Troubleshooting
The failures that actually happen, and what each one usually means.
A known-good run
1:17
What a healthy end-to-end session looks like, for comparison.
Start here
Run /help first — it reflects the exact build you have installed, which this page cannot. Then lk config show to see the configuration the CLI actually resolved, and lk whoami to confirm it is signed in — between them those cover most of what looks like a broken install.
lk: command not found
The package installed but its scripts directory is not on your PATH. This is the single most common problem, and it is not specific to Local Keep AI.
•
python3 -m pip show local-keep-ai-cli — confirms the package is installed.
•
python3 -m local_keep_ai — runs it without needing PATH, as a check.
•
Add the user scripts directory to PATH: usually ~/.local/bin on macOS and Linux.
•
If you have several Pythons, pip and python3 may not be the same install. python3 -m pip install ... avoids that entirely.
An editor integration cannot find the CLI
An editor launched from the Dock or Start menu does not inherit your shell PATH, so it can fail to find lk even when your terminal finds it fine. Every integration therefore lets you set an explicit path to the binary in its settings. Use the output of which lk.
A model will not load
•
Out of memory is the usual cause — try a smaller model. lk pull --list shows each one’s size.
•
A partial download reports as a corrupt file. lk pull <model> again — it will re-fetch.
•
Deleting ~/.sage/models/ is always safe; weights re-download on demand.
A session hangs
•
Ctrl+C interrupts the current turn without ending the session.
•
A long local generation is slow, not stuck — a large model on a small machine can take minutes.
•
If replies have started losing the thread, /compact is usually the fix rather than a restart.
Still stuck
Email info@localkeep.ai with the output of lk --version, the command you ran, and what happened instead of what you expected. Those three things resolve most reports without a second round trip.
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.