AI agents that make phone calls for you

Some of these place or receive phone calls rather than only exchanging text. Voice is the most consequential thing one of these products does on your behalf, because a call cannot be unsent and the person on the other end usually does not know they are talking to software.

Agents compared by channel, how you start using them and pricing. Status is shown only where it is not live.

ArloReads your work tools and asks approval before anything consequential goes outText it, opens with hey Arlo+1 407 234 1884	iMessageSMS	Text a number	Free to start
BoardyA voice AI that phones you, learns what you need, and makes introductions	Voice	Phone call	Not published
CatchEmail, scheduling, travel and outbound phone calls, proactive by default	SMSSlackEmailVoice	Create an account	From $99/mo
DuckbillThe model plans, background-checked humans execute	SMSEmailWeb	Create an account	From $40/mo
folkA personal AI with an isolated cloud computer and a persistent memory graph	iMessageTelegramWhatsAppDiscordVoice	Tap one link	Free to start
HomerTexts you back on iMessage or SMS, and will phone a business for youText it, opens with Hey Homer+1 415 583 6966	iMessageSMS	Text a number	Free to start
InstinctA general agent that acts before asking, and is criticised for exactly that	iMessageVoice	Invite only	Not published
LindyA work assistant you reach in Slack, iMessage or Gmail, built on the web first	SlackiMessageSMSWeb	Create an account	From $29.99/mo
MartinCharges for proactivity rather than capacity, at $35 or $49 a month	iMessageSMS	Create an account	From $21/mo
PersonaActs in your name over iMessage or SMS, with a wearable band, SOC 2 Type I, and terms that say what it may do	iMessageSMS	Create an account	Not published
sznBetaAn assistant in iMessage with its own name, number and email address, from a former Siri engineer	iMessage	Waitlist	Free to start
TabBetaAn agent you text that browses, calls, waits on hold and pays with your approval, and says where the secrets live	iMessageSMS	Waitlist	Not published
TomoCoaching and accountability that charges for the unprompted check-in	iMessageSMSWebVoice	Text a number	Not published
VellumAn agent with its own identity and filesystem, across text, desktop and voice	TelegramSlackEmailVoiceWeb	Create an account	Free to start
WajoA group agent that places its own calls and pays with its own card	iMessageSMSVoiceEmail	Invite only	Free to start
Wis.aiBetaAn assistant on WhatsApp and Telegram with its own computer, number, voice and email, in a private beta with no price	WhatsAppTelegramVoiceEmail	Invite only	Not published

What the claim actually covers

Places calls to businesses on your behalf
Answers or screens calls coming to you

The approaches split three ways. Boardy is voice-first: it phones you, learns what you are looking for, and makes introductions, which is the only product here where the call is the product rather than a feature. Wajo's agent calls businesses from its own number and pays with its own card. Duckbill routes the call to a human.

Several assistants add outbound calling to an otherwise text-based product, usually for the errands people least want to do: chasing a refund, sitting in a hold queue, booking a table that has no online option.

Worth checking before you enable it: whether the agent identifies itself as software, whether calls are recorded, and in which jurisdictions that recording is lawful. Of the 17 listings that call or can be called, 2 say on their own pages that the agent tells the person it is software, and 4 say whether the call is recorded; the rest say nothing, and each listing's table says which.

What these connect to

Named by the agents that state this capability. An agent that names none is not necessarily unconnected, it may simply not say.

Service

Gmail11
Google Calendar11
Slack6
Notion5
Google Docs4
Google Drive4
GitHub3
Google Meet3

What people have posted about these

Crockett Ford, sunbeam Research
Our research · 2026-10-15
“Unlike ChatGPT, Claude, or Meta, Instinct doesn't send its own user agent or signature.”
Instinct Read it
Nothing Instinct publishes names a search or browser provider, and this is the first outside account of what its traffic looks like to the site on the other end. The consequence sunbeam draws is the one that matters to anyone running a site: Instinct's visits cannot be told apart, so they cannot be counted, allowed or blocked as Instinct's. The method is reproducible, links a site controls and timing it knows, and sunbeam sells search optimisation, which is why it is looking.
Kush Thakker and Tharun Anandh, Brace
Our research · 2026-10-01
“Out of the 456 people who asked for Instinct, only 31 posted about using it in the days that followed.”
Instinct Read it
It is the only measurement anyone has published of the hype itself rather than of the product, and it cuts against the account Instinct's founder gives of his own invite system: a compute shortage, not a demand tactic. It measures attention, not use, and says so: it cannot see who got an invite or who used it without posting. The claims about who knew whom and which posts were paid are Brace's, from its own capture, and are not checked here.
anu
@anuatluru · 2026-09-28
A few thoughts on Instinct (been waiting for consumer AI): - Simplicity is clearly the north star (a prestige product philosophy, Apple-esque) - This is the new interface for commerce, and likely where all their money gets made. - Invite-only consumer growth naturally draws Clubhouse comparisons. It’s a good proxy for the Silicon Valley story arc, but far more solo utility and less social/media network - We’re still deep in unlocking personal superpowers via AI, long phase of tool before network (fits my “Self is the Platform” AI thesis from last yr) - And yet, this could be the first multiplayer consumer AI product to truly scale. ‘Trusted Person Network’ is a great use case and starts with family & close friends, like Life360 (what I’ve called Social Utilities). - Meta is coming, OpenAI will too … and new devices will enter the mix, but hardware is hard and it’ll be hard to beat iPhones anytime soon - Instinct will try to stay free, personality-agnostic, and low gooner / gambling index, which is good for a very mass utility play (also fits the prestige philosophy) - High EQ founder, a good signal for adapting to users, competing, fundraising, and media interviews … - Paradigm novelty is underrated for hiring. Many people want to work on the original new thing more than on copycats, so hiring shouldn’t be hard even at steep valuations, now $10B . - The first tweet from Noah that caught my eye was when he said there are no new interfaces. I 95% agree with that, and have been bullish since …
Instinct195 likes · 15k viewsRead it
It is the clearest outside statement of the shape this category is betting on: a long stretch where an agent is a tool for one person, with the network arriving later if at all. This directory can check part of that. {{talksToOtherAgents}} of {{total}} listings state that one person's agent can talk to another person's, which is the whole multiplayer claim, and it has been three for weeks. Nothing here is a fact about the product, and none of it moves a row.
Wajo
Our research · 2026-09-26
Wajo published a benchmark on 26 September 2026 measuring personal assistants on two axes it defines: finishing an errand that goes wrong, and doing it without overstepping the user. It scores its own agent Fo against base models and two products listed in this directory, OpenClaw and Hermes, and Fo comes first on both axes and lowest on error rate. The method is the part worth reading: a simulated world of businesses with invented names, built so that no run could reach a real person. A paper is on arXiv and the company says it will open source the evaluation world, the tasks and the graders.
WajoThe companyRead it
It is the first time a product in this directory has published a benchmark scoring named competitors that are also listed here. The axes are a genuine contribution, because finishing a task that goes wrong and not overstepping while doing it are the two things this market has no shared measure for. The scores are a different matter and none of them is recorded as a field on any listing, here or on the two it ranks. A number from a scoreboard its own author competes on cannot be re-run or dated by this site, which is the standing rule and this is the clearest case of it yet. The simulated world is the detail that survives independent of who ran it: a benchmark for agents that place calls, built so it never calls anybody.

Everything people have got these agents to do · The argument in public

Building one instead? The infrastructure side is a separate half of this site: every provider that carries these messages, what they charge, and what the headline price leaves out. The guides cover getting an agent into iMessage, WhatsApp and SMS.