Raspberry Pi
Small, focused setups
Local AI. Your own machine.
Own your
intelligence.
Your knowledge. Your models. Your machine.
Bring your documents, images, and recordings together. Turn what you know into answers, insights, and work you can use.
Open source tools. Knowledge you control.
Your information
- Documents
- Images
- Audio
- Video
Local model choices
Gemma · Qwen · GLM · Nemotron
Open foundation
Open-source harness. Runs locally.
Deployment options
Raspberry Pi · Mac & Mac mini · Windows / AMD · NVIDIA DGX
The things you know. The tools to use them.
A place that belongs to you.
Start with what
you already know.
Ask a question. Find a connection.
Pick up an idea.
Find the thought.
Not just the file.
Search across a collection and follow each result back to its source.
Interactive sample using fictional content. No files are uploaded and no model is called.
Your original knowledge stays close to every answer.
Explore the app previewYour models. Your machine.
A little computer.
Or a lot of compute.
One knowledge workspace, shaped around your hardware. Start small. Give it more room when you need it.
Windows & AMD
Modern laptops and AI PCs
Mac & Mac mini
Apple silicon, on your desk
NVIDIA DGX
Spark through larger systems
Choose from model families such as Gemma, Qwen, GLM, and NVIDIA Nemotron. Model size, memory, and runtime determine what fits.
Explore your setup ↗Hardware coverage shown as the product direction; this preview does not verify device compatibility.
Make every answer
more useful.
Start with sources you trust. Keep what works. Turn repeatable preferences into skills your brain can use again.
- Ask or searchStart with a real question.
- Check the sourcesSee where the answer came from.
- Add your feedbackMark what helped or needs work.
- Refine skills & searchImprove the instructions and sources.
- Ask againCheck whether the answer improved.
Carry what you learn into the next question.
Try the workflowExample collection
Make the answer
work for you.
From your answer preferences
Lead with what matters, connect the answer to its sources, and explain the details that help you act.
Check the original source
“Start with the key point. Cite the original material. Include helpful detail when needed, and check the source before acting.”
Fictional note for this example.
Did this help?
Your feedback gives you a place to start the next review.
Save the way
you like to work.
A skill is a reusable instruction. Try these two preferences and see how the same sourced answer changes.
The source stays the same. Your instructions change how the answer is put together.
Explore the knowledge workspaceInteractive example. Feedback and preferences stay in this preview; nothing is saved or trained.
Optional model improvementA guided path
A guided path
to fine-tuning.
Start with better sources and reusable skills. If the model still needs to learn a consistent pattern, review a training plan with clear examples and checks.
Choose examples worth learning from.
Review the question, the source, and the answer you would want. Include only examples you approve. A thumbs-up can flag an example for review; it does not train the model.
This walkthrough previews the decisions. It does not run training or change a model.
Make it yours
Start with your machine.
Build from there.
Explore the workspace yourself, or work with AIsoft to choose a model, connect your knowledge, and shape the experience around your work.
Talk through your setupA few good
questions.
The idea behind BrainBox.
What is BrainBox?
A personal AI workspace built around your knowledge, your choice of model, and your own machine. Ask questions, find connections, and open the original sources behind an answer.
What can I try here?
This website is an interactive design preview. Explore how your documents connect to local AI, try feedback and skills, open the example source, or open the app preview. The app uses fictional documents, and the improvement tools are illustrative.
Does it run without the internet?
The intended core experience keeps ingestion, indexing, questions, and citations local. Offline behavior needs to be verified on the actual machine; this design preview does not demonstrate a live local model.
Where does my knowledge go?
The core idea is that your original files, their index, and your model stay on hardware you own. The app makes the selected runtime and privacy policy visible.
Your next idea
is already in there.
Give your knowledge a place to connect. Keep the intelligence yours.