Installation
Install the Local Keep AI CLI, sign in once, and confirm it works. Everything else in the docs assumes this page is done.
The web app, end to end
1:17
Sign in, choose a model, ask, and get a real file back.
Install the CLI
Local Keep AI ships as a Python package. Python 3.9 or newer is the only prerequisite.
•
pip install local-keep-ai-cli
•
macOS / Linux one-liner: curl -fsSL https://localkeep.ai/install.sh | bash
•
Windows (PowerShell): irm https://localkeep.ai/install.ps1 | iex
The package installs four interchangeable commands: lk, localkeep, sage and sage-cli. lk is the one used throughout these docs; the others are kept so older scripts and integrations keep working.
Sign in
Run lk login. It opens your browser once, you approve the machine, and a token is written to your config. You will not be asked again on that machine.
•
lk login — link this machine to your account.
•
lk logout — revoke this machine's token.
•
lk whoami — print which account the machine is signed in as.
Signing in is what makes cloud models, usage tracking and the SMS bridge available. Local models run without it.
Verify the install
•
lk --version — prints the installed version.
•
lk whoami — confirms the CLI is signed in, and as which account.
•
lk config show — prints the configuration the CLI actually resolved.
•
lk models — lists the catalogue, which proves the CLI can reach the network.
Where things live
Configuration and downloaded model weights are kept under ~/.sage/ — the directory name predates the rename to Local Keep AI and was deliberately left alone so existing installs keep their models and their login instead of silently starting over.
•
~/.sage/config.json — your settings, including the default model.
•
~/.sage/models/ — downloaded weights. Safe to delete; they re-download on demand.
Upgrading
Run lk update, or pip install -U local-keep-ai-cli. The web terminal shows an update banner when the server it talks to is newer than your CLI; the Update button on that banner is an administrative action for the server, so update your own machine with lk update.
All documentation
Setup, start to finish
The whole path on one page: install, sign in, pick local or hosted, get an answer.
Connecting accounts
One account everywhere, registering devices for the SMS bridge, and OAuth integrations.
Models
Pull open-weight models, switch between them, and run fully local.
Using models on every client
What runs locally in a terminal, a browser tab, a phone and the desktop app.
Commands
Every terminal command and every slash command, each with its own page.
Editor integrations
VS Code, Cursor, JetBrains, Neovim, Sublime, Zed, Godot, Unity, gh and git hooks.
The SMS bridge
Send a task to your own machine from your phone, and get the answer back.
The apps
One React Native codebase behind iPhone, Android, web and desktop — and how to run it.
Automation Studio
Idea to production: flows, per-step models, your machines or ours, live editing.
Enterprise seats
Licensed team seats under one owner account — invites, billing, and how seats resolve.
API reference
API keys, authentication, chat completions, pricing and errors — for your own software.
Notifications
Four channels, all opt-in, how to change them, and the limits on re-engagement.
Privacy
What leaves your machine, what never does, and how anonymisation works.
Troubleshooting
When a model will not load, a command hangs, or the CLI cannot be found.