Claude Duet on Liam Ding https://www.liamding.com/en/tags/claude-duet/ Recent content in Claude Duet on Liam Ding Liam Ding https://www.liamding.com/img/og-cover.png https://www.liamding.com/img/og-cover.png Hugo -- 0.147.7 en Sun, 25 Oct 2026 00:00:00 +0800 Personal AI agents compared: Claude Duet vs Dot vs Gemini Spark vs Grok Bot vs Muse (October 2026) https://www.liamding.com/en/posts/2026-10-25-personal-agent-comparison/ Sun, 25 Oct 2026 00:00:00 +0800 https://www.liamding.com/en/posts/2026-10-25-personal-agent-comparison/ Eight personal AI agents in one table, including Claude Duet, Dot, Gemini Spark, Grok Bot, Muse, Hermes Agent and OpenClaw: access, pricing, regions, best fit. A personal AI agent is an AI that gets things done for you across websites, apps and accounts. It has its own cloud computer or connectors, so it can send email, fill in forms and place orders instead of only answering questions. This page puts eight of them in one table: the hosted Claude Duet, Dot, Gemini Spark, Grok Bot, Instinct and Muse, and the open-source, self-hosted Hermes Agent and OpenClaw. Every cell links to an official page. Anything the vendor doesn’t publish says “Not disclosed”, and anything I haven’t tested myself says “Not tested”. In the “Best for” column, I quote the vendor where it names a target user; otherwise it is my own judgment.

These eight personal agents are really two businesses: productivity agents help you create more value and are judged on ROI, while secretary agents give you back time by handling everyday errands. I use Grok Bot because it lets several named bots split the work like teammates; if you want a secretary for daily life, start with Muse or Instinct; and if you want to choose your own model and machine, pick the open-source Hermes Agent or OpenClaw.

This comparison is part of my personal AI agents guide.

The eight personal agents in one table

Last verified: 2026-10-25. Numbers in brackets link to sources and match the numbered “Sources” list at the end.

Hosted by the vendor

Product Company Access Apps and tools it connects to Price and usage Availability by country Payments and passwords Best for Last verified
Claude Duet Anthropic 1 Standalone iOS/Android app and claude.ai 2 6,000+ connectors and plugins in the Claude Marketplace, e.g. Gmail, Slack, QuickBooks, Stripe, HubSpot, Shopify; Microsoft 365 not yet supported 1 Included in Claude Pro/Max at no extra cost, sharing the plan’s usage 1; Pro $20/month, Max from $100/month 3 Research preview with a waitlist; US Pro/Max subscribers only, not Team/Enterprise 1 Link one-time virtual cards and Shop Pay; 1Password coming soon; passwords go into a separate form Duet can’t see; asks before sending, paying, signing or deleting 1 Officially for professionals and small business owners; Anthropic says personal errands like booking tickets are weaker 1 2026-10-25
Dot (written dot / dots by OpenAI) OpenAI 4 ChatGPT iOS/Android app, desktop app (including Windows) and desktop web, not mobile web 5; also in Slack and Teams 4; texting is a limited beta for US Pro 5 4,000+ apps through plugins; optional access to your local computer 4 First dot included in ChatGPT Pro and Business Premium; Enterprise and others in beta, off by default 5; Pro price: Not disclosed (the pricing page lists “3 usage tiers”) 6 Pro users must be 18+; not available in the EEA, Switzerland or the UK 5 Custom rules for sharing, purchases and access 4; signs in with saved passwords without exposing them to the model 4; steps such as changing a password must be done by you 5 People already on ChatGPT Pro who want an always-on agent inside ChatGPT (my judgment) 2026-10-25
Gemini Spark (Google’s help page says it is now called Task) Google 7 Gemini mobile app, Mac app and gemini.google.com 8 Gmail, Calendar, Drive, Docs, Sheets, Slides, Keep, Tasks, Maps, YouTube and other Google services; third-party and custom MCP apps such as Canva, OpenTable, Instacart 7 Requires Google AI Pro or Ultra 8; US prices: Ultra from $99.99/month ($199.99 for the 20x tier) 10; Pro price: not shown on the plans page 18+ with a personal account; available wherever Gemini Apps are, except the EEA, Nigeria, Switzerland and the UK 8 Can sign in with Google Password Manager with your permission; you take control to enter passwords and payment details; confirms before purchases and sending 8 People whose work and life already run on Google apps (my judgment) 2026-10-25
Grok Bot xAI, hosted by Cursor 11 Desktop apps for macOS, Windows and Linux; iOS and Android 13; several named bots that can join group chats 11 Connectors such as Gmail, Google Calendar, Drive, Sheets, Slack, Notion, X and 1Password 15; sites without a connector are handled with a cloud computer and browser; each account gets one persistent cloud computer that all its bots share, each with its own screen 1114; total connector count: Not disclosed The X Subscription: Premium $30/month, Super $100/month and Ultra $200/month include Grok Bot, Plus $8/month does not; usage comes from a shared weekly pool 12. Also included with paid individual Cursor plans and Cursor Teams, or via a SuperGrok link 13 Country restrictions: Not disclosed; the computers run in the United States today 14 Pays with X Money, Stripe Link and Shop Pay, showing the amount for you to allow or deny first 16; 1Password fills logins without the bot seeing them 15; login, two-factor and payment steps are handed to you 14 Official positioning: several named bots working in parallel and splitting work in group chats 11 2026-10-25
Instinct Spear Street Technology, Inc. d/b/a Instinct 18 Text or call it 17; the terms mention Mac OS and mobile apps 18 Not disclosed (the site only gives examples such as groceries, train tickets and flowers 17) Not disclosed (the terms mention paid services in USD but list no prices 18) Not disclosed Can make purchases for you; the terms say Instinct itself does not process payment; has a Vault feature 18 People who want errands done just by texting or calling (my judgment) 2026-10-25
Muse Meta 19 Muse app, WhatsApp, muse.ai 19 Not disclosed (the launch post only covers Link checkout and Shop Pay and 1Password coming soon, with no full integration list 19) Free with a usage limit; Power $20/month (500M tokens/week); Maximum $100/month (3B tokens/week) 20 Rolling out in the US first on iOS, Android and muse.ai 19; 18+; limited testing, not available in all locations 20 Link one-time virtual cards; Shop Pay and 1Password coming soon; Muse can’t see your passwords or payment methods 19 People who want help managing their goals, ideas and daily life (my judgment) 2026-10-25

