The best AI assistants in 2026: the ones that actually do things
Twelve AI assistants that act for you, ranked by what they can do on their own and how easy they are to get: Grok Bot, Rakazo, OpenClaw, Hermes Agent, Muse and more.
At a glance
| Assistant | Free plan | Open source | Self-hostable | Trains on your chats by default | ||
|---|---|---|---|---|---|---|
| Grok Bot | No | $30/mo | No | No | No | |
| Rakazo | Yes | $10/mo | Yes | Yes | No | |
| OpenClaw | Yes | – | Yes | Yes | No | |
| Hermes Agent | Yes | $20/mo | Yes | Yes | No | |
| Muse | Yes | $20/mo | No | No | Yes | |
| Poke | Yes | $19/mo | No | No | Yes | |
| Instinct | Yes | – | No | No | Yes | |
| Claude Duet | No | $20/mo | No | No | Unknown | |
| Lindy | Yes | $49.99/mo | No | No | No | |
| Manus | Yes | $20/mo | No | No | Unknown | |
| Perplexity Teammates | No | $200/mo | No | No | Yes | |
| dots | No | $100/mo | No | No | Yes |
Grok Bot is the best AI assistant for most people who want work handed off in November 2026: it does everything an assistant should, has apps on every platform, and needs no setup, though it costs $30 a month. Rakazo does the same jobs with the model you choose and a hosted plan from $15. If you’re technical and want it free on your own hardware, OpenClaw and Hermes Agent are the two open-source picks. If you just want to text an assistant, start with Poke, which is free.
Disclosure: Rakazo is made by the company that runs this site. It’s rated on the same terms as everything else, and its weak spots are listed below.
Why ChatGPT, Claude and Gemini aren’t on this list
A chat app answers when you open it and ask. That’s useful, but it isn’t an assistant in the sense of someone who works for you. A real assistant signs in to your accounts and gets things done, keeps going after you close the window, and tells you when something needs you.
So this list only includes products built to act for you. Where a big AI company has one, we list that product instead of its chatbot: dots is OpenAI’s agent inside ChatGPT, Claude Duet is Anthropic’s, Perplexity Teammates is Perplexity’s, Grok Bot is a separate app from the Grok chatbot, and Muse is separate from Meta AI.
How we ranked
The ranking follows our rating, shown with a one-line reason in the table on this page. It starts from five things an assistant should do, checked against its catalog entry and the sources listed under it. We didn’t run our own benchmark.
- Acts in your accounts: sends email, books, buys or edits on your behalf.
- Works while you’re away: keeps running tasks and routines when your device is off.
- Messages you first: briefs, alerts and follow-ups without being asked.
- Lives in your chat apps: a generally available WhatsApp, Telegram, iMessage, Slack or Discord channel. Betas and waitlists don’t count.
- Runs several bots: separate assistants for separate jobs.
The checklist alone doesn’t decide the rating. We also weigh setup effort (installing, running and securing it yourself counts against), price, and availability (invite-only access, waitlists and region locks count against). Higher-rated assistants come first.
1. Grok Bot: best overall
Grok Bot lets you create named Bots, give each a job, and let them work on a cloud computer with a browser, files and a terminal (Grok Bot). They sign in to your tools, run routines on a schedule or after an event, ask before sensitive actions, and can learn a task from a recorded demonstration. There are native apps for macOS, Windows, Linux, iOS and Android, plus Slack.
It comes first because it does everything on the checklist, needs no setup and the model is included. The catches: no free plan (the cheapest way in is X’s $30 Premium plan), a weekly usage pool shared with Grok and Cursor whose size SpaceXSI doesn’t publish, and all Bots share one computer and one set of logins, so the docs say not to treat separate Bots as a security boundary. It’s still in beta.
Pick it if you want recurring inbox and browser work done and don’t mind $30 a month. See Grok Bot alternatives.

2. Rakazo: best with your own model
Rakazo runs persistent bots, each with its own memory, routines and sandboxed computer, which run on a schedule, a webhook or a GitHub event and ask for approval on the actions you choose (Rakazo). You bring the model: a Claude or ChatGPT subscription, an API key, or local models. It’s open source under Apache-2.0 and free to self-host; the hosted plan starts at $15 a month with a 7-day trial (pricing).
