| What it does | Press a hotkey, drag a box around anything on your screen, and get instant AI explanations without switching apps
| An AI workforce that runs on your machines
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: $0 per month (3 captures daily, 10 per week, Fast model only, up to 2 follow-ups). Plus: $10/month or yearly with 17% savings (2,000 credits monthly, both Fast and Best models, up to 10 follow-ups). A capture costs 1 credit on Fast model and 20 credits on Best model.
| Free: $0/mo (1 agent, 10k API calls/mo). Starter: $9/mo (2 agents, additional agents $7 each). Pro: $29/mo (5 agents, additional agents $5 each). Business: $99/mo (25 agents, additional agents $3 each). Agentic OS early access is free while in beta.
|
|---|
| Key features | - Hotkey activation for instant capture
- Streaming answers while capturing
- Follow-up questions within the same capture
- Two AI models (Fast and Best)
- Rich formatting with Markdown and code blocks
- 16 color themes including Dracula and Nord
- Multiple regions selection (up to 4)
- Local searchable chat history
- Multilingual support for 8+ languages
| - Command Center shows goals, plans, and shipped work with pull request integration
- Agent runs on your own hardware with persistent, stoppable execution
- Signed, tamper-evident receipts for all memory access
- Encrypted Vault for private information sealed in browser before upload
- Trust score from 0 to 1000 based on verifiable activity
- Verified badge eligibility for published agents
- MCP tools for building and publishing custom agent capabilities
- JavaScript and Python SDKs with auto-instrumentation for tracking
- Cryptographic verification that instructions come from your workspace
- Full memory export with no vendor lock-in
|
|---|
| What makes it different | - No app switching or context loss during workflow
- Fast enough that using it never becomes a decision
- Free plan is a real plan with no trial countdown or feature restriction
- Works on Windows, macOS, and Linux
- Captured content is deleted after answer returns
| - Agents run on your machines with full data privacy and local execution
- Verifiable, tamper-evident audit trail for every agent action
- Agent memory persists across model changes with no loss of context
- Finished work delivered, not chat logs—pull requests and shipped tasks
- Earn from published agents through creator payouts on the directory
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 3 ▼ −1 (down) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 5 | 0 |
|---|
| Citation Flow (Majestic) | 25 | 13 |
|---|
| Referring domains (Majestic) | 65 | 4 |
|---|
Squint
Kynver