Back to timeline

Thu, October 1501:30Open SourceAPI & pricingMCP & SkillsOpen sourceAPI & pricing guide

goose Open-Source AI Agent Released: Desktop, CLI, and API

Decision Brief

What changedThe Linux Foundation's AAIF has open-sourced goose, a general-purpose AI agent available as a desktop app, CLI tool, and API.
Why it mattersWritten in Rust and supporting 15+ model providers, it offers dev teams needing local deployment and no vendor lock-in an embeddable open-source option.
Who should careOpen-source model users, Agent builders
Affected stackMCPClaudeOpenAIGemini
Builder actionUpdate MCP to the latest version
Source confidenceHigh · Official release / blog / repo

goose is a general-purpose AI agent that runs locally and handles not just coding but research, writing, automation, and data analysis. It ships as desktop apps for macOS, Linux, and Windows, a full CLI tool, and an API embeddable into other systems, written in Rust for performance and portability. It supports 15+ providers including Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, and Bedrock, usable via API keys or by reusing existing Claude, ChatGPT, or Gemini subscriptions through ACP. For extensibility, goose connects to 70+ extensions via the open Model Context Protocol standard. The project belongs to the Agentic AI Foundation under the Linux Foundation and lets teams build their own distributions with preconfigured providers, extensions, and branding. For teams building agent workflows, this avoids locking processes to a single model vendor; the CLI and API forms make it easy to integrate into existing terminal workflows or backend services. The CLI version installs via a one-line official script.

Summary basis: full article readCompiled from the source scope noted above; the original remains authoritative.

Sources

  • Skill Radar(GitHub 趋势)

    Trending hands-on MCP servers, agent skills, and AI-coding tools discovered from GitHub search momentum.

  • GitHub:aaif-goose/goose

Related intel

留言

登入后即可留言,和其他 builder 交换实测心得。

还没有留言,抢头香。