Self-learning AI that learns from your chats and runs on a single iMac
One prompt, multiple AI answers side by side
Stage
Startup
Not given
Founded
2026
Not given
Based in
GB
Not given
Pricing model
Freemium
Paid
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.
Pro plan $20/month or $216/year (10% off annual); Pro+ plan $40/month or $432/year (10% off annual); Ultra plan $100/month or $1,080/year (10% off annual). All plans include multi-model access up to 3 models, all latest models, unlimited custom shortcuts, and image generation. Higher plans offer mor
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
Send one prompt to up to 3 AI models simultaneously
Reusable snippet shortcuts for common prompts
Access to all frontier labs, open source, and image models
Generate multiple images side by side from same prompt
Monthly usage allowance shown as percentage
No overage charges
Web search and file input support
Stack multiple shortcuts together
Real-time model response streaming
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
Compare multiple AI models side by side in one interface
Reusable shortcuts reduce repetitive typing
All models and image generators included in single subscription
Simple monthly usage allowance with no surprise bills