Free limited beta — no card required

A real personal assistant. In your Telegram.

It reads your mail, guards your calendar, remembers what you asked for and quietly runs the routine — all from one private chat. Inside it runs Hermes Agent, the open-source AI agent — launched, updated and watched over for you. No VPS, no terminal, no DevOps.

  • Ready in about three minutes
  • Your own AI provider
  • Keys encrypted, never shown again
Talaria
online · private chat
07:40
Morning. 4 emails need a reply, 2 meetings today, and the studio invoice is due Friday.
Reply to Anna — I'll approve it.
Draft ready. Send it, or want to edit first?
Built on open-source Hermes AgentPowered by your AI providerHosted & updated by TalariaSecrets in an encrypted store
One day, one chat

This is the entire product, hour by hour.

No dashboard to learn, no commands to memorize. You type like you would to a person; the platform does the unglamorous parts around it.

07:40
Before you're up
Morning. 4 emails need a reply, 2 meetings today, and the studio invoice is due Friday.

You didn't ask this morning — you asked once. Recurring work runs on the platform, between your messages.

09:15
The inbox you were avoiding
What did the bank send yesterday?
A card statement and a rate change from 1 Aug. Nothing needs a reply — want the numbers?

Mail passes through only when you ask. Message bodies are never stored or logged on our side.

11:20
A reply you didn't have to write
Draft a reply to Anna — I'll approve it.
“Thursday works, 15:00 my time. I'll send the deck the evening before.” Send it?
Send itLet me edit

Sending always waits for your confirmation in the chat. A plain “yes” isn't enough — you press the choice.

14:05
A calendar that defends itself
Move my 3pm to tomorrow and warn me if it clashes.
Moved to Thu 15:00. It overlaps your dentist at 15:30 — shall I make it 16:00?

Read-only or read & write, per account — and you pick exactly which calendars it may touch.

16:30
An answer instead of ten tabs
Compare these three tools — one line each, then pick one.
Two have the API you need; the cheapest of those is the middle one. I'd take it.

Thinking runs on the provider you connected — your ChatGPT subscription or your own key. Your model, your bill.

19:00
One less thing to remember
Every morning at 8, send me my day and anything overdue.
Set. First one tomorrow at 08:00.

Automations live on the platform, not in a script you babysit. You can pause or delete any of them from the dashboard.

23:50
While you sleep
Watching the two mailbox rules you set. Nothing needs you tonight.

Updates, monitoring and recovery are our job. If something wobbles, we notice it — not you.

That was one day. Yours starts in about three minutes.

Connect Telegram, pick your AI provider, launch. Free during the limited beta — no card.

Start my day one
Before the day starts

Three steps, about three minutes

A guided wizard walks you through each connection, remembers where you stopped, and never asks for a card.

STEP 1
Connect Telegram

Open our official bot with one secure link. That private chat becomes the place you talk to your agent.

You bring: a Telegram account
STEP 2
Choose your AI provider

Sign in with your ChatGPT subscription, or paste a key from OpenAI, Anthropic, OpenRouter or Nous Portal.

You bring: a subscription or API key
STEP 3
Launch

We prepare your agent and keep it ready. Calendar and mail are optional — connect them now or any time later.

Optional: calendar & mail
Ours, not yours
Nothing to install

No VPS, no terminal, no config files — ever.

Ours, not yours
Secrets stay sealed

Saved encrypted once, shown masked forever after.

Ours, not yours
It stays alive

Updates, monitoring and recovery are on us.

Start the guided setup

Free during beta · nothing to install · you can change everything later

Trust & privacy

It gets access to real accounts. Here's the deal.

Four promises we can point at in the product, not four adjectives.

Your keys are write-only

Provider keys and app passwords are validated once, stored encrypted, then shown masked forever — the dashboard and the API never return the value again, only its last characters.

Encrypted secret store · masked after save

The agent never holds your credentials

It reaches your accounts through our broker with short-lived, scoped access. Refresh tokens and passwords never enter the agent, its memory, its files or your chat.

Broker access · credentials stay platform-side

You choose how far it can go

Read-only or read & write, per account — and for calendars, exactly which ones. Sending an email always needs your confirmation in the chat first.

Per-account permissions · confirm before send

Your content goes where you send it

Your agent runs as a private instance. Mail bodies pass through the broker only when you ask — not stored, not logged on our side. What you send does reach the AI provider you connected, and Telegram keeps its own copy; the agent keeps only what you asked it to remember.

Transit-only mail · your provider, your model

Automated content checks are narrow and best-effort — they can miss things and can flag safe things, and they don't certify what you send as safe or lawful. Read the details in Privacy, Prohibited data and Security.

Under the hood

Powered by Hermes Agent — open source, in the open

Hermes Agent is an open-source personal AI agent by Nous Research, released under the MIT License. It is the engine inside every Talaria agent — we don't fork it into a black box, we run it for you.

Run it yourself

A fine weekend project if you enjoy ops — the repository has everything you need, and self-hosting is a legitimate choice.

  • Rent and secure a VPS
  • Install the runtime and dependencies
  • Keep API keys in env files
  • Apply every update yourself
  • Notice when it breaks — and fix it
Launch on Talaria

The same open-source engine — with the wings already attached.

  • Press Launch — ready in minutes
  • Nothing to install, ever
  • Secrets encrypted, masked forever
  • Updates arrive automatically
  • Monitoring and recovery included

Talaria is an independent managed service and is not affiliated with, sponsored by or endorsed by Nous Research unless separately announced in writing.

Limited beta

Two free ways to start during beta

Payment isn't enabled while legal and Paddle launch requirements are unresolved. Choose your own AI credentials now, or request managed access.

Core
Bring your own ChatGPT/Codex account or provider key
Free during beta
  • Active immediately during beta
  • Your provider bills model usage directly
  • Telegram workspace, apps and automations
  • No card and no Talaria payment

No administrator approval required.

Plus
Use the Talaria managed model gateway
Free during beta
  • No model-provider key required
  • Small one-time starter allowance while pending
  • Full monthly allowance after admin approval
  • Telegram workspace, apps and automations

A beta request is sent to an administrator for a capacity decision.

Common questions

A private Telegram chat with your own agent instance: it remembers your context, can read and act on the accounts you connect, and keeps running scheduled work while you're away. We host it, update it and watch it for you.

Meet your new assistant today.

Mail, calendar, reminders and research — handled from one Telegram chat. Free during beta, live in about three minutes.