Proof of what an AI agent was allowed to do, and what it then did
Structured AI decision support through multiple independent perspectives
Stage
Startup
Not given
Founded
2026
Not given
Based in
Not given
Not given
Pricing model
Open source
Paid
Pricing
Not given
Essential: €9 (4 AI perspectives); Consilium: €19 (8 AI perspectives); Grand Consilium: €29 (12 AI perspectives). Prepaid packages available: Essential packages of 5 for €39 or 10 for €69; Consilium packages of 5 for €69 or 10 for €129; Grand Consilium packages of 5 for €99 or 10 for €179. Each pric
Key features
Signed permissions with passkey authentication
Receipts for each agent action with signatures
Free checker tool to verify compliance
Quantum-safe signatures (Ed25519 and ML-DSA-87)
Permission narrowing for helper agents
Permission cancellation with signed acknowledgement
JavaScript and Python libraries
LangChain and Pydantic AI middleware
Multiple independent AI perspectives analyze the same question
Anonymous cross-checking of AI answers
Structured Decision Brief with recommendation and risks
Three analysis levels: Essential (4), Consilium (8), Grand Consilium (12) perspectives
Support for 42 languages
Automatic masking of personal and identifying data
Zero Data Retention requirement from AI providers
One follow-up question included per report
What makes it different
Only open-source project combining machine-checkable limits, permission narrowing for helpers, and signed permission cancellation
Built entirely from published standards with no hand-made components
Free and no dependencies, sends nothing anywhere or holds money
Distinguishes between record integrity and whether agent stayed within permission
All published versions stay available for backward compatibility
Anonymous ranking ensures quality of arguments over model reputation
Structured decision report rather than raw AI text
Data confidentiality with Zero Data Retention built in
Provared
Expert Consilium