Skip to main content
The cubic CLI reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them. The CLI syncs supported cubic cloud context, including custom agents, past feedback, and repository settings. CLI usage appears in your analytics dashboard as CLI sessions.
Do not expect identical results from cubic review and cubic’s cloud PR reviews. The CLI uses a different model and review pipeline, optimized for faster local iteration. Cloud PR reviews are more thorough and may find issues that the CLI does not flag.

​
Get started

Install the cubic CLI for your operating system.
Run cubic to open the CLI. The first launch opens your browser so you can sign in with your cubic.dev account, then you can start a review. If authentication fails, press Ctrl+L to log out and sign in again. cubic CLI home screen showing review preset options

​
Bring your coding subscription

The CLI includes a default model, with inference handled by cubic. You can also use your existing ChatGPT Plus/Pro or Claude Code subscription to review with more capable models.
Connect your ChatGPT account to use Codex models with your existing plan:
Sign in through the browser, then choose a Codex model in the CLI.
When you connect multiple providers, cubic selects the best available model by default. Press Ctrl+P to switch providers or m to switch models without signing in again. Run cubic auth logout to disconnect a provider; disconnecting Claude Code from cubic does not sign you out of Claude Code.

​
Choose a workflow

Use GitHub review by default. Add local review when you want an extra iteration before you push.
If you have not connected cubic to your editor, start with Connect cubic to your IDE.
Run a local review before you push, then use GitHub review as the final pass. Add this block after the GitHub-first workflow:

​
Command reference

Run cubic review without options to review uncommitted changes. cubic CLI review results showing prioritized issues Omit the branch from --base to detect it automatically. The --base, --commit, and --prompt options are mutually exclusive. Use --output-format text, json, or stream-json to select an output format explicitly.

​
Output formats

The default text output shows human-readable findings with colored priority labels.
Run cubic review --json when an integration needs one JSON object after the review finishes.
Run cubic review --output-format stream-json when an agent, CI job, or integration needs progress before the review finishes. The command writes compact NDJSON events to stdout, including finding updates, retries, heartbeats, and a final review.completed or review.failed event.

​
Advanced settings

The CLI checks for a newer version in the background whenever you run a command. When an update is available, the CLI installs it before running the command.Run cubic upgrade to update immediately, or cubic upgrade <version> to install a specific version.
Add disable_auto_updates to ~/.config/cubic/config.json to receive update notifications without installing them automatically:
Set CUBIC_DISABLE_AUTOUPDATE=1 to skip both the update check and automatic installation:
This environment variable is useful in CI, on machines without outbound internet, or when you need to pin a version.
The CLI installs git-ai to tag AI-assisted commits with git notes. These notes power the AI coding analytics dashboard. Attribution tracking is enabled by default, and git-ai shows an AI-versus-human authorship summary after each commit.Set CUBIC_DISABLE_GIT_AI during installation to skip git-ai:
Manage tracking after installation with cubic stats:
cubic stats disable removes git-ai hooks and preserves your preference during future upgrades. cubic stats enable reinstalls git-ai and clears the opt-out preference.

​
Limitations

CLI usage is unlimited during alpha, subject to rate limits that ensure fair access.