Agentic AI research assistant that interprets lab results and turns research questions into cited, evidence-backed briefs
Brain-based AI that learns on your device without retraining, remembers you, and keeps your data private
Stage
Established
Startup
Founded
2018
2026
Based in
CY
US
Pricing model
Freemium
Not given
Pricing
Basic (free) with monthly usage allowance; Plus €18/month with 3x the Basic allowance; Pro €75/month with 13x the Basic allowance; Team €125/month for 3 seats then €37 per extra seat with 9x the Basic allowance per seat; Organization €150 per seat per month with Pro usage limits. Paid plans can purc
Not given
Key features
Semantic search across 40 million biomedical papers
Full-text reading and citation tracking
Trust Index for result reliability screening
Research landscape and concept mapping
Zotero library integration
Weekly research digest and personalized feed
PDF and Word report export with citations
Mechanistic links and hypothesis generation
Saved clusters for organizing research
Learns continuously on your device without retraining
Remembers individual users separately
Runs fully offline on consumer hardware like iPad
Learns without forgetting existing knowledge
Consistent performance over long conversations
Honest about uncertainty
User controls what it learns
Works with existing language models
Corrected facts replace outdated information
Designed for disconnected networks
What makes it different
Reads full-text papers instead of just abstracts for comprehensive analysis
Every claim grounded in verified citations with evidence-typed sources
Monitors when literature moves on and notifies users of updates
Constrained reasoning engine reduces AI hallucinations through literature grounding
Biology-native evidence engine with knowledge graphs for semantic understanding
Continual learning architecture that learns in place after deployment, unlike frozen models
Brain-modeled design with separate organs for memory, sleep, and decision-making
All learning happens on your device with no data sent to servers
Works where cloud connectivity is unavailable or undesirable
Patent-pending learning method usable with other large language models