Your private AI assistant for any website.
Works even offline! Run AI in your browser with no external connections, keeping all your data on your device.
Stop switching context, use directly on any site
Summarize private messages, emails and documents, ask about private code snippets, translate text, fix grammar, ... Everything in seconds without leaving the browser tab.
Select text to add context
Switch between local models
Use it even offline
Most languages supported
No matter where you are from, the models know your language
Pricing
Why paying an expensive subscription for no privacy if you can buy once and use it forever with total privacy?
$50 off for the first 100 customers
Our simple pricing
Fully private, one-time payment, use it forever
$149
$99 / one time
- Fully private local inference
- Use AI even offline
- Pay once, use it forever. No suscriptions
- Unbeatable price, as we don't depend on third-parties.
- Premium support - we are here for you
- Lifetime updates
Others Charge
Standard industry subscription pricing
$160-$360 / year
- They send your data to third-party APIs that store it
- Require an internet connection
- Force you to pay month after month for the same
- Very expensive since their inference providers are expensive.
Supported AI models
This table shows the currently supported AI models. All models run locally on your device. Your GPU needs the specified minimum memory to run each of them.
| Model | Required VRAM (Gb) |
|---|---|
| Llama 3.2 1B | 1.10 |
| Llama 3.2 3B | 2.88 |
| Llama 3.1 8B | 5.17 |
| Qwen 2.5 0.5B | 1.04 |
| Qwen 2.5 1.5B | 1.59 |
| Qwen 2.5 3B | 2.83 |
| Qwen 2.5 7B | 5.76 |
| Mistral 7B | 5.49 |
| Gemma 2 2B | 1.85 |
| SomlLM 7B | 7.26 |
Minimum device requirements
Your device must meet the following minimum specifications.
RAM
4 GB or higher
Storage
2 GB free disk storage
GPU
1.5 GB VRAM
Increase your productivity without risking your data
Install Extension