. We chose `platform`, the brief's kind for a desktop, web or phone app, because Grok Bot is reached through its own apps, Slack and X and has no API an outside agent calls. `metrics.kind` is `remote` and it is graded as a hosted service\n- Vendor. The lead named xAI. The docs are on docs.x.ai and name SpaceXAI, while accounts, billing, hosting, terms, privacy policy and status page are Cursor's (Anysphere, Inc.). No page read states how the companies are related\n- The lead said access comes through eligible Cursor and SuperGrok plans. The plans page confirms that and adds X Premium+ and self-serve Grok Business seats\n- Unchecked: a Business Insider report of 10 October 2026 named in the lead. We did not read it, nothing on the vendor pages read mentions an incident of that kind, and no deduction is taken\n- Unchecked: x.ai/bot (downloads and product page), the x.ai legal index and the third-party bot terms at x.ai/legal/bot-sharing-terms. x.ai/bot answered HTTP 403 and we sent x.ai nothing more\n- Unchecked: status.x.ai, which the docs header links, answered HTTP 403. Reliability is scored on status.cursor.com, which has the Grok Bot component\n- Unchecked: release dates. No Grok Bot changelog or version history was found, so `lastRelease` is null and Maintenance scores recency as absent\n- Unchecked: the list of connectors in Connect apps and their scopes. Cursor's changelog of 3 August 2026 announces Gmail, Google Drive and Calendar plugins for Cursor, and the Grok Bot docs mention email and Slack drafts, an X plugin, Jira and Linear, without a full list\n- Unchecked: the subprocessor list and certificates on trust.cursor.com (a script-drawn portal whose robots.txt request returned the portal page), the DPA, and Cursor's privacy overview on training data\n- Unchecked: the Pro+ and Ultra prices (behind tabs on the pricing page), the weekly usage amounts and the on-demand rate\n- Unchecked: these docs pages, left unread to keep to the page limit. Mobile, files and results, use cases, troubleshooting, identity and access, private networks, proxies, manage computers, and the Admin API on cursor.com\n- Unchecked: whether Auto Review is on by default for an individual account. The docs describe behaviour with Auto Review on and say Enterprise admins can enforce it\n- Whether single memories can be viewed, exported or deleted. The docs read describe what a Bot remembers and say to correct stale assumptions in conversation\n- Cursor's Terms of Service bar scraping, probing and scanning the Service and restrict sharing benchmark results. This matters before any probe or task suite is run\n- We read 16 pages on docs.x.ai, one over the brief's limit of about fifteen\n\n### Sources\n\n- Grok Bot overview: \u003chttps://docs.x.ai/grok-bot/overview\u003e (seen 2026-10-12)\n- approvals, security and privacy (Markdown copy): \u003chttps://docs.x.ai/grok-bot/approvals-security-and-privacy.md\u003e (seen 2026-10-12)\n- Grok Bot security (Markdown copy): \u003chttps://docs.x.ai/grok-bot/security.md\u003e (seen 2026-10-12)\n- security FAQ (Markdown copy): \u003chttps://docs.x.ai/grok-bot/security-faq.md\u003e (seen 2026-10-12)\n- computer and apps (Markdown copy): \u003chttps://docs.x.ai/grok-bot/computer-and-apps.md\u003e (seen 2026-10-12)\n- skills and routines (Markdown copy): \u003chttps://docs.x.ai/grok-bot/skills-routines-and-automations.md\u003e (seen 2026-10-12)\n- message and collaborate (Markdown copy): \u003chttps://docs.x.ai/grok-bot/chat-and-collaboration.md\u003e (seen 2026-10-12)\n- create and manage Bots (Markdown copy): \u003chttps://docs.x.ai/grok-bot/bots.md\u003e (seen 2026-10-12)\n- Team Bots (Markdown copy): \u003chttps://docs.x.ai/grok-bot/team-bots.md\u003e (seen 2026-10-12)\n- teams and enterprises (Markdown copy): \u003chttps://docs.x.ai/grok-bot/teams-and-enterprises.md\u003e (seen 2026-10-12)\n- settings and notifications (Markdown copy): \u003chttps://docs.x.ai/grok-bot/settings-and-notifications.md\u003e (seen 2026-10-12)\n- FAQ (Markdown copy): \u003chttps://docs.x.ai/grok-bot/faq.md\u003e (seen 2026-10-12)\n- Tag @bot on X (Markdown copy): \u003chttps://docs.x.ai/grok-bot/tag-on-x.md\u003e (seen 2026-10-12)\n- get started (Markdown copy): \u003chttps://docs.x.ai/grok-bot/get-started.md\u003e (seen 2026-10-12)\n- docs llms.txt: \u003chttps://docs.x.ai/llms.txt\u003e (seen 2026-10-12)\n- docs robots.txt (HTTP 200, allow all, ai-input=yes): \u003chttps://docs.x.ai/robots.txt\u003e (seen 2026-10-12)\n- plans and billing: \u003chttps://cursor.com/help/grok-bot/plans\u003e (seen 2026-10-12)\n- Cursor pricing: \u003chttps://cursor.com/pricing\u003e (seen 2026-10-12)\n- Grok Bot Terms, last updated 3 September 2026: \u003chttps://cursor.com/en-US/terms/grok-bot\u003e (seen 2026-10-12)\n- Cursor Terms of Service, last updated 3 September 2026: \u003chttps://cursor.com/terms-of-service\u003e (seen 2026-10-12)\n- Cursor privacy policy, last updated 11 October 2026: \u003chttps://cursor.com/privacy\u003e (seen 2026-10-12)\n- Cursor security page, last updated 25 August 2026: \u003chttps://cursor.com/security\u003e (seen 2026-10-12)\n- delete your Grok Bot account: \u003chttps://cursor.com/help/grok-bot/delete-account\u003e (seen 2026-10-12)\n- Cursor changelog, pages 1 and 2: \u003chttps://cursor.com/changelog\u003e (seen 2026-10-12)\n- security.txt: \u003chttps://cursor.com/.well-known/security.txt\u003e (seen 2026-10-12)\n- cursor.com robots.txt (HTTP 200): \u003chttps://cursor.com/robots.txt\u003e (seen 2026-10-12)\n- status page: \u003chttps://status.cursor.com/\u003e (seen 2026-10-12)\n- status history, August to October 2026: \u003chttps://status.cursor.com/history\u003e (seen 2026-10-12)\n- Cursor security advisories on GitHub, first page: \u003chttps://github.com/cursor/cursor/security/advisories\u003e (seen 2026-10-12)\n- RDAP record for cursor.com: \u003chttps://rdap.verisign.com/com/v1/domain/cursor.com\u003e (seen 2026-10-12)\n- x.ai robots.txt (HTTP 200, ai-input=yes). The product page x.ai/bot then answered 403: \u003chttps://x.ai/robots.txt\u003e (seen 2026-10-12)\n\n## Who's behind it (provenance 84/100, checked 2026-10-12)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Anysphere, Inc. | 20/20 |\n| Domain age | cursor.com, registered 1995-12-20 (30 years) | 15/15 |\n| Endpoint on the vendor's domain | no hosted endpoint | n/a |\n| Terms of service | read, states 4 of the 7 things a reader expects | 7.4/10 |\n| Privacy policy | read, states 7 of the 8 things a reader expects | 9.3/10 |\n| Status page | status.cursor.com | 10/10 |\n| Changelog | not found | 0/10 |\n| security.txt | valid | 10/10 |\n\nThe Grok Bot Terms (last updated 3 September 2026) supplement the agreement that governs the customer's use of the Services and define the Provider as the entity under that agreement. For a Cursor account that agreement is Cursor's Terms of Service (last updated 3 September 2026), which name Anysphere, Inc., 2261 Market Street STE 86466, San Francisco, CA 94114 (https://cursor.com/terms-of-service).\n\nThe product docs are on docs.x.ai, titled SpaceXSI Docs, and name SpaceXAI. The Grok Bot Terms say they create no contractual relationship between the customer and any affiliate of the Provider. No page read states how the two companies are related.\n\nThe privacy policy (last updated 11 October 2026) is Anysphere's and says it does not apply where Anysphere processes data for commercial customers as a processor.\n\ncursor.com/.well-known/security.txt gives a GitHub security page and security-reports@cursor.com as contacts and has no Expires field.\n\nThe docs name api2.cursor.sh and *.cursorvm.com as the hosts the app and the cloud computer use. There is no endpoint an outside agent calls.\n\nRDAP for cursor.com gives a registration date of 1995-12-20.\n\nNo changelog for Grok Bot was found. Cursor's changelog entries from 29 July to 6 October 2026 do not mention it.\n\ndocs.x.ai's robots.txt allows every path with Content-Signal ai-input=yes. x.ai's robots.txt does the same, but x.ai/bot and status.x.ai answered HTTP 403.