Joshua is an assistant that runs entirely on your own computer, a Mac or a Linux PC. It searches the web, reads your files, writes code, makes pictures and learns how you like answers, without sending your life to anyone's servers.
▸ Checking your Mac ✓ Apple M4 · 16 GB memory · 212 GB free · macOS 15.1 ▸ A few questions With 16 GB of memory, Joshua uses the 8-billion- parameter model: the best fit for your Mac. Install the deep-thinking version? [Y/n] y Install image generation? [Y/n] y Install the fine-tuning tools? [y/N] y ✓ Plan: qwen3-vl 8b + deep thinking + images + fine-tuning · about 21 GB Go ahead? [Y/n]
Joshua is artificial intelligence on a human scale. It runs on the computer you already own, on a small model, with the power of the machine on your desk instead of a data centre's. No tech giant sits in the middle holding your data and setting the rules. Technology at the service of people and of the planet, not the other way round. Read the manifesto
The honest small print: the models were trained in data centres, and your computer uses electricity too. What changes is the scale, and who is in control.
What you ask an assistant is a diary of your worries, your work and your plans. With Joshua, the model runs on your own chip. Your chats, files and memory sit in one folder on your disk, in plain files you can open, copy or delete.
When Joshua searches the web it goes out anonymously, with no account and no cookies, so nobody builds a profile from it. The same question gets the same results on any computer, in the language you asked in.
Untick the internet and Joshua keeps working: on a train, in the mountains, during an outage. Nothing switches off because a company changed its plans or its prices.
Every rule Joshua follows is in a few readable Python files. The memory it keeps about you is a notes file you can edit. And you can teach it your own style, on your own computer, with your own examples.
Joshua's model is a file on your disk, and it is yours to shape. With fine-tuning you retrain it on your own examples and create a new model of your own: one that writes in your tone, follows your formats and speaks your field's language. You keep it, you can copy it to another computer, and it stays exactly as you made it. How fine-tuning works
What you give up. A model that fits on a laptop is smaller than the giant ones in data centres: it makes more mistakes and writes less brilliantly. Joshua makes up for part of it by checking the web before it answers and fact-checking itself against its sources, and it tells you where each fact came from. It is also slower, and it needs a reasonably recent computer. If yours is too small, you can choose a cloud model for the chats that need one: see where your data lives.
Everything Joshua knows about you is kept in ordinary files in one folder on your computer, ~/AskJoshua. You can open them, back them up or delete them. Joshua answers with a model on your own computer by default. You can also pick a cloud model for a chat, to get a bigger model or to help a small computer. The table shows what each choice sends out.
| What | Where it is stored | Local model | Cloud model ☁ |
|---|---|---|---|
| Chats | Each chat in its own folder: ~/AskJoshua/joshua/conversations/; scheduled tasks in schedules.json | Never leaves your computer | The chat you are in is sent with each message, so the model can answer. Your other chats are not. |
| Files | The chat's files folder, or the project folder you point it to | Never leave your computer | Only the text Joshua reads from them, and pictures you attach |
| Memory | Notes about you, as editable text: ~/AskJoshua/joshua/memory/ | Never leave your computer | Not sent, unless you switch on “Share notes with cloud models”. The notes are always written by the model on your computer; with cloud models only, Joshua writes new notes only if sharing is on. |
| Your trained models | Examples in ~/AskJoshua/joshua/finetune/, models in Ollama's folder ~/.ollama | Trained and kept on your computer | Trained and kept on your computer |
| Pictures | The chat's files folder | Drawn on your computer | Drawn on your computer |
| Web searches | Nowhere: not stored | Search words go to search engines (Yahoo, DuckDuckGo, Brave, Startpage) with no account and no cookies. Tick “No internet” to stop it. | The same. The pages Joshua reads also go to the cloud model, as part of the chat. |
| Programs using Joshua | Each request is saved as a 🔌 chat in conversations/; the API key is in ~/AskJoshua/joshua/api.json | Only programs on this computer can connect, unless you allow your home network. They need the key. | Only if a program asks for a cloud model by name |
| Updates and model lists | Nowhere: not stored | When Joshua opens it asks ask.joshua.earth for the latest version number. The model lists are read from ollama.com when you open those panels. Nothing about you is sent. | The same |
| Your Ollama account | Only with cloud models: a key in ~/.ollama links this computer to your account | Not needed | Ollama knows your account and how much you use, to apply your plan's limits and billing |
With a local model, your conversations are never sent anywhere. The only things that go out are web searches and the pages Joshua reads, and you can switch those off. This is the default.
With a cloud model you rely on Ollama's word. Ollama says cloud prompts and replies are never logged or trained on, and that its hosting partners must keep nothing. The models run mainly in the United States, sometimes in Europe. Your computer can't check any of this, so Joshua marks every cloud chat with ☁ and tells you in the chat itself. Ollama's cloud terms
Plans and prices as of November 2026, from ollama.com/pricing; Ollama may change them. Local models stay free and unlimited.