AnjadheFour homes for the brain
Every AI feature in Anjadhe (chat, email insights, action filing, builds) runs on one model: the default entry in Settings → AI Assistant. That model can live in one of four places, and the choice is always yours:
- This Mac (the default). A free open-weight model like Gemma or Qwen running right on your Mac, through the app's built-in engine. Works offline, and nothing you ask leaves the machine. Local models are offered on Macs with 32 GB of memory or more, and that is what first-run setup installs there. Below 32 GB no local model is offered (the small ones didn't work well enough to keep), and setup suggests Anjadhe Cloud instead.
- A server you own. Any OpenAI-compatible endpoint you host:
llama-server, vLLM, LM Studio on a desktop or homelab box. Good when your Mac is light on RAM but another machine you own isn't. - An AI provider you trust, with your own key. The official OpenAI or Anthropic API, added as a model entry with an API key from your own account. This buys frontier-model capability that no local model matches yet, at the cost of sending what runs on that model to the provider.
- Anjadhe Cloud. An open-weight model hosted by Anjadhe, for Macs that can't run a capable model: no account, no key, and a free monthly allowance of AI requests while it is in preview. What runs on it goes to Anjadhe's server (api.anjadhe.com), which forwards it to an inference provider under a no-retention agreement, without your identity. Nothing is stored and nothing is used to train models; the service keeps usage counts, never what you asked, and its source code is public so that can be checked.
Every off-Mac option is an explicit choice. The app never falls back to a provider you didn't add, and your traffic goes only where you pointed it.
When a cloud model makes sense
Local models are offered only on Macs with 32 GB of memory or more. On an 8 or 16 GB Mac, Anjadhe Cloud is the no-setup option, with a free monthly allowance; when it runs out, requests pause until the 1st of the next month. If you already trust OpenAI or Anthropic with the kind of questions you'd ask a chatbot, bringing your own key gives the assistant a much stronger brain for exactly those conversations, while everything else about Anjadhe (your data on disk, sync, accounts) stays local and unchanged.
Two things to be clear-eyed about with your own key:
- What you run on that model goes to the provider. A chat that includes your briefing, or an email insights pass, sends that content to OpenAI or Anthropic under your account and their data terms.
- Usage is billed by the provider to you. Anjadhe adds nothing on top; you pay OpenAI/Anthropic directly at their API rates.
Adding a cloud model
- Open Settings → AI Assistant and click + Add model. The page lists the homes on the left: On this Mac first when your Mac can run one, Anjadhe Cloud first on a Mac under 32 GB.
- Pick Anjadhe Cloud, OpenAI API, or Anthropic API.
- Anjadhe Cloud needs no key: pick a model when more than one is offered (each shows a short description of what it's good at) and click Add. You can add several and switch between them. For OpenAI or Anthropic, paste an API key from your account (platform.openai.com/api-keys or console.anthropic.com/settings/keys), click List models to fetch the live list your key can use, and pick one (or type a model id).
- Test if you like, then Add model.
Make it the default (the radio on its card) and it becomes the brain for everything. You can keep local and cloud models side by side in the list and switch from the model chip in the chat box: a local model for everyday private work, a frontier model when you need the horsepower.
Keys are stored encrypted on your Mac, per model, and don't sync between machines; each Mac you use needs its own copy. The Anjadhe Cloud card's Manage panel shows how much of the monthly allowance is used.