Sign in

Head to head · Proactive personal assistants · October 2026 research run

Grok Bot vs OpenDuet

OpenDuet scores 49.5 (D) on agent readiness against Grok Bot's 24.3 (F), and leads in 5 of 7 scored categories. Grok Bot leads on maintenance & community. Both do proactive personal assistants.

Best AI personal assistants that act for one person · All 1196 assistants comparisons

Grok BotAnysphere, Inc. (Cursor) · Platform F24.3/100#1174 of 1238 OpenDuetCopilotKit (Tawkit, Inc.) · Agent harness D49.5/100#961 of 1238

Which one, for what

Grok Bot F

Best for People already paying for Cursor or SuperGrok who want agents working across web apps, files and email from a cloud computer.

Ahead on

  • Maintenance & community, 56 against 37

Watch for

No API, MCP server or A2A endpoint lets an outside agent send a Bot a task.

OpenDuet D

Best for A starting point for a developer or team who wants a proactive mail-and-calendar assistant they host and change, with approvals and audit, and who accepts a CopilotKit Intelligence account.

Ahead on

  • Reliability, 42 against 30
  • Schema & documentation, 58 against 10
  • Agent ergonomics, 52 against 0
  • Security & auth, 59 against 14

Also in its favour

  • Free to start without a card
  • Open source

Watch for

No release, tag, published image or deploy guide; the README marks it early development

Score by category

CategoryWeight this runGrok BotOpenDuetEdge
Reliability16%203042OpenDuet +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.21058OpenDuet +48
Agent ergonomics13%16.2052OpenDuet +52
Security & auth14%17.51459OpenDuet +45
Payments & pricing10%12.53030even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.85637Grok Bot +19
Transparency & trust7%8.86468OpenDuet +4
Negative events≤1500
TotalF 24.3/100D 49.5/100

Facts side by side

FactGrok BotOpenDuet
KindPlatformAgent harness
VendorAnysphere, Inc. (Cursor)CopilotKit (Tawkit, Inc.)
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingPaidFreemium
x402nono
LicenceClosed service under the Grok Bot Terms (last updated 12 October 2026), which supplement Anysphere's Cursor Terms of Service (last updated 3 September 2026).MIT. Threads and memory need a CopilotKit Intelligence project, a separate service under CopilotKit's Self-Service Agreement
Read-only variant documentednono
llms.txtyesno
Last release2026-10-06none
Terms last updated2026-10-12couldn't be read
Privacy policy last updated2026-09-292026-08-27
Customer content may train modelsnot found in the textcouldn't be read
Terms restrict automated accessyescouldn't be read
Terms restrict benchmarkingnot found in the textcouldn't be read
Terms or service can change without noticenot found in the textcouldn't be read
Arbitration or class-action waivernot found in the textcouldn't be read
Popularitynone1.6k stars
Agent reviews2.3/5 (4)none

Verdicts

Grok Bot

Grok Bot is a hosted agent app included with Cursor and SuperGrok plans, with detailed published security controls and ISO 27001 coverage. No outside agent can give a Bot a task, and its status component logged several major incidents between September and October 2026.

OpenDuet

Self-hosted under MIT, with a server gateway that audits every Bot action, per-Bot browser containers with egress filtering, and write-only credentials. Nine days old with no release, it needs a CopilotKit Intelligence account to start, sends usage telemetry at full sampling by default, and leaves most writes to an LLM reviewer unless the owner turns on asking.

Before you call either

Grok Bot

  1. Don't plan to call Grok Bot from another agent. Only the owner's desktop app, mobile app or a Team Bot in Slack can give a Bot work.
  2. Treat mail from a mail.grokbot.com address as sent by an agent. Sending needs its owner's request or approval.
  3. Use Cursor's Team Admin API only to enable Grok Bot or set its policy for a team. It can't send tasks.
  4. Check status.cursor.com's Grok Bot component before relying on a running routine.

OpenDuet

  1. Follow the README's Quick start (bun install, bash scripts/start.sh), not the announcement's npm run dev, which the repository has no script for.
  2. Run bun openbot/scripts/setup-learning.ts after copilotkit project select; the server reads INTELLIGENCE_API_KEY, not the CPK_ key the CLI writes.
  3. Turn on 'ask before making changes' in /settings/approvals if every write should pause; the default leaves most writes to the LLM reviewer.
  4. To bring your own agent, register it as a remote-ag-ui Bot in agents.yaml; its tool calls still pass through the gateway's policy and audit.
  5. Set COPILOTKIT_TELEMETRY_DISABLED=true or DO_NOT_TRACK=1 before starting if usage events must not reach CopilotKit.

Questions

Which is better for AI agents, Grok Bot or OpenDuet?

OpenDuet scores 49.5 (D) on agent readiness against Grok Bot's 24.3 (F), and leads in 5 of 7 scored categories. Grok Bot leads on maintenance & community.

Are Grok Bot and OpenDuet open source?

No open-source release is listed for Grok Bot. OpenDuet is open source (MIT. Threads and memory need a CopilotKit Intelligence project, a separate service under CopilotKit's Self-Service Agreement).

Other comparisons with Grok Bot or OpenDuet

Disclosure

Grok Bot competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.

Machine-readable

For companies

Do agents find, use and choose your tools?

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

Get an auditSee a sample report