| What it does | Real-time AI assistant for meetings, interviews, and sales calls across 18 languages
| Policy-driven spending controls for AI agents
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2025
| Not given
|
|---|
| Based in | IN
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Starter: Free (20 credits/month); Pro: $38/month or $19/month yearly (180 credits/month); Pro Max: $59/month or $39/month yearly (420 credits/month); Ultra: $99/month or $69/month yearly (780 credits/month). One credit equals one minute of live session; credits reset monthly.
| Free: $0/month (open source, self-hosted). Pro: $24/month with hosted dashboard, 3 agents, 1,000 spend checks/month. Team: $99/month with 10 agents, 10,000 checks/month, team approvals. Business: $299/month with unlimited agents and checks.
|
|---|
| Key features | - Real-time AI responses in under one second during conversations
- Live transcription in 18 languages with mid-conversation language switching
- Private desktop overlay invisible to other meeting participants
- Interview copilot with resume and job description context
- Sales call assistance with objection handling and battle cards
- Automatic meeting summaries with action items and decisions
- Compatible with all major platforms including Zoom, Google Meet, Teams, Slack, WebEx
- Custom AI personas and instructions for personalized responses
- Session history and analytics to track performance
- Fully movable window that follows your eyes and stays on top
| - Policy Engine with YAML configuration for amount limits, merchant allowlists, category blocks, business hours, and duplicate windows
- Duplicate Detection using SQLite to prevent the same purchase twice within a configurable time window
- Human-in-the-Loop approval with Telegram alerts and dashboard queue for purchases exceeding threshold
- MCP-Native integration for OpenClaw, Hermes, and any MCP-compatible agent
- Zero Credential Exposure with no access to cards, tokens, or Stripe credentials
- Local-first architecture with all policy files, logs, and databases stored on your machine
- Dry-run and simulation mode for testing policies before deployment
|
|---|
| What makes it different | - No bots join your calls - completely invisible to other participants
- Responses generated in under one second, fast enough to use mid-sentence
- Works with any meeting platform without requiring bot integration
- Context-aware AI that understands your resume, role, and conversation history
| - Policy-driven rules that the agent cannot override, unlike prompt-based guardrails
- Zero credential exposure means the gateway never sees payment cards or API keys
- Duplicate detection with SQLite prevents duplicate purchases within a configurable time window
- Native MCP integration works out of the box with OpenClaw, Hermes, Claude Code, and Cursor
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 13 ● no change since last check | 21 ● no change since last check |
|---|
| Trust Flow (Majestic) | 5 | 6 |
|---|
| Citation Flow (Majestic) | 11 | 19 |
|---|
| Referring domains (Majestic) | 33 | 12 |
|---|
Craqly
ActOnce Spend Gateway