An open-source, extensible AI agent that goes beyond code suggestions to install, execute, edit, and test with any LLM.
goose is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view block/goose --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Goose is an AI assistant that can run on your computer and do tasks like installing software, editing files, running tests, and more. It works with different AI models and can be extended with new abilities. Think of it as a smart helper that can actually do things, not just suggest code.
Goose is an open-source, extensible AI agent developed by Block (formerly Square). It goes beyond traditional code suggestions by actively installing, executing, editing, and testing software using any large language model (LLM). Goose supports the Agent Communication Protocol (ACP) and the Model Context Protocol (MCP), allowing it to integrate with various AI agents and tools. It is written in Rust and designed to be safe, fast, and reliable. Goose can be used for a wide range of tasks including software development, system administration, and automated testing. Its extensibility allows developers to add custom skills and connectors. With over 46,000 stars on GitHub, it is a popular choice for developers looking to automate complex workflows.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 57 days ago.
46083 GitHub stars indicate community interest.
240 open issues signal maintenance load.
Apache-2.0 license detected.
Automate software installation and configuration across different environments.
Run and debug test suites for continuous integration pipelines.
Edit and refactor codebases based on natural language instructions.
Manage system administration tasks like file operations and process management.
Build custom AI-powered workflows by integrating with MCP-compatible tools.
Goose can execute arbitrary commands on your system; ensure you review actions before allowing them.
Using Goose with untrusted LLMs may lead to unintended behavior; always use trusted models.
46,083
Stars
4,770
Forks
240
Issues
Apache-2.0
License
Anthropic's official CLI agent for coding. Claude-powered terminal agent that reads, writes, and refactors entire codebases.
The leading open-source AI code assistant for VS Code and JetBrains. Connect any model, customize your workflow.
AI-powered web app generator — turn natural language ideas into full code with live preview and code explorer ｜AI 驱动的 Web 应用生成平台，通过自然语言对话生成完整可运行的代码，并提供实时预览与代码浏览
An open-source, extensible AI agent that goes beyond code suggestions to install, execute, edit, and test with any LLM.
Software developers who want to automate repetitive coding tasks., DevOps engineers looking for AI-driven infrastructure management., QA engineers needing automated test execution and reporting.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Goose can execute arbitrary commands on your system; ensure you review actions before allowing them. Using Goose with untrusted LLMs may lead to unintended behavior; always use trusted models.
Similar or complementary options to evaluate include Claude Code, Continue, evoke.
Jun 1, 2026
2 security/trust notes recorded.
Setup difficulty is 3/5.