| What it does | Free personal AI agent that asks before it acts
| The AI assistant who gets work done, before it slips
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | IN
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: $0/month, 50 messages a day, 3 tasks in background, 5 computer tasks a month, every feature. Pro: $8/month, unlimited messages, smarter engine, unlimited tasks, 100 computer tasks a month.
| Free plan with up to $50 in free credits; Individual plan $25/month including 5,000 credits per month; Team plan with custom pricing.
|
|---|
| Key features | - Asks for approval before sending, posting, booking or deleting
- Scheduled tasks and background automation
- Pre-built ideas and templates for common tasks
- Computer tasks using real browser automation
| - Drafts email replies in your voice
- Prepares meeting briefs automatically
- Captures and tracks commitments
- Updates CRM automatically
- Connects to 100+ tools including Gmail, Slack, and HubSpot
- Learns work patterns without workflow setup
- Morning and evening digests of what needs attention
- Surfaces forgotten follow-ups and open loops
|
|---|
| What makes it different | - Asks for approval before any action that changes something
- Lives on Telegram where you already chat, no new app to learn
- Works on phone, tablet or computer with one shared conversation
- Data never used to train AI or sold; you control your memory
- Runs tasks on a schedule and checks in when things slip
| - Proactive: surfaces work that needs attention before you ask, rather than waiting for you to prompt
- No setup required: builds workflows automatically from your patterns, not from a configuration wizard
- Full control: everything external or consequential waits for your approval before sending or changing systems
- Multi-tool context: learns across all your tools to understand your tone, priorities, and patterns
- Privacy-first: data encrypted end-to-end, SOC 2 Type II compliant, and never used to train models
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 2 ▲ +1 (up) since last check | 32 ▼ −1 (down) since last check |
|---|
| Trust Flow (Majestic) | 0 | 6 |
|---|
| Citation Flow (Majestic) | 17 | 32 |
|---|
| Referring domains (Majestic) | 5 | 144 |
|---|
Yomi AI
Demi