It ranks below Grok Bot because you usually supply and pay for the model yourself unless you buy Rakazo credits, it’s in beta, and Telegram, WhatsApp and iMessage only work when you self-host. Read the Rakazo review for the details.
Pick it if you want several bots with separate computers, or want to choose the model.

3. OpenClaw: best free and open source
OpenClaw is a free, MIT-licensed agent that runs on your own computer and takes instructions from WhatsApp, Telegram, iMessage, Slack, Discord and many more chat apps (OpenClaw). You bring any cloud model or a local one, and state, memory and credentials stay on your hardware.
It does everything on the checklist, but it rates below the hosted picks because you install, run and secure it yourself: it expects comfort with the command line, sandboxing is off by default, and model bills are yours. Testers have reported spending over $100 in a day with expensive models.
Pick it if you’re technical and want full control. See what OpenClaw is and OpenClaw alternatives.

4. Hermes Agent: best for an agent that learns
Hermes Agent, from Nous Research, is free and MIT-licensed, and runs on your computer, a cheap server or serverless infrastructure (GitHub). After complex tasks it writes reusable skills and refines them, and one gateway connects it to Telegram, Discord, Slack, WhatsApp, Signal, email and more. You can run several agents as separate profiles, and it imports settings, memories and skills from OpenClaw.
Like OpenClaw, it does everything on the checklist but you run and secure it yourself. It sits just below OpenClaw because it has no native mobile app and iMessage needs a separate BlueBubbles server on a Mac. An optional Nous Portal subscription from $20 bundles models, hosted tools and one cloud agent (Hermes Agent).
Pick it if you run your own server and want an agent that improves with use.

5. Muse: best free assistant for everyday errands
Muse is Meta’s personal agent: you message it like a person, it works on its own cloud computer, asks before sending email or buying, and pays through one-time card numbers (Meta). It’s free up to an unpublished limit, with paid plans from $20.
It rates well because it’s free and does the work from its own cloud computer with nothing to set up. It misses the chat-app point because WhatsApp access is still in limited testing, and Meta doesn’t say whether you can run several Muses. It’s only in the US, Canada, Japan, Singapore and Mexico, it requires a payment card even on the free tier, and your chats train Meta’s models unless you opt out. See what Muse is and Muse alternatives.

6. Poke: best assistant you just text
Poke has nothing to install: you sign up with your phone number and text it over iMessage, SMS or Telegram (Poke). It connects to Gmail, Outlook, Google Calendar and many other apps, runs shareable automations called recipes, and messages you first. The free plan needs no card, and Pro is $19 (pricing).
It misses only the several-bots point, which Poke doesn’t document. Its privacy notice says your data may train its models unless you choose Maximum Privacy, and it’s now owned by Cognition.
Pick it if you want an assistant in your texts at no cost. See Poke alternatives.

7. Instinct: most hyped, hardest to get
Instinct is an assistant you text or call, which uses a phone and computer to book travel, order groceries and run errands, including in group chats (TechCrunch). It keeps working in the background and follows up with you on its own (Built In), but it’s invite-only, so no chat channel is generally available. Its terms also let it train on your materials unless you opt out. See what Instinct is and Instinct alternatives.
8. Claude Duet: best morning brief, if you get in
Claude Duet is Anthropic’s proactive agent app. Each morning it reviews your email and calendar and sends a brief, checks your accounts every few hours, and asks before sending, paying, signing or deleting anything (Anthropic).
It’s a US-only waitlist preview for paid Claude plans, you can’t reach it through chat apps, and it shares Claude’s usage limits. See what Claude Duet is.
9. Lindy: best for work email and meetings
Lindy triages email, drafts replies, schedules meetings and preps you for calls, and you reach it by iMessage, SMS, Slack, phone or a Gmail extension (Lindy). It sends daily briefs, asks before anything with outside impact, and says it never trains on your data.
It’s one shared assistant per team rather than several, the free credits last seven days, and paid seats start at $49.99 per user a month (pricing).
Pick it if you’re a small team that lives in Slack and email.

10. Manus: best for finished deliverables
Manus plans and carries out a task on its own cloud computer and hands back a research report, website, slide deck or video, and its automations start on a schedule or from an event in Gmail, Slack or Notion (Manus 2.0). It has apps for web, iOS, Android, macOS and Windows, plus Slack and Telegram, and a free plan.
