| What it does | Policy-driven spending controls for AI agents
| AI that reads each person first, knows their normal, and remembers every pair
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| 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.
| 43¢ per Reading. First 3 Readings free. Prepaid balance, stops at zero.
|
|---|
| 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
| - Reads individual email history and communication patterns
- Analyzes what has built up between two people over time
- Tracks changes against each person's normal baseline
- Provides color-coded feedback: green, yellow, red across five dimensions
- Predicts likely outcomes with recommended actions
- Includes contextual external factors when provided
- Sealed record system for privacy and historical continuity
- MCP server with Apache 2.0 open source client code
- llms.txt file for agent discovery and integration
- OpenAPI file for tool integration
|
|---|
| 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
| - Reads each person individually first, through their own patterns, rather than generic scoring
- Remembers relationship history and shows what changed between readings
- Never returns scores, trait ratings or personality labels on named people
- Simple one-request API integration with no library installation needed
- Privacy-first: sealed records only ARVX can decrypt, keeps nothing about subjects
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 23 ▲ +1 (up) since last check | 12 ▲ +3 (up) since last check |
| Trust Flow (Majestic) | 6 | 4 |
| Citation Flow (Majestic) | 19 | 28 |
| Referring domains (Majestic) | 12 | 24 |