Documentation
Everything you need to install Local Keep AI, sign in, pull models, and drive a session from the command line — including the slash commands, shell escapes, and the SMS bridge.
Quick start
Three commands and you are working. Everything else in these docs is detail on top of this.
•
pip install local-keep-ai-cli — installs the lk command onto your PATH.
•
lk login — opens your browser once to link the machine to your account.
•
lk run — opens the interactive session. Ask it something.
The CLI is the product. The web app, the mobile apps and the ten editor integrations are all front ends onto the same lk command, so anything you learn here applies everywhere.
What Local Keep AI actually is
A coding assistant that runs models on your own hardware by default. Local models cost nothing to run, work with no network, and never send your code anywhere. Cloud models are available when a harder task is worth it, and the request is anonymised before it leaves your machine.
•
Local-first — 1,000+ open-weight models you download once and run offline.
•
No API key needed for local models. No subscription needed to start.
•
Cloud when you want it — GPT-4o, Claude and Gemini, with the request stripped of who you are.
•
Runs on macOS, Linux, Windows, iOS, Android and in the browser, and syncs between them.
Watch it working
Six recorded walkthroughs, unedited and in real time. Each one also appears on the page it belongs to, so you can read and watch together rather than choosing between them.
The CLI in depth
2:22
Fourteen chapters covering the terminal client end to end — install, models, sessions, slash commands.
The web app, end to end
1:17
Signing in, starting a conversation, and picking it up where the terminal left off.
Every slash command, demonstrated
2:06
Each slash command run in a real session, with what it actually returns.
Models, offline and private
0:48
Running local weights with the network off, and what that does and does not protect.
Files, sources and trust
1:04
Reading files into context, where answers come from, and how to check them.
On your phone
0:41
The mobile client doing the same work as the desktop app, on the same account.
Where to go next
Each page below is self-contained. If you are setting up for the first time, read them in order; otherwise jump to the one you need. Commands has a page for every one of the CLI's commands and slash commands; Editor integrations has one per editor.
All documentation
Installation
Install the CLI on macOS, Linux or Windows, and sign in.
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.