AI governance and privacy platform that detects PII, masks prompts and audits LLM traffic
Open-source memory for AI agents that stays correct as facts change
Stage
Not given
Not given
Founded
Not given
Not given
Based in
ES
SE
Pricing model
Paid
Freemium
Pricing
Starter: €150/month or €120/month (annual). Growth: €250/month. Business: €400/month or €320/month (annual). Scale: €700/month. Enterprise: €1,250/month. Enterprise+: €2,500/month. Volume-based pricing available for >5M requests/month. 14-day free trial available. Additional requests: €15 per extra
Open Source: free self-hosted. Oort Pro: $19/month (VAT included where applicable) with 5,000 saves a month, 25,000 recalls a month, and 1 GB of memory storage.
Key features
Multi-provider LLM routing for OpenAI, Anthropic, Mistral, Groq, and OpenAI-compatible endpoints
Immutable blockchain-certified audit logs via iCommunity Blockchain Services
Governance dashboard with visibility into AI usage, policy enforcement, and audit logs
Privacy-first governed chat interface for enterprise teams
Output scanning to detect and anonymize sensitive data in model responses
Context optimization reducing token usage by up to 57% on logs and tool outputs
Exportable DPO reports in PDF for compliance documentation
RAG protection with Privaro Ingest and Retrieval Guard with per-chunk access control
Memory recall with millisecond latency and explanations
Automatic fact lifecycle management
Data privacy with secrets scrubbed before saving
Export and forget capabilities
CLI and npm package
Integration with ChatGPT and Claude.ai
Flat-rate pricing that does not scale with history
What makes it different
Blockchain-certified immutable audit trail provides legally admissible evidence for compliance and regulatory audits
Works with any LLM provider through unified multi-provider routing without vendor lock-in
Reduces LLM costs through context optimization that compresses logs and outputs before model inference
Built specifically for regulated industries with pre-configured use cases for legal, healthcare, and fintech
No integration friction with endpoint-level proxy requiring only an endpoint change in LLM calls
Facts stay correct as they change, with closed-out old versions
Costs remain flat as memory history grows
Every recall can explain why it returned that memory
Self-hosted with no required API keys for open source
Privaro
Oort