Private AI for regulated firms with data kept in your country or on your own servers
Proof of what an AI agent was allowed to do, and what it then did
Stage
Not given
Startup
Founded
Not given
2026
Based in
US
Not given
Pricing model
Freemium
Open source
Pricing
Per seat per month: €19 with ChatGPT, Claude or Codex integration (Your current AI setup); pricing varies for open models hosted in country or on own servers. Minimum 3 seats. Annual billing provides 2 months free versus monthly billing. Individual plans available. Custom quotes for more than 100 se
Not given
Key features
Inbox Triage bot: reads support inbox, drafts routine replies, flags items needing human attention
Reply Drafter bot: writes careful replies to emails using company history and policies
Support Report bot: turns weekly support emails into actionable reports with trends
Article Writer bot: creates weekly website articles from client questions
SEO Doctor bot: checks Google rankings and identifies pages to improve
Data audit logging: every question, answer and data access recorded on customer's servers
Open model support: runs Mistral, Qwen, DeepSeek and other open-source language models
Flexible deployment: existing AI apps, local cloud provider, or on-premise servers
Team Brain with source attribution: firm's memory with sources cited for every answer
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
What makes it different
Complete audit trail for regulatory compliance: every action logged on customer's side for audits and regulators
No per-prompt billing: fixed seat-based pricing regardless of usage volume
Designed by security expert: built by someone experienced in regulated industry deployments and compliance
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
Locul
Provared