AI that reads each person first, knows their normal, and remembers every pair
Make AI decisions inspectable
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Paid
Not given
Pricing
43¢ per Reading. First 3 Readings free. Prepaid balance, stops at zero.
Community: Free (open artifacts, self-serve). Team: $2,500 per month (launch pricing). Governed Evidence Pilot: $15,000 flat for 30 days (launch pricing). Enterprise: Custom annual contract with own hardware. Per-call API: $0.02 USDC for OpenAI-compatible chat and completions, $0.05 USDC for mesh an
Key features
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
Policy gates before AI agent actions
Signed hash-chained receipt ledger
Offline verification capability
Evidence synthesis through Second Brain
Mapped controls for ISO/IEC 42001, EU AI Act and NIST AI RMF
Air-gap deployment on own hardware
Hardware-key signing with user's own keys
Evidence-plane sidecar for agent stacks
Auditor export bundle
Open receipt specification and format
What makes it different
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
Every decision sealed into verifiable offline receipts
Eight core formulas proven in Lean 4
Explicit labeling of claims as declared, simulated or roadmap
No hidden paywall metrics—usage counted in signed receipts you verify