Text-message AI agents are turning chats into task lists

A growing group of AI agents can now be reached through text messages instead of requiring a separate app. They can help with calendars, reminders, travel, email, reservations, shopping, family coordination and work tasks, with options ranging from Instinct and Folk to Fambot, Ollie, Wajo and Town.

WTF Index TERMINATOR
◄ Terminator 2 Idiocracy 1 ►

Text-based agents gaining context, app access and multi-step task execution mildly increases AI autonomy, though the story is mostly a productivity trend.

Text-message AI agents are turning chats into task lists

AI agents are moving into one of the most familiar interfaces people already use every day: text messages. Instead of asking users to install another app, many of these assistants can be reached through iMessage, SMS, WhatsApp, Telegram, RCS or other messaging channels.

The idea is simple. A user sends a request, and the agent can remember context, connect to apps and services, and complete tasks on the user’s behalf. That can include scheduling an appointment, organizing a calendar, researching a trip, sending an email, making a reservation, shopping online or sending a reminder days later.

Why text messages are becoming the interface

The products in this category are not all doing the same job, but they share a common direction. They are trying to turn scattered information into action without forcing users to manage another inbox.

Caddy, for example, lives in iMessage for iPhone users and RCS for Android users. It connects to calendars and conversations, then identifies details that may require action. If an email contains an appointment or a friend sends a shopping list, Caddy can help turn those loose details into calendar events, reminders, follow-ups or research tasks. It has been available in public beta since April 2026.

Folk is also built around messaging access, with support for iMessage, WhatsApp and Telegram. It can remember personal context, manage reminders, research topics, track flights, handle email and perform real-world tasks such as restaurant reservations. Folk also runs on its own private cloud computer, can run code and can execute multi-step tasks. Its beta launched in May 2026, and it offers a free version plus a Pro subscription for $8.33/month for unlimited background tasks.

Rene takes a similar text-first approach. It is available on iMessage, Telegram and WhatsApp, and is designed as a user’s “best contact” rather than another productivity agent. It can turn natural-language conversations into tasks, reminders, summaries and follow-up actions, while keeping context across conversations. It also has a browser, can write code, shop for users, and create slides and images.

Instinct shows the scale of the market

Instinct is one of the most visible companies in the category. It first drew attention after raising $350 million at a $2.5 billion valuation. In September 2026, it raised $1 billion, valuing it at $10 billion.

The assistant is designed to be always available and able to take action rather than only answer questions. Users can communicate with Instinct by text or voice and connect it to apps and services they already use, including email, calendar and Google Workspace. The company says early users have used Instinct for planning trips, buying groceries, booking tickets and cancelling subscriptions.

In September, Instinct began giving users dedicated email addresses for their assistants. That allows the agent to create and manage accounts on a user’s behalf without filling the user’s personal inbox. The assistant can use its address to sign up for services, contact businesses, follow up on requests and handle tasks that require an email account. This level of autonomy has also raised concerns about privacy and security. Instinct has also begun rolling out support for placing calls, and the company remains in private beta.

Family assistants focus on daily coordination

Several text-based AI agents are aimed specifically at households. Their shared bet is that family logistics are often spread across school messages, calendars, task lists, group chats, emails and verbal reminders.

Fambot describes itself as an AI-powered “chief of staff” for families. It brings together school communications, sports activities, meal planning, calendars and other daily responsibilities into an organized plan. Families can use it across an app and text messages, and it is available on iOS devices, Android devices and the web. Every night, Fambot automatically sends a summary of the following day, including events, to-dos and details such as school uniform or packing requirements.

Fambot currently connects to Gmail and Google Calendar, with Outlook and Apple Calendar support planned for the future. It launched in beta in early September 2026, has raised $3.5 million in pre-seed funding and is free during the beta period. The company expects to eventually charge roughly the equivalent of a Netflix subscription.

Ohai is another family assistant. Users can send messages, forward emails or make voice requests, and the assistant can turn them into schedules, reminders and plans. It can also coordinate calendars, household chores and meals across multiple family members. Ohai includes a free basic option, with subscriptions based on family size starting at $9.99 per month.

Ollie also focuses on family information spread across school messages, calendars, task lists and group chats. It can track calendars, emails, reminders, tasks and household details, then deliver relevant information through text. Its main differentiator is that Ollie is one of the first mainstream, family-focused AI assistants to achieve SOC 2 compliance, a widely used security standard. Launched in June 2026, it offers a free tier and paid plans starting at $25 per month for 150 messages, with a $100-per-month plan that includes up to 1,000 messages.

Travel, work and creator tools are splitting off

Not every assistant is trying to be a general-purpose helper. Some are narrowing the use case.

Miso applies the personal-assistant model to travel. It works through iMessage and combines AI trip planning with support from a dedicated travel team. Users can arrange flights through messaging while Miso accounts for travel preferences, loyalty points and other priorities. It also provides trip details, flight updates and personalized recommendations.

Town is aimed at professional life. It gives users a “Townie,” an AI assistant designed to learn how they work and handle recurring professional tasks. It can work with email, calendars, documents, Slack and other platforms. In June 2026, the company raised a $55 million Series A led by Andreessen Horowitz and Forerunner.

Stanley targets content creators. Available through iMessage, Telegram and the web, it acts as an AI head of content, helping users develop ideas, turn them into posts and maintain a publishing schedule. It can connect to Instagram, use that context to suggest content, turn voice notes into scripts and captions, and manage a content calendar that can schedule posts.

More autonomy means more responsibility

The most ambitious products in this space are beginning to act outside the chat window. Wajo’s consumer agent, Fo, can call businesses, send emails, join group chats, make bookings and purchases, and coordinate with people to complete everyday tasks. Fo has its own email address, phone number and payment card, so it can interact with businesses without requiring users to hand over their own credentials. If Fo cannot complete a task, Wajo says it can bring in a human assistant.

Other assistants are pushing in different directions. Poke launched in March 2026 as a general-purpose assistant reachable through text messaging, and in June 2026 Apple approved Poke as the first AI agent on the Apple Messages for Business platform. Tomo can join group conversations and help with goals, accountability, scheduling and everyday organization. Skye, from Signull Labs, is an “agentic homescreen” for the iPhone that surfaces contextual cards, suggestions and daily briefings instead of waiting for users to open an app.

Taken together, these products show how AI agents are moving from chat responses toward practical delegation. The interface may be as ordinary as a text thread, but the underlying promise is larger: calendars, email, reservations, shopping, travel, family logistics and work tasks handled from the same place people already message each other.