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.
curl -fsSL https://ask.joshua.earth/install.sh | bash
Paste it in a terminal. A Mac with Apple Silicon (M1 or later) or a Linux PC, 8 GB of memory, 10–40 GB of free disk. On Linux an NVIDIA graphics card makes it much faster. Free and open.
▸ 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]
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.
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. |
| 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; Ollama may change which models are free. Local models stay free and unlimited.
For facts that change, it searches, reads the pages, answers with numbered sources, then fact-checks its own answer against them.
Drop in text, Word, PDF or images. Each chat has its own folder; point a chat at a project folder and it works there.
Python in a sandbox that can only write in the chat's folder. Packages install on demand.
Looks at your photos and screenshots. With images installed it creates pictures and edits your own photos, locally.
Keeps short notes on who you are and how you like answers, in files you can read and edit. Switch it off any time.
Download other local models that fit your computer from inside Joshua, keep them up to date, or pick a bigger cloud model for a chat.
A built-in API in the common OpenAI format lets your scripts, a robot or other apps use Joshua, tools and memory included, from this computer or your home network. How to use it
Goal mode works until a task is done and checked. Swarm mode asks several agents and merges the best answer. Scheduled tasks run on their own at set times, while Joshua is open and the computer is on.
The installer looks at your computer first: chip, graphics card, memory, free disk, and estimates how fast each model would run on it. It asks whether you want deep thinking, images and fine-tuning, shows the plan and the space it needs, and waits for your yes.
Then it installs Ollama, the engine that runs the models, a private copy of Python, Joshua and the models you chose, and offers to start Joshua when you log in, so it opens at once and scheduled tasks can run. On a Mac, Safari's File → Add to Dock then makes Joshua an app of its own, with its own window and Dock icon; on Linux it opens in its own window from the applications menu. Everything else stays in one folder, ~/AskJoshua, with an uninstall.sh that removes it.
Prefer to read before you run? Open install.sh: it is plain, commented shell.
| Memory | Model | Options |
|---|---|---|
| 8 GB | qwen3-vl 4B · about 3 GB | Deep thinking. Images are not offered: they need 16 GB. On a slow chip the 4B is suggested even with 16 GB. |
| 16–24 GB | qwen3-vl 8B · about 6 GB | Deep thinking, images (FLUX.2 klein), fine-tuning. |
| 32 GB+ | qwen3-vl 30B · about 20 GB | Everything, with a larger and smarter model if you want it. |
| Linux | chosen by the graphics card: 4B under 7 GB, 8B from 7 GB, 30B from 22 GB | Images from 12 GB, fine-tuning from 8 GB, on NVIDIA cards. Without a card, the 4B runs on the processor, slowly. |
Fine-tuning nudges a few of the model's billions of numbers with your examples, so it picks up a habit: a tone of voice, a format, your jargon. Joshua walks you through it in the Teach Joshua panel, explaining each step as you go. It runs on your Mac in 15 to 60 minutes, and your examples never leave it.
It teaches style, not facts. Train it on 200 answers about your company and it will sound like it knows your company, but it will invent the details. For facts, Joshua has memory, your files and the web.
joshua-<name>.The model has no memory of its own. Every time you write, Joshua sends it the whole conversation, and the model either answers or asks for a tool. Joshua runs the tool, adds the result, and asks again, up to 25 rounds.
Built with Ollama · qwen3-vl · FLUX.2 klein via mflux · mlx-lm · llama.cpp's converter · Gradio · anonymous search through ddgs. All open source.