It misses the several-bots point, which Manus doesn’t document. Credits are charged by task complexity, so costs are hard to predict and failed runs still use them, and a training opt-out is listed only for Team plans.
Pick it if you want a concrete result from a prompt. See Manus alternatives.

11. Perplexity Teammates: best for long-running projects
Teammates are persistent agents, each on its own isolated computer, that watch Slack, GitHub, Linear and Gmail, act when something changes, and contact you when they need input (Perplexity). You choose the model per teammate.
It misses the chat-app point because its only listed platform is the web. It’s also a research preview for Perplexity Max at $200 a month, with no published credit cost per task.

12. dots: best if you already pay for ChatGPT Pro
A dot is OpenAI’s always-on agent inside ChatGPT, with its own cloud computer, over 4,000 connected apps, and the same memory in ChatGPT, Slack and Microsoft Teams (OpenAI). When idle, it researches your connected apps and comes back with work to review.
It ranks last on access and cost: it needs ChatGPT Pro from $100 a month or Business Premium, Pro access excludes the EEA, the UK and Switzerland, you get one dot, and Pro content trains OpenAI’s models unless you opt out. See what dots is.

Which one to pick
- Hand off work, no setup: Grok Bot.
- Your own model, or several bots with separate computers: Rakazo.
- Free, on your own hardware: OpenClaw or Hermes Agent.
- Free errands in the US: Muse.
- Just text it: Poke.
- Team inbox and meetings: Lindy.
- A report, site or deck from one prompt: Manus.
- Already on ChatGPT Pro or Claude Pro: dots or Claude Duet.
Whichever you choose, start with tasks where a mistake is cheap and keep approvals on for email and payments. For agents ranked on how much they can do alone, see the best AI agent; for keeping your data on your own machine, the best private AI assistant.
Best picks
$30/mo
Always-on AI agents from SpaceXSI that run on a shared cloud computer, sign in to your apps and finish multi-step work while you're away.
Visit Grok BotStrengths
- Bots work on their own cloud computer, so tasks keep running when your laptop or phone is closed
- Can operate websites and apps that have no API, using saved logins it never sees in plain text
- Several Bots can run in parallel, message each other and share one workspace
- Routines can run on a schedule or after an event, and a Bot can learn a task from a recorded demonstration of up to 10 minutes
- Can place phone calls to US businesses for you and send a summary afterwards
- Native apps for macOS, Windows, Linux, iOS and Android, plus Slack
Weaknesses
- No free plan and no standalone price: the cheapest way in is the $30/month Premium plan
- Usage comes from a weekly pool shared with Grok and Cursor, and SpaceXSI does not publish how much work that pool covers
- No model picker: Grok Bot chooses the model for each task and does not show which one it used
- All Bots on an account share one computer, files and logins; the docs say not to use separate Bots as a security boundary
- Users report Amazon blocks it from shopping as an unauthorized AI agent; Amazon hasn't commented
- Still labelled beta, with no browser version
$10/mo
Open-source, self-hostable platform for persistent AI bots that each get a job, a computer, memory and routines, using the model you choose.
Visit RakazoStrengths
- Open source (Apache-2.0) and fully self-hostable, including with local models
- Choice of model per bot, including existing Claude or ChatGPT subscriptions
- Bots keep working on schedules and triggers with their own cloud computer
- Approval controls over which actions a bot may take on its own
Weaknesses
- Still in beta, with frequent releases
- You supply and pay for the model on the hosted plans, unless you buy Rakazo credits
- Telegram, WhatsApp and iMessage/SMS are only available when self-hosted
- More setup than a single chat app
Free, MIT-licensed personal AI agent that runs on your own computer and takes orders from WhatsApp, Telegram, iMessage, Slack and 20+ other chat apps.
Visit OpenClawStrengths
- Free and MIT licensed, with no paid tier
- Runs on your own hardware; state, memory and credentials stay local, and it sends nothing home except an optional daily version check
- Works in 29 chat channels, including WhatsApp, Telegram, iMessage, Slack, Discord and Microsoft Teams
- Model-agnostic: 64 model and media providers, plus local models
- Large ecosystem of skills and 142 official plugins, and very active development
Weaknesses
- Model costs are on you and can run high: testers and users have reported spending over $100 in a day with expensive models
- Sandboxing is off by default and the agent can run commands on the host unless you turn on approvals
- Setup and upkeep expect comfort with the command line; maintainers warn it is risky for non-technical users
- Broad access to email, messages and the system makes prompt injection and malicious third-party skills a real risk
$20/mo
Free, MIT-licensed AI agent from Nous Research that runs on your own machine or server, learns reusable skills, and chats with you on Telegram, Slack and more.
