| What it does | A company brain that answers questions and drafts follow-ups for your approval
| Runtime security for your own agents
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | IN
| Not given
|
|---|
| Pricing model | Paid
| Freemium
|
|---|
| Pricing | Solo $24/mo for one person or small founder team; Team $100/mo for up to 10 people. Monthly plans, cancel anytime. In India: Solo ₹1,999/mo, Team ₹8,299/mo. Bring your own AI key billed separately by provider. Enterprise custom pricing available.
| Free: $0/mo for 1 agent with scanner, approvals, kill switch, phone and Telegram alerts, and 7-day history. Pro: $24.99/mo for up to 5 agents with learned autonomy, Time Machine, data-leak tripwire, vault, and unlimited history. Team: $79.99/mo for unlimited agents with everything in Pro plus priori
|
|---|
| Key features | - Connect to Slack, Gmail, Google Drive, Notion, Jira, Linear, GitHub, Zendesk and databases
- Ask questions in plain English and get answers with links to sources
- AI code review on every pull request
- Turn meeting notes into tickets
- Draft email replies, calendar events and Notion pages
- Actions queue for approval before any action runs
- Ask from web app, Slack, phone, Claude, Cursor or API
- Bring your own AI key from Google, OpenAI or Anthropic
- MCP server support for Claude and Cursor
- Permission control so people only see what they can access
| - Skill scanner for hidden instructions in documentation
- Encrypted vault for secrets kept away from agent context
- Kill switch for instant agent stopping
- Rewind time machine to walk back agent actions
- Data-leak tripwire for PII and secrets detection
- Live operations dashboard monitoring all agents
- Phone and Telegram alerts for held and blocked actions
|
|---|
| What makes it different | - Answers always include citations and links to the source
- Flat monthly pricing not per-seat or per-question
- No markup on AI—use your own key and pay providers directly at cost
- Works across all your tools as one connected brain
| - Runtime gate checks actions before they execute, not after like logs
- External to agent so injected content cannot override security rules
- Differentiates between reversible actions that flow immediately and irreversible ones needing approval
- Catches runtime threats that static scanning misses
- Built for individual developers, not enterprise
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 7 ▼ −1 (down) since last check | 2 ● no change since last check |
| Trust Flow (Majestic) | 5 | 7 |
| Citation Flow (Majestic) | 26 | 13 |
| Referring domains (Majestic) | 29 | 8 |