Self-learning AI that learns from your chats and runs on a single iMac
AI roleplay and novel reader for mobile with branching story continuations and SillyTavern compatibility
Stage
Startup
Startup
Founded
2026
2026
Based in
GB
Not given
Pricing model
Freemium
Freemium
Pricing
Free: £0/forever with 25K tokens/week. Pro: £15/month with 500K tokens/week. Max: £30/month with 2M tokens/week. API: £1.50 per 1M tokens, minimum £5 top-up.
Free core app with unlimited messages. Optional one-time Pro purchase: $19.99 (unlocks 3+ books/cards/companions). AI costs: bring your own API key at provider list price with zero markup, or official credits at $0.0001 per credit (5,000 granted at sign-up). Credit packs: $0.99 (6,000 credits), $2.9
Key features
Private memory that works immediately when you teach it
Verified shared knowledge with public rejection ledger
Local MLX inference not forwarded to external API
cognira Entity for local on-device AI with optional weight retraining
OpenAI-compatible API endpoint
Served from single 16GB iMac not a GPU cluster
Background learning loop with safety filtering
Chat history, pinning, and search
One-tap Forget button to remove memories
No ads and no data sales
SillyTavern character card and lorebook import
AI story continuation with branching timelines
Support for 60+ AI providers including OpenAI, Claude, DeepSeek
Visual novel theater mode with choices
Roleplay chat with 12 contextual actions
Text-to-speech narration with speed and sleep timer
Five page-turn animation styles including realistic curl
API key encryption with zero-markup provider routing
Request logging with prompt cache hit tracking
What makes it different
Self-learning from user chats with verified public ledger of what stuck
Runs on one iMac not a GPU cluster with measurable low energy use
Independent model served directly, not a wrapper around external API
Immediate private memory plus verified weight updates to shared knowledge
First mobile reader that treats AI continuation as structural branches rather than overwrites
Zero-markup pricing for 60+ AI providers at raw list price
89% prompt cache hit rate saves costs on repeated contexts
Free core with every feature except unlimited library storage
cognira
Foreverse