Visit Hermes AgentStrengths
- Free and MIT licensed, and runs on hardware you control
- Writes and refines its own skills from experience, on top of persistent memory and cross-session search
- One gateway for 20+ chat platforms, including Telegram, Discord, Slack, WhatsApp, Signal and email
- Run several separate agents as profiles, each with its own model, memory and skills, and let them talk in group chats
- Model-agnostic, with a one-command import from OpenClaw
Weaknesses
- Setup expects comfort with the command line and with running your own server
- Model costs are on you unless you use free models, and hosted web search, images and speech need a paid Nous Portal plan or your own keys
- iMessage needs a separate BlueBubbles server on a Mac
- No native mobile app; Android support is a command-line install through Termux
$20/mo
Meta's personal AI agent that sends email, books travel and shops for you from its own cloud computer, in the Muse app or on the web.
Visit MuseStrengths
- Free tier, and no technical setup: you message it like a person in the app or on the web
- Runs on its own cloud computer and keeps working after you close the app
- Asks before sending email or buying, and shows an audit trail of what it did and plans to do
- Purchases go through a one-time card number with Link's purchase protections, so the agent never sees your real card
- Connects to email, calendar and Instagram, and can use a browser for sites without an API
Weaknesses
- Only in the US, Canada, Japan, Singapore and Mexico so far, and Meta says Muse is still in limited testing
- Requires a payment card even for the free tier, and the stronger Muse Wonder model is for paid plans only
- Your interactions train Meta's AI models unless you opt out
- Free usage limit is not published, so it is hard to know when you will hit it
- Early users and press reported it overstepping permissions, such as reading messages it was not meant to
- Requires a Meta account and asks for broad access to email, calendars and payments
$19/mo
A personal AI assistant you text in iMessage or Telegram that connects to your email, calendar and apps and messages you first when something needs attention.
Visit PokeStrengths
- Nothing to install: you sign up with a phone number and text it like a contact
- Messages you first, using your connected services and memory
- Free plan with no credit card, and email and calendar included
- Connects to Gmail, Outlook, Google Calendar, Notion, GitHub, Linear and many more apps, plus custom integrations through MCP
- Shareable automation recipes, and developers can build their own
Weaknesses
- Uses your data to train its AI models unless you choose Maximum Privacy
- WhatsApp support is limited to some markets
- Only one phone number per account
- Does not say which AI models it uses, and does not publish how many credits each plan includes
- Now owned by Cognition, so the product's direction may change
Invite-only personal AI assistant you text or call. It uses a phone and computer for you to book travel, order groceries and handle errands.
Visit InstinctStrengths
- No new interface: you text or call it like a person
- Handles real-world errands end to end, such as travel bookings, groceries and subscription cancellations
- Group chats can use one shared Instinct, even for friends without an account
- Free during the beta
Weaknesses
- Invite-only, with no public sign-up or published pricing
- Terms let it use your materials to train AI models unless you opt out, and the opt-out only applies going forward
- Terms appoint it as your agent to enter agreements and transactions on your behalf, and require binding arbitration with a class action waiver
- Early testers reported it sending an email without asking and keeping inbox data after Google access was revoked
- No choice of model, and the company does not say which models it uses
$20/mo
Anthropic's proactive agent app: briefs you each morning, works on its own cloud computer and asks before acting. US waitlist preview for paid Claude plans.
Visit Claude DuetStrengths
- Messages you first: a morning brief from your email and calendar, then check-ins every few hours
- Works with over 6,000 connectors and plugins, and uses a cloud browser for sites without one
- Brings your existing Claude memory, skills and connectors from the first message
- Asks before sending, paying, signing or deleting, and blocks trading and moving money even with approval
- Pays through one-time card numbers via Link and Shop Pay, and turns larger jobs into editable briefs, decks and dashboards
Weaknesses
- Waitlist-only research preview, US only, and not on Team or Enterprise plans yet
- Uses the same Claude usage limits as chat, and background checks count too
- One model only, Claude Opus 5.5, with no choice of model
- Anthropic's docs say you can't yet watch or take over its browser
- Microsoft 365 isn't available yet, and it can misread threads, misjudge urgency or miss things between check-ins
$49.99/mo
An AI assistant for work that runs your inbox, calendar and meetings, takes requests by iMessage, Slack, phone or browser, and sends you daily briefs.
