goose Guide
An open-source agent that connects model providers, MCP tools and repeatable recipes.
Last verified: · How we verifySuitable workflows
Developers automating local workflows with extensible tools and provider choice.
Limitations and billing
The client is free; external model providers and connected services may charge separately.
Capabilities we verified
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
Free CLI; model-provider or optional service charges. The cost of metered usage or an external agent can be separate from the subscription.
Check official pricing ↗Models & access
Choose a supported model provider or an ACP agent as the execution provider.
Official model information ↗Install and start the CLI
Use the official CLI installer and configure a supported provider before starting a session.
Installation command · macOS / Linux
curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bashOpen your project folder in a terminal, then run:
goose sessionAccount and authentication
Run goose configure to select your provider and its credentials.
Project configuration and tools
Extensions expose MCP tools; recipes capture repeatable workflows for later runs.
First task to try
Inspect a local project and connect only the tools needed for one bounded task.
Official configuration reference ↗Related CLI tools
All AI CLI tools →Project evaluation checklist
- Open a small, familiar project and confirm that your essential language tooling works.
- Give the agent one bounded change with an observable acceptance criterion.
- Review the diff, run the project’s checks and compare the result with your current workflow.
- Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.