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://cursor.com/en-US/terms/grok-bot), read 2026-10-12, dated 2026-09-03, states 4 of the 7 things a reader expects.\n\n- Gives the date it was last updated. Last updated 2026-09-03.\n- Not found in the text. Names the governing law or courts.\n- Not found in the text. States a limit on its liability.\n- Not found in the text. Says how the agreement or account can be ended.\n- Says how changes to the terms are announced. Says it gives notice of a change.\n- Also in the text (2026-10-08). The customer is solely responsible for charges, commitments, communications and other consequences of agentic actions that the customer or its users authorised or initiated. \"Customer is solely responsible for charges, commitments, communications, and other consequences resulting from Agentic Actions authorized or initiated by Customer or its Users.\"\n- Also in the text (2026-10-08). Deleting a bot may leave shared files, sessions, credentials and routines in the persistent cloud environment. \"Deleting a Bot may not delete shared files, sessions, credentials, or routines.\"\n- Also in the text (2026-10-08). The vendor may remove content or disable agentic actions without prior notice when delay would pose a risk to safety, security or third parties. \"Provider may remove content or disable Agentic Actions that Provider reasonably determines violate the Agreement, the applicable acceptable use policy, or applicable law, without prior notice when delay would pose a risk to safety, security, or third parties.\"\n\n**Privacy policy** (https://cursor.com/privacy), read 2026-10-08, dated 2026-09-29, states 7 of the 8 things a reader expects.\n\n- Gives the date it was last updated. Last updated 2026-09-29.\n- Not found in the text. Says whether personal data is sold or shared for advertising.\n- Gives a privacy contact. hi@cursor.com.\n- Says where data is transferred or stored. Data goes to the United States.\n- Also in the text (2026-10-08). Inputs and suggestions are not used for model training unless they are flagged for security review, reported by the user or explicitly agreed to. \"We do not use Inputs or Suggestions to train our models, or permit third parties to use them for training, unless: (1) they are flagged for security review (in which case we may analyze them to improve our ability to detect and enforce our Terms of Service), (2) you explicitly report them to us\"\n- Also in the text (2026-10-08). The policy does not apply where Anysphere processes personal data as a data processor for commercial customers, such as an account an employer set up. \"Please note that this Privacy Policy does not apply where Anysphere acts as a data processor and processes personal data on behalf of commercial customers using our commercial services, for example, if your employer has provisioned a Cursor account for you to use at work.\"\n\n## Live (updated 2026-10-12 18:56 UTC)\n\n- Vendor status page: none, All Systems Operational\n- Always current: https://www.anchorterminal.com/api/v1/live/grok-bot.json\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Prices\n\n| Item | Price | Unit | Note |\n| --- | --- | --- | --- |\n| Cursor Individual plan, as shown on the pricing page | $20 | per month (plan) | Includes Grok Bot with weekly usage. On-demand usage extra |\n| Cursor Teams plan | $40 | per seat per month | Includes Grok Bot for every member. On-demand usage on by default |\n\nAcross all listings: https://www.anchorterminal.com/prices/index.md\n\n## Strengths\n\n- Connector OAuth tokens stay on Cursor's backend. Bots call tools without receiving them, and tokens are never stored on the cloud computer\n- Each user's work runs in a dedicated Firecracker microVM. A Bot has no identity of its own and holds no more access than the signed-in member\n- Approvals from routines, triggers or other Bots expire after about 10 minutes and the action does not run\n- Email and Slack messages can appear as editable drafts with Send and Discard buttons, and passwords, two-factor codes and payment confirmations are handed to