Open-source, extensible AI agent from Block that runs on your machine and orchestrates LLMs, MCP tools, and developer workflows.
Open-source, extensible AI agent from Block that runs on your machine and orchestrates LLMs, MCP tools, and developer workflows.
Goose is Block's open-source desktop and CLI AI agent — the same Block that owns Square, Cash App, and Tidal — released under Apache 2.0 and documented at block.github.io/goose. Unlike SaaS coding agents, Goose runs locally and brings its own LLM provider so you can plug in OpenAI, Anthropic, Google, Groq, Ollama, or any OpenAI-compatible endpoint. Its core differentiator is first-class Model Context Protocol (MCP) support: Goose calls extensions and tools as MCP servers, so the rapidly growing MCP ecosystem (filesystem, GitHub, Slack, browsers, databases, custom company tools) is immediately available. The desktop app provides a chat UI with rich tool visibility, while the CLI is designed for scripting agentic workflows in terminals and CI. Goose can edit files, run shell commands, browse the web, and complete multi-step tasks, with each step shown for inspection or interruption. Because the project is open source there is no subscription — costs come from whichever model API or local model you point it at. Common use cases include code refactoring across a repo, automating ops tasks, batch documentation generation, custom internal agents with private MCP servers, and as a reference implementation for teams building their own agentic UX on top of MCP.
Was this helpful?
Feature information is available on the official website.
View Features →$0
Ready to get started with Goose (by Block)?
View Pricing Options →Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
No reviews yet. Be the first to share your experience!
Get started with Goose (by Block) and see if it's the right fit for your needs.
Get Started →Take our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack →Explore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates →AI agents without memory restart from zero every conversation, wasting time and money. Here's how the three types of agent memory work, why they matter for your business, and which tools actually deliver results in 2026.
Deploy AI agents to production with confidence. Covers containerization, cloud deployment on AWS/Azure/GCP, Kubernetes orchestration, observability, cost control, and security best practices.
Running an online store means juggling product listings, customer questions, inventory, pricing, and marketing — all at once. AI agents can now handle most of it for you. Here's exactly how to automate your e-commerce business without hiring a team.
Compare GPT-4o, Claude 3.5 Sonnet, Gemini 2.0, Llama 4, and more for AI agent workloads. Covers tool calling, reasoning, cost, latency, and which model fits your use case.