Skip to content
TraeIDE

Search

Popular pages

No matching pages

Try a tool name or a topic such as pricing or MCP.

English

Factory Droid Guide

Factory’s terminal agent for implementation, review, custom agents and automated missions.

Last verified: · How we verify
Coding agentFactorymacOSWindowsLinux

Suitable workflows

Teams taking a local coding workflow into scripted tasks and multi-agent projects.

Limitations and billing

Rolling limits, extra usage and BYOK rules differ; Missions may require extra usage to be enabled.

Capabilities we verified

Agent workflowCLI surfaceMCPSkillsHooksBring your own keyParallel agentsCloud agents

This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.

Pricing & usage

See official pricing

Factory subscription, rolling limits and optional extra usage. The cost of metered usage or an external agent can be separate from the subscription.

Check official pricing ↗

Models & access

Use Factory’s available model pool or configure custom model credentials.

Official model information ↗

Install and start the CLI

Use the official installer for your OS; the npm package is another documented option.

Installation command · npm

npm install -g droid

Open your project folder in a terminal, then run:

droid
Official installation instructions ↗

Account and authentication

Complete browser sign-in, or use FACTORY_API_KEY for scripted execution.

Project configuration and tools

Use /settings, /droids and /skills to configure work. droid mcp manages external tools.

First task to try

Ask Droid to review a change, inspect its findings, then run a small approved correction.

Script usage

This example asks for a project summary. Tool permissions still apply; a prompt is not a sandbox.

droid exec "Summarize the project structure without modifying files."
Official configuration reference ↗

Related CLI tools

All AI CLI tools →

Project evaluation checklist

  1. Open a small, familiar project and confirm that your essential language tooling works.
  2. Give the agent one bounded change with an observable acceptance criterion.
  3. Review the diff, run the project’s checks and compare the result with your current workflow.
  4. Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.