the owner\n- Markdown copies of every docs page and an llms.txt, with a security page that states what the controls do not cover\n\n## Weaknesses\n\n- All of one user's Bots share one cloud computer, with its files, browser sessions and command-line credentials. The docs say separate Bots are not a security boundary\n- The review model does not check memory writes or most settings changes, and the Grok Bot Terms call approval controls aids only\n- Deleting a Bot leaves shared files and browser sessions on the computer. No way to view or delete single memories was found in the docs read\n- Seven incidents marked major named Grok Bot on status.cursor.com between 3 September and 6 October 2026, the longest about six and a half hours\n- Audit logs, Action Recording, network allowlists and enforced review rules are Enterprise only. Other teams default to allow-all network access\n- Cursor chooses the model with no picker and no fixed set of model vendors, and no Grok Bot changelog was found\n\n## Before you call it (notes for agents)\n\n1. State in each request what the Bot may change and where it must stop. Which actions pause for approval depends on the tool, the risk and the owner's Auto-review rules\n2. Add narrow Ask first rules for sending, publishing, purchasing and deleting. Ask first wins over Allow automatically when both match\n3. Treat any sign-in or file on the cloud computer as available to every Bot on the account. Give a workload its own Cursor user when it needs separate credentials\n4. Run Test run with safe inputs. A test run performs real work and can call connected tools\n5. To remove access, pause routines, sign out of sites on the computer, uninstall connectors and revoke them at the source service. Deleting the Bot is not enough\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| ZeroClaw | BB | 70.2 | 161 | assistant.proactive, assistant.messaging, assistant.memory, assistant.accounts, agent.mcp-client | no | https://www.anchorterminal.com/tools/zeroclaw.md |\n| NanoClaw | B | 68.3 | 229 | assistant.proactive, assistant.messaging, assistant.memory, agent.mcp-client, assistant.accounts | no | https://www.anchorterminal.com/tools/nanoclaw.md |\n| Hermes Agent | B | 67.9 | 244 | assistant.proactive, assistant.messaging, assistant.accounts, assistant.memory, agent.mcp-client | no | https://www.anchorterminal.com/tools/hermes-agent.md |\n| OpenClaw | B | 67.1 | 270 | assistant.proactive, assistant.messaging, assistant.accounts, assistant.memory, agent.mcp-client | no | https://www.anchorterminal.com/tools/openclaw.md |\n| IronClaw | B | 66.7 | 288 | assistant.proactive, assistant.messaging, assistant.accounts, assistant.memory, agent.mcp-client | no | https://www.anchorterminal.com/tools/ironclaw.md |\n| nanobot | B | 62.4 | 446 | assistant.proactive, assistant.messaging, assistant.memory, assistant.accounts, agent.mcp-client | no | https://www.anchorterminal.com/tools/nanobot.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- Grok Bot is documented on docs.x.ai, whose pages are titled SpaceXSI Docs and name SpaceXAI in the text, while sign-in, billing, hosting, terms, privacy policy and status page are Cursor's (Anysphere, Inc.) (source: \u003chttps://docs.x.ai/grok-bot/overview\u003e, \u003chttps://cursor.com/en-US/terms/grok-bot\u003e)\n- Each Bot works on a persistent cloud computer with a browser, filesystem and terminal. The computers run in Cursor's cloud, in the United States today, with no on-premises or bring-your-own-image option (source: \u003chttps://docs.x.ai/grok-bot/security\u003e)\n- Every Bot on an account uses the same computer. Browser cookies, signed-in sessions, files and command-line credentials are shared across them (source: \u003chttps://docs.x.ai/grok-bot/computer-and-apps\u003e)\n- Auto Review is a separate review model that evaluates shell commands, plugin calls, computer use, changes to routines and triggers, and delegation. It can let an action proceed, require approval or deny it. The docs say it does not review every side effect, naming memory