| What it does | One memory. Every AI. Only yours.
| The new interface for AI agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| DE
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Not given
| Free: €0/month with 25 on-screen requests per month, 2 projects, and 5 connected tools. New users get a 14-day Pro trial. Pro: €19/month or €199/year for unlimited on-screen requests, unlimited projects, unlimited integrations, knowledge graph memory, and priority support. AI provider charges are se
|
|---|
| Key features | - Chrome extension integration with ChatGPT, Claude, Gemini, Grok, DeepSeek and Kimi
- MCP server for coding tools like Cursor and Claude Code
- Python and TypeScript SDKs for custom agent integration
- Save conversations, web pages, documents and connected app content
- Review, correct and remove saved memory
- Control which AI tools access specific memories
- Export memory in documented formats
- Local deployment option with Python 3.12 or 3.13
- 93.1% answer accuracy on LoCoMo benchmark
- 67% fewer tokens than full conversation history on LoCoMo
| - Computer use: clicks, types and fills forms in apps
- Voice dictation and screen marking
- Memory that learns user details and reuses them
- Parallel agents running simultaneously
- On-screen guidance showing where to click
- Integrations with Gmail, Slack, Notion, GitHub and more
- Task board to track running, done and waiting tasks
- Projects as workspace homes with tasks, chats and results
- Skills: save and reuse how you do a job
- Works with Claude Code, Codex and OpenCode
|
|---|
| What makes it different | - One unified memory across all your AI tools instead of separate memories in each
- Complete user control: review, correct, delete and export your memory anytime
- Runs hosted or locally on your own machine
- Published benchmark method and results for transparency
- Open source SDKs, CLI and MCP server on GitHub
| - Works directly on your screen in your apps instead of forcing you to a chat window
- Visual input through pointing, drawing, and marked screenshots instead of text prompts
- Full user control: asks before acting and shows cursor while working
- Remembers user details and context across tasks
- Voice-based task dispatch from any app you're already using
|
| Community votes | 0 | 5 |
| DR (Domain Rating by Ahrefs) | 28 ▼ −1 (down) since last check | 28 ● no change since last check |
| Trust Flow (Majestic) | 11 | 0 |
| Citation Flow (Majestic) | 32 | 27 |
| Referring domains (Majestic) | 73 | 56 |