Open source, self-hosted

Product Company Access Apps and tools it connects to Price and usage Availability by country Payments and passwords Best for Last verified
Hermes Agent Nous Research 21 Desktop apps for macOS, Windows and Linux; Telegram, Discord, Slack, WhatsApp, Signal, Email, CLI 21 Persistent memory, skills, scheduling, subagents, browsing; your own model provider or Nous Portal 21 MIT, free 21; optional Hermes Cloud with a $2 minimum credit or a subscription, billed daily by usage 22 Self-hosted, no stated country restrictions; Hermes Cloud has 14 server locations 22 Not disclosed People who want to choose their own model and machine (self-hosting and model choice are the site’s pitch 21) 2026-10-25
OpenClaw OpenClaw Foundation (US 501(c)(3)) 23 macOS, Windows, Linux; 29 chat channels including WhatsApp, Telegram, Discord, Slack, Signal, iMessage 23 Bring your own models (Claude, GPT and others); scheduled and background tasks; skills and plugins such as Gmail, GitHub, Obsidian 23 MIT, free; “No subscription. No hosted tier.”; model costs are separate 23 Fully self-hosted, no stated country restrictions 23 Not disclosed People who want to self-host everything 23 2026-10-25

Note: OpenClaw is stewarded by the independent OpenClaw Foundation, whose donors include OpenAI, Amazon and Red Hat 23; the foundation’s site says no single company controls OpenClaw 24.

Candidate for the next update: Cue. Its site says each agent has its own phone, email, wallet and computer, and lists no pricing or regions 25.

How I choose: five criteria

In productivity vs secretary agents I argued that personal agents make two different promises 26. In practice I look at five things:

  1. How much context it gets. Can it read your email, calendar, files and chats? The more it sees, the less you have to explain.
  2. How many apps it connects to. Connectors decide what it can do reliably, and a built-in browser covers what connectors don’t.
  3. Whether it can actually order and pay. That is the “Payments and passwords” column: a one-time virtual card or your real card, and whether it asks before paying.
  4. Who is responsible when it goes wrong. Does it stop before sending, paying or deleting, and does it hand logins and verification codes back to you?
  5. Price. Productivity agents are judged on ROI; secretary agents on what the saved time is worth.

I’m leaving Claude Duet, Dot and Gemini Spark unclassified for now. For reference, the official positioning: Claude Duet is for professionals and small business owners 1; Dot sits in ChatGPT Pro, Business Premium, Slack and Teams 5; Gemini Spark works across Google’s own apps 7.

