Annotated screenshots for AI agents, not directions in words
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Open source
Pricing
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
Free
Key features
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
Numbered steps on screenshots
Arrows, boxes and labels
Automatic redaction of emails, tokens and API keys
MCP server integration
Command line tool
Runs on your machine only
Works with Claude, Codex, Gemini CLI and Cursor
Smart label placement with curves around content
Export as Markdown, HTML or PDF
What makes it different
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
Built for regulated and defense deployment
Shows the button instead of describing where it is
Runs entirely on your machine with no server communication
Automatically redacts sensitive data before AI sees it