Visit LindyStrengths
- Texts you first: a personalized first message, alerts on time-sensitive email, and daily briefs
- Reachable almost anywhere: iMessage or SMS, Slack, its own phone number, Gmail via a Chrome extension, and the web
- 1,500+ integrations plus any hosted MCP server, and a browser for tools without one
- Asks for approval before anything with outside impact
- Says it never uses your data to train models, with SOC 2 Type II, GDPR and PIPEDA compliance
Weaknesses
- Expensive for individuals: paid seats start at $49.99 per user a month, and free credits last only 7 days
- Credit-based usage is hard to predict, from 2 credits for a simple ask to 2,500 for a big build
- One shared Lindy per team rather than separate assistants for different jobs
- No mobile app; on phones you use iMessage, SMS or calls
- Plan names differ between its pricing page and its docs, so it is hard to tell what each tier includes
$20/mo
General-purpose AI agent that researches, builds websites, slides, videos and games, and runs automations on its own cloud computer.
Visit ManusStrengths
- Turns one prompt into finished output: research reports, websites, slides, videos and playable games
- Automations can start from a schedule or an event in a connected service such as Gmail, Slack or Notion
- Video Editor and Game Dev let you edit what the agent made instead of regenerating it
- Free plan to try it, with apps for web, iOS, Android, macOS and Windows
Weaknesses
- Credit-based pricing makes costs hard to predict, and long or failed runs can use up credits
- Free daily credits are capped at 1,500 a month and only work in the Lite mode
- A built-in training opt-out is listed only for Team plans
- Several plans share the Pro name and differ only by credit amount
$200/mo
Persistent Perplexity agents, each with its own computer, browser and memory, that own ongoing work and watch Slack, GitHub and Linear. Max-only web preview.
Visit Perplexity TeammatesStrengths
- Run several teammates, each on its own isolated computer and browser with separate sessions
- Watches Slack, GitHub, Linear and other connected tools, acts on changes and reaches out when it needs you
- Pick the model per teammate or task, with Claude Opus 5.5 as the default
- Splits a goal into parallel agent tasks, and teammates in a Project share context and hand work to each other
- You can take over a teammate's desktop and steer it, and it can't view your saved credentials
Weaknesses
- Only on Perplexity Max at $200 a month; Pro and Enterprise plans are excluded by default
- Research preview whose behavior may change
- Web only for now; the iOS app is only promised soon
- Usage draws on credits, and parallel agents, large files and frequent automations use more
- No published cap on teammates and no published credit cost per task
$100/mo
OpenAI's always-on agent inside ChatGPT, with its own cloud computer, that works on your goals between chats and reaches you in ChatGPT, Slack or Teams.
Visit dotsStrengths
- Runs on its own cloud computer and browser and keeps working when your devices are off
- Connects to over 4,000 apps through ChatGPT plugins and can hand work to Codex and ChatGPT Work
- Reachable in ChatGPT, Slack and Microsoft Teams, and you can call it, with one memory across channels
- Researches your connected apps on its own and brings you finished work or decisions to review
- Custom Rules and Auto-review gate sensitive actions, and some steps always stay with you
Weaknesses
- No free, Go or Plus access: it needs ChatGPT Pro from $100 a month or Business Premium
- Pro access excludes the EEA, the UK and Switzerland
- One dot per user for now; teams of dots are only planned
