Getting Started
Get from zero to directing an AI coding agent from your phone in under five minutes.
1. Install the CLI
Install with a single command — no Node.js or npm required:
curl -fsSL https://longshothq.com/install.sh | sh
This downloads a self-contained binary and adds it to your PATH.
Verify the installation:
longshot --version
Alternative: install via npm
If you prefer npm, you can install globally (requires Node.js 18+):
npm install -g @longshot/cli
Or run directly with npx:
npx @longshot/cli
Prerequisites
- Git — your project must be a git repository
- Claude Code CLI — Longshot spawns
claudeas a subprocess. Install it from@anthropic-ai/claude-code
2. Initialize your project
Navigate to your project directory and run:
cd your-project
longshot
On first run, Longshot detects it's a new project and starts interactive onboarding:
- Single project — scaffolds a
.longshot/directory in the current folder - Multi-project — lets you pick subdirectories to manage as separate projects
Longshot creates a .longshot/ directory containing your project spec, task index, and history. If you're in a git repo, these files are auto-committed.
3. Open the mobile UI
After initialization, Longshot starts a local web server:
longshot
# Longshot running at http://localhost:3333
Open this URL on your phone (when on the same network) or in any browser. The UI is mobile-first — designed for thumbs.
To use a different port:
longshot --port 8080
4. Create your first task
From the Chat tab, describe what you want to build:
Tap Draft Task. The agent creates a task spec — a structured description of the work with scope, approach, and acceptance criteria.
Review the spec on the Tasks tab. You can:
- Refine — chat with the agent to adjust the spec
- Mark Ready — approve the spec and mark it ready for implementation
5. Start work
Once a task is marked ready, tap Start Work. The agent begins implementing against the task spec. You can:
- Watch progress in real time on the agent progress page
- Walk away — work continues in the background
- Queue up more tasks — they'll be processed one at a time
6. Review and approve
When the agent finishes, you'll see a Review Diff button. The diff page shows:
- Visual diff of all changes (what was added, removed, modified)
- Change summary — what the agent did and why
- Test results and checks the agent ran
- Acceptance criteria from the task spec
You can:
- Approve — commits the changes to git
- Reject — discards the changes entirely
- Fix — describe what needs changing; the agent makes targeted fixes
Next steps
- Set up remote access — control your agent from anywhere, not just your local network
- API Reference — explore the full API for programmatic access
- FAQ — common questions about security, data, and billing