Qodo CLI agent tool
> 📦 Package Renamed: This package has been renamed from @qodo/gen to @qodo/command.
> If you have @qodo/gen installed, please update to the new package name:
> ``bash`
> npm uninstall -g @qodo/gen
> npm install -g @qodo/command
>
Qodo Command is a command-line interface for running and managing AI agents.
It allows you to automate complex workflows, interact with AI models and external tools using your own tools and schemas, and serve AI agents as HTTP services — all from your terminal.
Qodo Command supports:
- Custom agent configuration
- CI and automation integration
- Interactive web UI mode
- General code generation
- Intelligent PR code review
It's fast, extensible, and designed to work in real-world engineering environments.
), exactly like Qodo Gen Chat.
- Custom Agent Commands: Configure your own agent and define reusable workflows (qodo ).
- Interactive Web UI mode: Run Qodo Command with --ui to interact with Qodo Command's chat in an interactive web UI.
- Serve Agents as HTTP APIs: Turn any agent into a callable service (--webhook mode).
- Model Control: Choose which AI model to use (Claude, GPT-4, etc.) with --model={model-name}.
- Agent to MCP: Turn any agent into an MCP with --mcp.
- Secure Integration: Use tools without exposing your API keys.Installation
To use Qodo Command, you’ll need Node.js and npm installed.
Then run:
`bash
npm install -g @qodo/command
`$3
Schema-driven analytics updates (no private registry required):
- Make schema or tracking plan changes in the Qodo-Event-Schema repo
- Open a PR there; after it’s merged to main, CI will generate analytics and automatically open a PR to this repo targeting the
This replaces the old flow that required GCP auth and private registry installs.
Go to the Qodo Command documentation site for full options and usage manuals.
Check out Qodo's agent repository on GitHub to see examples of working agents.