Build agents by talking
Say what you want handled. Your Companion checks it understood you.
Build them by talking. They use your calendar, contacts, camera, location and Shortcuts to get real things done. Nothing to host, no Mac mini.
Real screens from the app, doing real things.
Say what you want handled. Your Companion checks it understood you.
From any app, share a PDF, link or photo straight to the agent that should handle it.
Your new agent runs on schedule, right on your phone.
Agents show the exact action and wait for your tap.
Every agent is a voice agent. Talk, and it runs the app.
Agents turn routines into fast workflows you can re-run.
Tappable boards for your tasks, habits and people.
Three steps, all on your phone.
Describe what you need in plain words, typed or spoken.
Your Companion sets it up, tests it and puts it on a schedule.
Watch your agents work from Home, and step in whenever you like.
Your agents don't just live in a chat box. They have direct access to your phone's sensors, hardware, and system tools to get real work done.

Calendar, reminders, contacts, alarms.
On iPhone, alarms open the Clock app.

Drafts texts and emails for you to send, and starts calls you confirm.
On Android it can also read your other apps' notifications.

Location, plus geofence automations ("when I get to the office...").

Schedules, heartbeats and triggers wake your agent, which runs on your phone.

Camera, text recognition (OCR), photo search, on-device memory and files.

An in-app agentic browser, web search and web requests.

Apple Shortcuts (build and run), Siri "Ask HITL", Share to HITL, Live Activities, and Health (Apple Health / Health Connect).
On Android it can analyse your screen when you tap.

HITL-managed models from leading AI providers, included with your plan; bring your own API key (OpenAI, Anthropic, Google, OpenRouter); or connect your own self-hosted OpenAI-compatible endpoint.
*Agents stay on your phone unless you turn on backup; HITL registers only their names, for metering. Model requests go to the provider you choose. See our privacy policy.
Built-in, any major provider, or your own server. You choose how private.
Already running Claude Code, an MCP client or OpenClaw? Get their questions and approvals on your phone too. Unblock coding and background workflows with one-tap decisions from anywhere.
No cloud computer, server or Mac mini.
Not one assistant.
Use HITL's built-in models, your own key, or your own server.
On your phone. HITL is an iPhone and Android app, and your agents, their memory and your chats live there, not on a cloud computer we rent for you. When an agent needs to think, it sends that request to the AI provider you choose. Some Android phones can also run an experimental model on the phone itself.
Your agents, their memory, your chats and your files are stored on your phone. When an agent works on something, your request, plus anything the agent read to answer it (for example a calendar entry or a photo), goes to the AI provider you've chosen. That's the only way it can reply. The first time this happens, the app tells you what's sent and to whom, and asks your permission. We don't sell your data. Backups are made only when you ask for them.
No. Texts and emails are drafted for you to send yourself, and calls start only when you confirm. Every tool an agent can use has a trust level:
The agent shows you exactly what it's about to do and waits for your tap.
The things your day runs on:
Each of these needs your permission first.
One assistant juggling every instruction gets confused. With HITL, each agent has one job, such as a morning brief, a receipts tracker or a research helper, with its own instructions, tools, model and schedule. Your Companion helps you build and manage them, and agents can team up in a Squad for bigger jobs.
Yes. Add HITL as an MCP server in Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, Zed or any MCP client, or connect an OpenClaw instance. Its questions, notifications and approval requests then arrive in your HITL Inbox. You answer with a tap, by voice or with a file, from anywhere. Optional end-to-end encryption is available.
Yes. The Free plan includes agents, up to 4 active schedules and a monthly model allowance. Agents are unlimited during the beta. Pro and Max add more model usage and schedules, and their prices are shown in the app for your country. Bringing your own API key works on every plan, including Free.
Your AI agents live on your phone. Join the public beta on iPhone and Android.