| What it does | Policy-driven spending controls for AI agents
| AI agents for business that handle customer conversations, lead qualification, and task handoff across channels
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| PL
|
|---|
| Pricing model | Freemium
| Not given
|
|---|
| 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.
| Trial (free for 24 hours): 2 standard bots, 1 active automation, 5 MB knowledge base, 1 CRM pipeline. Standard ($59/mo or $47/mo yearly): 2 standard bots, 1 active automation, 100 MB knowledge base, 1 CRM pipeline, virtual office. Pro ($159/mo or $127/mo yearly): 4 standard + 1 Pro bot, unlimited au
|
|---|
| Key features | - 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
| - Multi-channel deployment across messengers, social networks, websites and email
- Marketplace with pre-built agents for specific roles
- Context and workflow connection between multiple agents
- Knowledge base integration for agent access to company information
- Virtual office dashboard for monitoring and control
- Lead qualification and customer qualification
- CRM pipeline integration and management
- Scalable agent expansion from single agent to unlimited
|
|---|
| What makes it different | - 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
| - No-code platform requiring no technical skills to build and deploy AI agents
- Agents automatically route completed requests to human managers
- Agents maintain context across multiple channels and business processes
- Visual dashboard with game layer makes AI work progress transparent
- Clear pricing tiers with included agents and ability to expand
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 23 ▲ +1 (up) since last check | 18 ● no change since last check |
| Trust Flow (Majestic) | 6 | 2 |
| Citation Flow (Majestic) | 19 | 19 |
| Referring domains (Majestic) | 12 | 13 |