- Texting over iMessage or RCS is a US-only beta, and your dot cannot call you yet
- Stopping a task does not undo actions it already took, and tasks it starts in Codex or ChatGPT Work count toward those limits
Features
| Grok Bot | Rakazo | OpenClaw | Hermes Agent | Muse | Poke | Instinct | Claude Duet | Lindy | Manus | Perplexity Teammates | dots | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Web search | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Image generation | Yes | Yes | Yes | Yes | Yes | Unknown | Unknown | Unknown | Yes | Yes | Yes | Yes |
| Voice mode | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Unknown | Yes |
| File uploads | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Memory | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Takes actions for you | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| App integrations | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Works on its own | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Messages you first | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Runs several bots | Yes | Yes | Yes | Yes | Unknown | Unknown | Unknown | No | No | Unknown | Yes | No |
Sources
Grok Bot
- Grok Bot product page and FAQChecked Nov 8, 2026
- SpaceXSI pricing: The X Subscription plansChecked Nov 8, 2026
- Introducing Grok Bot (launch post, Aug 11, 2026)Checked Nov 8, 2026
- Grok Bot FAQ: plans, platforms, memory, privacy and limitsChecked Nov 8, 2026
- Grok Bot docs: Create and manage BotsChecked Nov 8, 2026
- Grok Bot changelog (v0.78.1, Oct 27, 2026)Checked Nov 8, 2026
- Cursor help: Grok Bot plans and usageChecked Nov 8, 2026
- Teslarati: Grok Bot can now call US businesses (Nov 2026)Checked Nov 8, 2026
- Teslarati: Amazon shuts out Grok Bot (Oct 15, 2026)Checked Nov 8, 2026
- Grok Bot docs: Overview (proactive teammate, morning briefing)Checked Nov 8, 2026
- Grok Bot docs: Chat and collaboration (Slack DMs, X Chat rolling out)Checked Nov 8, 2026
- Grok Bot docs: Get started (desktop and mobile apps)Checked Nov 8, 2026
- Grok Bot docs: Skills, routines and automationsChecked Nov 8, 2026
- SpaceXSI: Team Bots in public beta (Sep 28, 2026)Checked Nov 8, 2026
- Wikipedia: SpaceXAI (xAI renamed SpaceXAI, then SpaceXSI)Checked Nov 8, 2026
- Cursor: Data Use & Privacy Overview (Privacy Mode and training)Checked Nov 8, 2026
Rakazo
- Rakazo homepageChecked Nov 8, 2026
- Rakazo pricingChecked Nov 8, 2026
- Rakazo privacy policyChecked Nov 8, 2026
- Rakazo on GitHub (README and license)Checked Nov 8, 2026
- Rakazo changelogChecked Nov 8, 2026
- Rakazo releasesChecked Nov 8, 2026
- Rakazo docs: Image and video generationChecked Nov 8, 2026
- Rakazo docs: MemoryChecked Nov 8, 2026
- Rakazo docs: Connect appsChecked Nov 8, 2026
- Rakazo docs: RoutinesChecked Nov 8, 2026
- Rakazo docs: Chat appsChecked Nov 8, 2026
- Rakazo docs: Messaging apps (self-hosting)Checked Nov 8, 2026
- Rakazo docs: Bots and chats (add another bot, bot templates)Checked Nov 8, 2026
- Rakazo docs: Groups (several bots in one chat)Checked Nov 8, 2026
- Rakazo docs: Mobile app (notifications)Checked Nov 8, 2026
- Rakazo privacy policy (updated Sep 14, 2026)Checked Nov 8, 2026
- Rakazo privacy policy source on GitHubChecked Nov 8, 2026
OpenClaw
- OpenClaw homepage and Foundation sectionChecked Nov 8, 2026
- OpenClaw integrations: channels, providers and pluginsChecked Nov 8, 2026
- openclaw/openclaw on GitHub (MIT, v2026.11.1)Checked Nov 8, 2026
- OpenClaw docs: Sandboxing (off by default)Checked Nov 8, 2026
- Wikipedia: OpenClawChecked Nov 8, 2026
- Notebookcheck: OpenClaw can burn through hundreds of dollars per dayChecked Nov 8, 2026
- OpenClaw docs: Memory overviewChecked Nov 8, 2026
- OpenClaw docs: AutomationsChecked Nov 8, 2026
