aaif-goose/goose

This page introduces an external open-source repository. It is not an HDATF product.

What it does

goose is an open source AI agent that runs locally as a desktop app, CLI or API, for coding, research, writing and automation. It works with many model providers and connects to extensions via MCP.

How it helps ATF

Worth comparing with the executors Harness hands work to, since it runs the same agent through desktop, CLI and API entry points. Its MCP extension model could also be a reference for connecting tools to the ATF Works assistant.

License

Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.

More in this category

• openclaw/openclaw
  OpenClaw is an open-source AI assistant that runs on the user's own computer and works through chat apps such as Slack, Discord, Teams and WhatsApp. State, memory and credentials stay local, and models and agent harnesses are swappable plugins.
• vercel-labs/agent-browser
  agent-browser is a browser automation CLI for AI agents, built as a native Rust binary. It drives Chrome from Chrome for Testing and can detect existing Chrome, Brave, Playwright and Puppeteer installs.
• github/copilot-sdk
  GitHub Copilot SDK lets applications call the agent runtime behind Copilot CLI from Python, TypeScript, Go, .NET, Java or Rust. The application defines agent behavior, and the runtime handles planning, tool calls and file edits.
• frankbria/ralph-claude-code
  A tool that runs Claude Code in a loop to keep improving a project until complete. It exits only when completion indicators and an explicit exit signal both appear, and uses rate limits and a circuit breaker.
• Shubhamsaboo/awesome-llm-apps
  A collection of more than 100 open-source AI agent, agent skill and RAG app templates that work with models such as Claude, Gemini, GPT and Llama. The agent skills add abilities to coding agents like Claude Code and Codex.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.