writes and most settings changes (source: \u003chttps://docs.x.ai/grok-bot/security\u003e)\n- An approval requested by work that started without the owner (a routine, a trigger or a message from another Bot) expires after about 10 minutes and the action does not run (source: \u003chttps://docs.x.ai/grok-bot/approvals-security-and-privacy\u003e)\n- Routines run on a schedule or after an event such as a Slack message or a GitHub notification. A Bot can own up to 50 routines, schedules must be at least five minutes apart, and the app keeps the 20 most recent runs of each (source: \u003chttps://docs.x.ai/grok-bot/skills-routines-and-automations\u003e)\n- Tagging @bot in a post on X hands the post to the owner's main Bot as a task, and X's first-use notice says tagged requests start work automatically. Not available for X accounts based in Australia, the United Kingdom, the European Union, Iceland, Liechtenstein or Norway (source: \u003chttps://docs.x.ai/grok-bot/tag-on-x\u003e)\n- A Team Bot can have its own Slack app that teammates DM or @mention. Plugins added to a Team Bot are used in every conversation without asking anyone first, with each teammate's own account where the plugin signs in by OAuth (source: \u003chttps://docs.x.ai/grok-bot/team-bots\u003e)\n- Teams without a network policy default to allow-all, and Network Controls are Enterprise only. Hosted computers leave through static egress IP ranges shared across customers (source: \u003chttps://docs.x.ai/grok-bot/security\u003e)\n- The Grok Bot Terms (last updated 3 September 2026) say approval and automated-review controls are aids only, may not prevent every unintended or harmful action, and do not reverse completed actions. The customer is solely responsible for all agentic actions (source: \u003chttps://cursor.com/en-US/terms/grok-bot\u003e)\n- The Grok Bot Terms say the service may retain customer data, files, browser sessions, credentials, memory and routines in a persistent cloud environment, and that deleting a Bot may not delete shared files, sessions, credentials or routines (source: \u003chttps://cursor.com/en-US/terms/grok-bot\u003e)\n- Deleting the Cursor account removes Grok Bot agents, chats, computers and connected plugins, with all data removed within 30 days. Grok Bot cannot be deleted without deleting the Cursor account (source: \u003chttps://cursor.com/help/grok-bot/delete-account\u003e)\n- Cursor manages model selection. There is no model picker, the serving mix can change with no fixed vendor set guaranteed, and the Enterprise model allowlist is not guaranteed to be followed (source: \u003chttps://docs.x.ai/grok-bot/security\u003e)\n- Grok Bot requires cloud data storage and does not support Cursor's Legacy Privacy Mode. With Privacy Mode enabled, the docs say customer data is not used for training (source: \u003chttps://docs.x.ai/grok-bot/approvals-security-and-privacy\u003e, \u003chttps://docs.x.ai/grok-bot/teams-and-enterprises\u003e)\n- status.cursor.com has a Grok Bot component. Sixteen incidents named Grok Bot between 18 August and 9 October 2026, seven of them marked major (source: \u003chttps://status.cursor.com/history\u003e)\n- Anysphere holds ISO/IEC 27001 and ISO/IEC 42001 certificates issued by Schellman, with Grok Bot in the current ISO scope per the docs. Cursor's security page also lists a SOC 2 Type II attestation and AIUC-1 (source: \u003chttps://docs.x.ai/grok-bot/security\u003e, \u003chttps://cursor.com/security\u003e)\n- Cursor's Terms of Service bar scraping the Service, probing or scanning it, and giving third parties benchmark results without the information needed to replicate the tests. Recorded as a fact that matters before any probe is run (source: \u003chttps://cursor.com/terms-of-service\u003e)\n- x.ai/bot, the downloads page the docs link, and status.x.ai both answered our reader with HTTP 403 on 12 October 2026, so the download page, the x.ai legal index and the third-party bot terms were not read\n\n- #12 of 20 in Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md\n- All 190 