- OpenClaw docs: Chat channelsChecked Nov 8, 2026
- OpenClaw docs: iMessageChecked Nov 8, 2026
- OpenClaw docs: Heartbeat, now a default Proactive check jobChecked Nov 8, 2026
- OpenClaw docs: Multi-agent routingChecked Nov 8, 2026
- OpenClaw docs: Platforms (macOS, Windows, Linux, iOS and Android apps)Checked Nov 8, 2026
- OpenClaw docs: Tools (exec, browser, web search)Checked Nov 8, 2026
- OpenClaw docs: Audio and voice notes (inbound transcription)Checked Nov 8, 2026
- OpenClaw docs: Image and media support (inbound media)Checked Nov 8, 2026
Hermes Agent
- NousResearch/hermes-agent on GitHub (MIT, v0.23.0)Checked Nov 8, 2026
- Hermes Agent homepage and Nous Portal pricingChecked Nov 8, 2026
- Hermes Agent documentationChecked Nov 8, 2026
- Hermes Agent docs: Profiles, running multiple agentsChecked Nov 8, 2026
- Hermes Agent docs: Bot ModeChecked Nov 8, 2026
- Hermes Agent docs: Voice modeChecked Nov 8, 2026
- Hermes Agent docs: Vision and image pasteChecked Nov 8, 2026
- Hermes Agent docs: iMessage via BlueBubblesChecked Nov 8, 2026
- Nous Research on X: Meet Hermes Agent (February 25, 2026)Checked Nov 8, 2026
- Hermes Agent docs: Session heartbeats and cron watchdogsChecked Nov 8, 2026
- Hermes Agent docs: FAQ (Is my data sent anywhere?)Checked Nov 8, 2026
Muse
- Meta: Introducing Muse, the world's first personal AI agent built for everyoneChecked Nov 8, 2026
- Muse homepageChecked Nov 8, 2026
- Meta Help Center: About Muse subscriptionsChecked Nov 8, 2026
- Meta Help Center: Meta AI, Muse and Vibes are separate appsChecked Nov 8, 2026
- TechCrunch: Meta debuts its Muse AI agent. Will consumers trust it?Checked Nov 8, 2026
- 9to5Mac: Muse personal agent gets apps for iPhone and MacChecked Nov 8, 2026
- The Guardian TechScape: early Muse users report the agent overstepping permissionsChecked Nov 8, 2026
- iPhone in Canada: Meta's Muse AI agent is now available in CanadaChecked Nov 8, 2026
- Superpower Daily: Meta launches Muse in Japan (Oct 23, 2026)Checked Nov 8, 2026
- Meta: Muse is now available in Singapore (Oct 27, 2026)Checked Nov 8, 2026
- Mexico News Daily: Meta launches its Muse AI agent in Mexico (Nov 6, 2026)Checked Nov 8, 2026
- Meta Q3 2026 earnings call transcript: Muse Wonder in the paid tier, free tier on Muse SparkChecked Nov 8, 2026
- How to manage reminders and scheduled tasks with MuseChecked Nov 8, 2026
- WhatsApp Help Center: About chatting with your Muse agent through WhatsAppChecked Nov 8, 2026
- TechCrunch: Meta's Muse hits MacChecked Nov 8, 2026
- Meta AI: Muse features and FAQ (browses the web, generates images)Checked Nov 8, 2026
- Meta Help Center: How your Muse agent browses the webChecked Nov 8, 2026
- Meta Help Center: How to use Muse with artifacts (uploads, image generation)Checked Nov 8, 2026
- Meta Help Center: How to get started with MuseChecked Nov 8, 2026
Poke
- Poke homepageChecked Nov 8, 2026
- Poke pricingChecked Nov 8, 2026
- Poke FAQChecked Nov 8, 2026
- Poke privacy notice (last updated September 11, 2026)Checked Nov 8, 2026
- Cognition: welcoming The Interaction Company to Cognition (July 23, 2026)Checked Nov 8, 2026
- TechCrunch: Poke makes using AI agents as easy as sending a textChecked Nov 8, 2026
- TechCrunch: Apple approves Poke as the first AI agent on its Messages for Business platformChecked Nov 8, 2026
- Introducing Poke.com (launch announcement, September 8, 2025)Checked Nov 8, 2026
- Poke docs: Welcome (built-in web search)Checked Nov 8, 2026
- Poke release notes (web search, sharing images, attachments)Checked Nov 8, 2026
Instinct
- Instinct homepageChecked Nov 8, 2026
- Instinct Terms of Service (last revised Aug 26, 2026)Checked Nov 8, 2026
