| What it does | Self-learning AI that learns from your chats and runs on a single iMac
| Your portable, quotable memory vault for every AI you work with
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| 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: $0 with 1 complete personal workspace, unlimited capture from Claude ChatGPT & Gemini, automatic extraction of decisions frameworks & action items, and connect to Claude via MCP. Plus: $19/month includes everything in Free plus unlimited client & project workspaces, ability to talk workspaces
|
|---|
| 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
| - 1-click browser export for Claude, ChatGPT, Gemini, Perplexity conversations
- Automatic extraction into 8 categories: decisions, frameworks, golden passages, definitions, actions, questions, offers, emergence
- Real-time vault recall in Claude and ChatGPT via Model Context Protocol
- Character-level provenance tracking with exact line quotes
- Free archive unpacker for ChatGPT and Claude exports
- Chrome browser extension for automated export
- Export to multiple formats: Markdown, PDF, HTML, JSON, plain text
- Bring your own AI API key for Claude, OpenAI, Google, or Ollama
- Cross-conversation research briefs synthesizing insights with cited quotes
- Voice profiles to make AI write in your authentic voice
|
|---|
| 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
| - Every extraction traces back to exact character positions in original source, with zero hallucinations
- Persistent memory across multiple AI platforms means knowledge compounds instead of resetting
- Automatic extraction from raw chats without manual tagging or organizing
- Open infrastructure with portable markdown seeds and zero vendor lock-in
- Independent founder maintaining complete data sovereignty
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 23 ▼ −1 (down) since last check | 1 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 0 |
|---|
| Citation Flow (Majestic) | 23 | 12 |
|---|
| Referring domains (Majestic) | 44 | 3 |
|---|
cognira
Multiplist