For how access and interaction differ, see entry points and interaction for personal agents.

Recommendations by use case

Shopping and errands

The agents that can pay use one-time virtual cards or third-party payments: Claude Duet and Muse use Link 1, and Grok Bot supports X Money, Stripe Link and Shop Pay 16. Instinct works over text and phone calls, and every example on its site is an errand like groceries or tickets 17. Which one works best: Not tested.

Work and information

Claude Duet is officially aimed at professionals and small business owners 1; Dot works inside Slack and Teams 5; Gemini Spark is tied into Google Docs, Sheets and Gmail 8; Grok Bot can run several bots in parallel and bring them into one group chat 11.

Privacy first

If you want to keep the data and the model under your control, look at the open-source Hermes Agent and OpenClaw. Both are MIT-licensed, run on your own machine and let you pick the model 21. Among the hosted products, Claude Duet, Dot, Grok Bot and Muse state that the agent doesn’t see your passwords 215.

Security: how agents handle your passwords and cards

The hosted products take broadly similar approaches:

  • The model doesn’t see passwords. Claude Duet has you type them into a separate form 2; Dot uses saved passwords without exposing them to the model 4; Grok Bot fills logins through 1Password without seeing the values 15; Muse can’t see your passwords or payment methods 19; Gemini has you take control to enter passwords 8.
  • Payments use one-time cards or need your approval. Claude Duet and Muse use Link one-time virtual cards 1; Grok Bot shows the amount for you to allow or deny 16; Gemini confirms before purchases 8.
  • Risky actions stop and ask. Claude Duet asks before sending, paying, signing or deleting, and trading securities or moving money are off-limits 1.

Hermes Agent and OpenClaw don’t say how they handle payments or passwords: Not disclosed. Self-hosting means designing that part yourself.

FAQ

Which personal AI agent should I use?

Start from what you want it to do, then use the five criteria above. My own short answer is the opening paragraph of this page. Before you pick, check the availability column: most hosted agents launched in the US first, and several exclude the EEA, Switzerland or the UK.

What’s the difference between Muse, Grok Bot, Dot, Claude Duet and Gemini Spark?

Where they live: Muse in the Muse app and WhatsApp, Dot in ChatGPT, Slack and Teams, Claude Duet in the Claude app, Gemini Spark in the Gemini app, and Grok Bot in its own desktop and mobile apps. Pricing: Muse has a free tier; Claude Duet, Dot and Gemini Spark come with each company’s paid plans; Grok Bot comes with The X Subscription Premium and above or paid Cursor plans. Details are in the table.

Who are the open-source Hermes Agent and OpenClaw for?

People who want to decide which model to use and which machine it runs on. Both are MIT-licensed and free, with model costs separate 21. Hermes offers optional hosting through Hermes Cloud 22; OpenClaw explicitly has no hosted tier 23.

What’s the difference between a personal agent and ChatGPT?

A chat assistant like ChatGPT mainly answers questions. A personal agent acts for you: it signs in to websites, fills in forms, places orders and sends email. Most hosted products in the table give the agent a cloud computer or virtual machine 111.

What’s the difference between a personal agent and a coding agent?

A coding agent writes code in a repository and terminal. A personal agent works in your inbox, calendar, shopping sites and chat apps. The underlying capability is similar; the tools and permissions are different.

How much does a personal AI agent cost?

From free to $200 a month. Muse has a free tier and Power at $20/month 20; Claude Duet comes with Pro ($20/month) and Max 1; Gemini Spark needs Google AI Pro or Ultra (Ultra from $99.99/month in the US) 8; Grok Bot starts at The X Subscription Premium, $30/month 12; Hermes Agent and OpenClaw are free software with separate model costs 21. Dot needs ChatGPT Pro, whose price isn’t shown on the pricing page 6; Instinct: Not disclosed.

Is it safe to give an AI agent my passwords?

It depends on how the agent handles them. The security section above lists each vendor’s stated approach: the model never sees the password, payments use one-time cards, and key actions need your approval. With open-source agents you set up those protections yourself.

Update log

  • 2026-10-25: First published with eight products; data verified on 2026-10-25.

Disclosure

I use Grok Bot myself and have said publicly, “I pick Grok Bot” 27. I work at NVIDIA. This comparison is my own research and opinion, not my employer’s.

This post is part of my personal AI agents guide.

]]>