assistants comparisons: https://www.anchorterminal.com/compare/personal-assistants/index.md\n\n## Compare\n\n- [AstrBot vs Grok Bot](https://www.anchorterminal.com/compare/astrbot-vs-grok-bot.md): C 58.8 vs E 45.2\n- [CowAgent vs Grok Bot](https://www.anchorterminal.com/compare/cowagent-vs-grok-bot.md): C 58.5 vs E 45.2\n- [GAIA vs Grok Bot](https://www.anchorterminal.com/compare/gaia-vs-grok-bot.md): D 49.5 vs E 45.2\n- [Gemini Spark vs Grok Bot](https://www.anchorterminal.com/compare/gemini-spark-vs-grok-bot.md): F 24.5 vs E 45.2\n- [Grok Bot vs Haven](https://www.anchorterminal.com/compare/grok-bot-vs-haven.md): E 45.2 vs F 22.2\n- [Grok Bot vs Hermes Agent](https://www.anchorterminal.com/compare/grok-bot-vs-hermes-agent.md): E 45.2 vs B 67.9\n- [Grok Bot vs Instinct](https://www.anchorterminal.com/compare/grok-bot-vs-instinct.md): E 45.2 vs F 11.4\n- [Grok Bot vs IronClaw](https://www.anchorterminal.com/compare/grok-bot-vs-ironclaw.md): E 45.2 vs B 66.7\n- [Grok Bot vs Leon](https://www.anchorterminal.com/compare/grok-bot-vs-leon.md): E 45.2 vs E 41\n- [Grok Bot vs Lindy](https://www.anchorterminal.com/compare/grok-bot-vs-lindy.md): E 45.2 vs F 32.3\n- [Grok Bot vs nanobot](https://www.anchorterminal.com/compare/grok-bot-vs-nanobot.md): E 45.2 vs B 62.4\n- [Grok Bot vs NanoClaw](https://www.anchorterminal.com/compare/grok-bot-vs-nanoclaw.md): E 45.2 vs B 68.3\n- [Grok Bot vs Dots](https://www.anchorterminal.com/compare/grok-bot-vs-openai-dots.md): E 45.2 vs F 28.3\n- [Grok Bot vs OpenClaw](https://www.anchorterminal.com/compare/grok-bot-vs-openclaw.md): E 45.2 vs B 67.1\n- [Grok Bot vs PicoClaw](https://www.anchorterminal.com/compare/grok-bot-vs-picoclaw.md): E 45.2 vs D 46.1\n- [Grok Bot vs Poke](https://www.anchorterminal.com/compare/grok-bot-vs-poke.md): E 45.2 vs F 37.6\n- [Grok Bot vs QwenPaw](https://www.anchorterminal.com/compare/grok-bot-vs-qwenpaw.md): E 45.2 vs B 62.2\n- [Grok Bot vs ZeroClaw](https://www.anchorterminal.com/compare/grok-bot-vs-zeroclaw.md): E 45.2 vs BB 70.2\n- [Grok Bot vs Zo Computer](https://www.anchorterminal.com/compare/grok-bot-vs-zo-computer.md): E 45.2 vs E 43.1\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on cursor.com or x.ai or one of their subdomains. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"grok-bot\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/grok-bot\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/grok-bot.svg\" alt=\"Grok Bot on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![Grok Bot on Anchor Terminal](https://www.anchorterminal.com/badges/grok-bot.svg)](https://www.anchorterminal.com/tools/grok-bot)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/grok-bot\"\u003eGrok Bot on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Grok Bot is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/grok-bot-dark.png\n- Light: https://www.anchorterminal.com/assets/share/grok-bot-light.png\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-12",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Terminal",
        "url": "https://www.anchorterminal.com/tools/"
      },
      {
        "name": "Personal assistants",
        "url": "https://www.anchorterminal.com/categories/personal-assistants"
      },
      {
        "name": "Grok Bot",
        "url": ""
      }
    ],
    "description": "Hosted assistant from SpaceXAI and Cursor. Named Bots work on a persistent cloud computer with a browser, files and terminal, reached from desktop and mobile apps, Slack and X, with routines that run on a schedule.",
    "facts": [
      "rank #893 of 986",
      "OAuth or key auth",
      "0 desk reviews"
    ],
    "h1": "Grok Bot",
    "image": "https://www.anchorterminal.com/assets/og/tools-grok-bot.png",
    "path": "/tools/grok-bot",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Grok Bot review (2026): pricing, alternatives and grade E",
    "toc": null,
    "updated": "2026-10-12",
    "url": "https://www.anchorterminal.com/tools/grok-bot"
  },
  "tokens": {
    "markdown": 10400,
    "slim": 2080
  },
  "version": 1
}
