| What it does | Policy-driven spending controls for AI agents
| AI readiness check for websites: measures how well AI agents can access, understand and navigate your site
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2024
|
|---|
| Based in | Not given
| AT
|
|---|
| Pricing model | Freemium
| Free
|
|---|
| 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.
| Not given
|
|---|
| 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
| - 28 automated checks across access, understanding, discoverability, EU transparency and usability
- Static HTML analysis without JavaScript execution
- AI crawler identifier testing with GPTBot, ChatGPT-User, ClaudeBot, PerplexityBot and Google-Extended
- Rendered page analysis with JavaScript execution comparison
- Observed agent task execution with logging
- Five weighted scoring layers with consequence-based assessment
- Letter grade result from A to F based on rubric version 1.1.3
- Instant results with no registration required
- Checks for robots.txt, sitemap, llms.txt and trust pages
- Optional in-browser JavaScript rendering check
|
|---|
| 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
| - Weighted scoring model that treats missing features as not applicable rather than failures, preventing unfair penalties
- EU-focused transparency and privacy layer addressing GDPR and consent requirements specific to European compliance
- Versioned rubric that allows results to remain comparable across time
- Real agent task execution logging showing exactly where AI agents get stuck on your site
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 23 ▲ +1 (up) since last check | 45 ▲ +1 (up) since last check |
|---|
| Trust Flow (Majestic) | 6 | 15 |
|---|
| Citation Flow (Majestic) | 19 | 33 |
|---|
| Referring domains (Majestic) | 12 | 268 |
|---|
ActOnce Spend Gateway
Blck Alpaca