Your AI knowledge partner for collecting, organizing, and creating from information
Brain-based AI that learns on your device without retraining, remembers you, and keeps your data private
Stage
MVP
Startup
Founded
Not given
2026
Based in
CN
US
Pricing model
Freemium
Not given
Pricing
Free plan: 5 GB storage, PDF/image parsing up to 600 pages/month, audio/video up to 60 minutes/month, maximum file size 20 MB. Pro plan: ¥35/month (or ¥0.94/day when paid annually with ¥70 discount) includes 50 GB storage, PDF/image parsing up to 3000 pages/month, audio/video up to 300 minutes/month
Not given
Key features
Web content capture and saving from browser
PDF, Word, and PPT file parsing into searchable documents
Automatic OCR for images and document scans
Audio and video transcription with summaries and key frames
Natural language search across knowledge base
AI-powered question answering with source citations
WeChat and QQ message forwarding to knowledge base
RSS feed subscription and auto-import
AI Agent for file organization and workflow execution
Open source code with self-hosting and offline support
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Corrected facts replace outdated information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
Unified content collection from multiple sources including chat apps, RSS, and web without changing habits
Automatic understanding and indexing of all content types for search and AI use
AI capabilities integrated directly into other AI tools via Skill integration
Free tier with generous quotas for most users before paid upgrade needed
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