- TechCrunch: Instinct brings its AI agent to group chatsChecked Nov 8, 2026
- Fortune: Noah Shinn's viral AI assistant Instinct raises $1B Series CChecked Nov 8, 2026
- Vellum: Instinct breakdown (competitor; summary of early tester reports)Checked Nov 8, 2026
- Digit: Instinct clarifies WhatsApp outage (works through WhatsApp and iMessage)Checked Nov 8, 2026
- RuntimeWire: Instinct brings its group AI agent to iMessage for all users (Oct 29, 2026)Checked Nov 8, 2026
- Privacy Policy | InstinctChecked Nov 8, 2026
- Built In: What Is Instinct AI? (Oct 21, 2026)Checked Nov 8, 2026
Claude Duet
- Anthropic: Introducing Claude Duet (October 21, 2026)Checked Nov 8, 2026
- Claude Help Center: Get started with Claude DuetChecked Nov 8, 2026
- Claude Duet product pageChecked Nov 8, 2026
- Claude pricing: Pro, Max and UltraChecked Nov 8, 2026
- Inc.: I Tried Claude Duet (reviewer sent it a screenshot)Checked Nov 8, 2026
Lindy
- Lindy homepageChecked Nov 8, 2026
- Lindy pricingChecked Nov 8, 2026
- Lindy docs: What is Lindy?Checked Nov 8, 2026
- Lindy docs: iMessage & SMSChecked Nov 8, 2026
- Lindy docs: Phone CallsChecked Nov 8, 2026
- Lindy docs: Ad Hoc Tasks (research)Checked Nov 8, 2026
- Lindy docs: Pricing and creditsChecked Nov 8, 2026
- Lindy Assistant: The AI that runs your work lifeChecked Nov 8, 2026
- Lindy docs: Set up Lindy (web search, image generation)Checked Nov 8, 2026
- Lindy docs: Files (drop files and folders in for Lindy to use)Checked Nov 8, 2026
- Lindy changelog (Creatives: on-brand images, Sep 16, 2026)Checked Nov 8, 2026
Manus
- Manus Plans & PricingChecked Nov 8, 2026
- Manus Help Center: What is the current membership pricing for Manus?Checked Nov 8, 2026
- Manus Help Center: rules for credit consumptionChecked Nov 8, 2026
- Introducing Manus 2.0 (Sep 28, 2026)Checked Nov 8, 2026
- Download Manus: macOS, Windows, iOS and AndroidChecked Nov 8, 2026
- Tech Xplore/AFP: Manus raises $500 million after Meta acquisition blocked by ChinaChecked Nov 8, 2026
- Wikipedia: Manus (AI agent)Checked Nov 8, 2026
- Manus for Slack: Turn Your Workspace into an Autonomous EngineChecked Nov 8, 2026
- Manus docs: AutomationsChecked Nov 8, 2026
- Is my data safe when using Manus Agents in Telegram?Checked Nov 8, 2026
- Chatting with Manus Agent on Slack: Channels, DMs, and File DeliveryChecked Nov 8, 2026
- Manus Agents in Telegram (available to all users)Checked Nov 8, 2026
- Manus Help Center: What's new in Manus 2.0 (Cue requires an invitation code)Checked Nov 8, 2026
- Manus API docs: Agents (default agent plus agents you create)Checked Nov 8, 2026
- Manus privacy policy (updated Sep 28, 2026)Checked Nov 8, 2026
Perplexity Teammates
- Perplexity blog: Teammates are agents for complex, ongoing work (November 4, 2026)Checked Nov 8, 2026
- Perplexity Help Center: Perplexity TeammatesChecked Nov 8, 2026
- Perplexity Help Center: Perplexity Max ($200 a month)Checked Nov 8, 2026
- Perplexity Help Center: Data Collection at PerplexityChecked Nov 8, 2026
- Perplexity Help Center: Generating Images with PerplexityChecked Nov 8, 2026
dots
- ChatGPT: Dots feature pageChecked Nov 8, 2026
- ChatGPT docs: Meet dotsChecked Nov 8, 2026
- ChatGPT docs: Dot channels (Slack, Teams, calls, texting beta)Checked Nov 8, 2026
- ChatGPT pricing: Dots on Pro only; training opt-outChecked Nov 8, 2026
- TechCrunch: OpenAI launches dots, its bubbly agentic avatarChecked Nov 8, 2026
- DataCamp: OpenAI Dots, always-on agents in ChatGPT, explainedChecked Nov 8, 2026
- eesel: OpenAI Dots pricing by Pro tier and limitsChecked Nov 8, 2026
- ChatGPT docs: Dot computers and apps (cloud browser for research)Checked Nov 8, 2026
- OpenAI Help Center: Images in ChatGPT (image generation on all tiers)Checked Nov 8, 2026











