| What it does | Policy-driven spending controls for AI agents
| Accountable AI for autonomous work that answers for itself
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| DE
|
|---|
| Pricing model | Freemium
| Paid
|
|---|
| 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.
| Founder $1,000/month, Team (up to 10 people) $3,000/month, Investor firm $3,000/month, Company from $10,000/month. Early members receive launch prices set on individual calls. Flat plans with unlimited jobs, no per-seat fees, and month-to-month billing.
|
|---|
| 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
| - Autonomous job planning and execution with parallel specialists
- Independent verification check before results reach user
- Integrates with existing apps and accounts without API requirements
- Private per-customer workspace with encryption in transit and at rest
- Corrections become rules for future runs
- Full audit trail with source links for all findings
- Month-to-month billing with no lock-in contract
- Unlimited jobs on flat monthly pricing
- Results within the hour after setup
- Draft approval workflow for outbound communications
|
|---|
| 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
| - Answers for the work rather than just running tasks autonomously
- No setup required; company handles configuration and ongoing management
- Separate verification step ensures quality before delivery
- Works across 35 AI providers through user's own API keys
- Customer playbooks never shared with competitors
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 21 ● no change since last check | 2 ● no change since last check |
|---|
| Trust Flow (Majestic) | 6 | 2 |
|---|
| Citation Flow (Majestic) | 19 | 21 |
|---|
| Referring domains (Majestic) | 12 | 38 |
|---|
ActOnce Spend Gateway