Self-learning AI that learns from your chats and runs on a single iMac
AI phone assistant that answers calls, clarifies inquiries, and hands over to your team
Stage
Startup
Startup
Founded
2026
2025
Based in
GB
DE
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.
Pay as you Go: 0.35 € per minute without base fee; Advanced: 249 € per month (annual contract) or 299 € monthly, 1,250 minutes included; Scale: 449 € per month (annual contract) or 499 € monthly, 3,000 minutes included; Enterprise: from 0.15 € per minute; additional chat messages at 0.006 € each, SM
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
Call analysis: automatically evaluates conversations and transfers inquiries, contact details and urgency to CRM, ticketing or workflows
Internal dashboard chat for simulating calls and testing knowledge database
Outbound calling: scheduled or event-based calls with clean tracking
Personal call transfer to the right contact person
Call transcripts: all conversations documented, traceable and exportable
Widgets for simple interfaces leading callers to the AI assistant
Knowledge database: answers from your own know-how, versioned and controllable
Support for 10+ languages including German and Swiss German
On-Premises deployment option on customer's Linux and Docker infrastructure
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
No OpenAI or US AI subprocessors in conversation processing
Cloud hosting in Germany with GDPR and EU AI Act compliance
No AI training with customer data
Setup in minutes without technical knowledge required
cognira
smao