One assistant across every chat app

Most people juggle several messaging apps in a day, and most AI tools live in just one of them. MiyoMind takes the opposite approach: it is the same assistant, with the same memory and the same abilities, wherever you happen to be typing. Ask Miyo a question on Discord at your desk, then pick up the thread from WhatsApp on your phone, and it already knows what you were doing.

Which chat apps does MiyoMind work on?

MiyoMind works on four surfaces today: WhatsApp, Telegram, Discord and a web dashboard at miyomind.com that runs in any browser. For chat there is nothing extra to install — you message Miyo inside the app you already use, the same way you message a contact. The web dashboard adds a fuller view for managing files, connectors, reminders, credits and settings.

• WhatsApp — message Miyo like any contact, including voice notes that get transcribed.
• Telegram — chat one-on-one with the bot, with the same memory as every other surface.
• Discord — talk to Miyo inside Discord for quick questions and help.
• Web dashboard (miyomind.com) — the full control panel for files, connectors, reminders, memories and billing.

How does continuity across platforms work?

Continuity comes from a shared account and a long-term memory layer that sits behind every surface, not inside any one chat app. When you connect WhatsApp, Telegram, Discord and the web dashboard to the same MiyoMind account, they all read from and write to the same place. So Miyo's understanding of you — your preferences, the things you have told it to remember, your reminders and your files — is consistent no matter where the conversation happens.

1. Link a platform to your MiyoMind account from the dashboard (Settings).
2. Message Miyo on that platform — it shares the same memory and tools as every other surface.
3. Start a task anywhere: ask a question, draft an email, set a reminder, or generate an image.
4. Continue it anywhere: switch apps and Miyo carries the relevant context with you.
5. Reminders you set fire across your chat apps, so a nudge reaches you where you are.

A practical example: you are on your laptop in Discord and ask Miyo to research a topic with live web search and citations, then save a short summary as a file. Later, away from your desk, you message on WhatsApp — "send me that summary" — and Miyo knows what you mean, because the file and the conversation live with your account, not with Discord. Set a recurring reminder from Telegram and it can reach you on WhatsApp at the right time.

What can the assistant actually do on each platform?

The core abilities are the same across surfaces. In one conversation, Miyo handles live web search with citations, drafting email, one-off and recurring reminders that fire across your chat apps, image generation, voice notes and transcription, reading and analysing documents and PDFs, creating and delivering files, long-term memory of what matters to you, and recall of past conversations. It also connects through secure OAuth to tools you already use.

The connectors you enable apply to the whole account, so a tool like Gmail, Google Calendar, Drive, Outlook, Notion, Slack, GitHub or Linear is usable from any surface once the operator has configured it and you have connected it. MiyoMind offers around 30 connectors across productivity, storage, social and more.

Is it private and safe across all these apps?

Privacy and safety are built into the platform, not bolted onto each app. Every paid user gets their own dedicated, sandboxed Docker container with an isolated workspace, no public internet egress, zero stored external API keys, a read-only root filesystem and dropped Linux capabilities. Your integrations and memories are encrypted at rest with AES-256-GCM. A 10-layer prompt-injection defence plus output scrubbing runs on every message, whichever surface it arrives from. The free tier runs on a shared direct-agent path without a dedicated container.

It is worth being clear about how MiyoMind is built, because cross-platform continuity depends on it. MiyoMind runs the open-source OpenClaw agent runtime plus a model router called Hermes plus our own proprietary orchestration, memory, billing, safety and routing code. It uses frontier models from OpenAI, Anthropic, Google, xAI and Alibaba. The persona, memory, safety and routing are ours — MiyoMind is not a wrapper around a single model.

How much does a multi-platform assistant cost?

You use every supported platform on a single account, and the same pricing covers all of them. The Free plan is $0/mo with 100 credits each month and no card required, running on the shared direct-agent path. Plus is $14.99/mo with 6,000 credits/mo and one dedicated container. Pro is $39.99/mo with 18,000 credits/mo and one dedicated container. Credits meter actual model and tool usage, where 1 credit is roughly $0.005 of value, and you can buy top-up packs (600/$3, 2,000/$10, 5,000/$25, 10,000/$50).