Open-source memory for AI agents that stays correct as facts change
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
SE
Pricing model
Freemium
Freemium
Pricing
Free plan with 10,000 monthly credits; Starter at $50/month with 40,000 credits; Pro at $500/month with 400,000 credits; Enterprise with custom pricing. Additional pay-as-you-go credits available. Pricing based on a credit system where 1,000 credits equals $1.25.
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
Agentic OCR parsing with semantic understanding for complex document layouts
Support for 130+ file formats including PDFs, Office docs, images, and spreadsheets
Structured data extraction with schema-based, LLM-powered agents
Document classification and splitting based on natural language rules
Enterprise-grade RAG indexing and retrieval pipeline
Handwritten text parsing and structured extraction
Table and chart extraction with structured row and column relationships
Cloud SaaS or VPC deployment with flexible data residency options
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
4x cheaper than frontier labs, 5x more accurate than other APIs
Auto-correction loops with recursive checks that detect and fix errors automatically
Task-specific specialist agents that route content to the right expert
HIPAA, GDPR, and SOC2 compliant with enterprise-grade security
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
Oort