| What it does | AI assistant that automates desktop tasks by learning from your actions
| Policy-driven spending controls for AI agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: $0 per user with 10 included workflow runs and basic features. Plus: $20 per seat per month with expanded usage. Pro: $100 per seat per month with 5x more usage than Plus. Annual billing available at 20% discount. Enterprise plans available with custom pricing.
| 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 | - Learn tasks by demonstration - show once, replay automatically
- Works with existing apps via screen automation without integrations
- Voice command interface
- Team collaboration with shared playbooks
- Automatic workflow detection and updates when apps change
- Scheduled task automation
- Manual and automatic approval modes
- Content generation with image and music creation
- Knowledge base for team documentation and context
| - 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 integrations required - uses screen automation like a human would
- Learns by watching - no code or complex setup needed
- Automatically adapts when app interfaces change
- Voice-controlled AI that understands context from your screen
- Full team access to shared automations and knowledge base
| - 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) | 26 ● no change since last check | 21 ● no change since last check |
|---|
| Trust Flow (Majestic) | 4 | 6 |
|---|
| Citation Flow (Majestic) | 26 | 19 |
|---|
| Referring domains (Majestic) | 18 | 12 |
|---|
Audimate
ActOnce Spend Gateway