Ross ROSS = Recommend OSS · open-source software intelligence for agents

aaif-goose/goose

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM observed · 2026-08-28

github.com/aaif-goose/goose · homepage · Rust · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

85/100

  • Activity 99
  • Release rhythm 86
  • Longevity 52
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 3.0
  • age_days: 740
  • days_rel: 12
  • days_push: 7
  • n_releases_24m: 137

Full methodology

Adoption not part of the score

53534 stars · 6117 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

goose is an open-source, extensible general-purpose AI agent built in Rust that runs locally as a desktop app, CLI, and API. It connects to 15+ LLM providers and 70+ MCP extensions, supporting skills, recipes, subagents, and security features like sandbox mode and prompt injection detection.

Use cases

  • automate coding tasks with an AI agent on my machine
  • use my Claude or ChatGPT subscription with a local AI agent
  • connect an AI agent to databases, browsers, and GitHub via MCP
  • run an AI agent headlessly in CI/CD pipelines
  • capture reusable agent workflows as shareable configs
  • run parallel subagents for code review and research
  • build custom MCP extensions for an AI agent

When to choose

  • you want a local, open-source AI agent with desktop, CLI, and API interfaces
  • you need flexibility across many LLM providers or want to use existing subscriptions via ACP
  • you want deep MCP integration with 70+ extensions and custom extension support
  • you need automation-friendly features like headless mode, recipes, and CI/CD usage

When to avoid

  • you only need a simple code autocomplete or inline suggestion tool
  • you require session fork/resume with ACP providers, which is not yet supported
  • you prefer a fully managed cloud agent rather than something running on your machine

Facets

application · maturity active

agent-framework mcp llm-inference cli developer-tools chatbot workflow-automation large-language-models developer-tools windows cli rust mcp-client acp coding-agent desktop-app recipes subagents open-source ai-agents automation command-line macos linux desktop docker

10 sources

Member repositories

RepositoryRoleHealth v2
aaif-goose/goosemain85

For agents

markdown · JSON · MCP: product_card(name="aaif-goose/goose")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem