| What it does | Policy-driven spending controls for AI agents
| The evidence layer for AI-agent actions
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| 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.
| Developer: Free with no time limit (1,000 verified actions/month). Builder (Founding): $59/month for first 12 months, then $99/month (5,000 verified actions/month, then 2.5¢ per action). Team: $299/month (25,000 verified actions/month, then 1.5¢ per action). Growth: $999/month (100,000 verified acti
|
|---|
| 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
| - Records agent actions through API or OpenTelemetry spans
- Verifies actions against systems of record including Stripe, Shopify, Salesforce, HubSpot, Zendesk, Intercom and Coinbase
- Integrates with agent frameworks: LangGraph, CrewAI, OpenAI Agents SDK, Pydantic AI
- Supports workflow runtimes: Temporal and Inngest
- Action contracts define verification rules with limits and required effects
- Settlement window re-checks verify actions again at end of settlement window
- Webhooks and Slack/PagerDuty alerts on verdict results
- Public hash verification allows verifying verdicts without an account
|
|---|
| 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
| - Verdicts come from deterministic rules, not language models
- Never blocks actions; verifies after the fact only
- Takes no payment from vendors; paid only by customer
- Tested against real models: Claude, GPT and Gemini
- Priced by verified actions, not seats or agent claims
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 23 ▲ +1 (up) since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 6 | 0 |
| Citation Flow (Majestic) | 19 | 17 |
| Referring domains (Majestic) | 12 | 1 |