goose
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM observed · 2026-10-12
Health v2 · maintenance only
86/100
- Activity 99
- Release rhythm 86
- Longevity 56
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: 3
- age_days: 788
- days_rel: 12
- days_push: 9
- n_releases_24m: 138
Adoption not part of the score
55171 stars · 6407 forks observed · 2026-10-12
What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-21, confidence 0.97
Goose is an open‑source, extensible AI agent written in Rust that runs locally as a desktop app, CLI tool, and embeddable API. It connects to many LLM providers and supports extensions via the Model Context Protocol.
Use cases
- automate code generation, review, and testing with a local AI assistant
- run research, writing, or data‑analysis tasks through a conversational agent
- integrate an AI agent into CI/CD pipelines to perform automated workflows
- create custom extensions that let the agent interact with databases, APIs, or file systems
- use the desktop UI to manage sessions, recipes, and interactive tools
When to choose
- You need a local, privacy‑preserving AI assistant that can run on any OS.
- You want a single tool that provides a desktop UI, CLI, and API for the same agent.
- You require integration with many LLM providers and the ability to add custom MCP extensions.
- You prefer a Rust‑based, high‑performance solution with active community support.
When to avoid
- You need a cloud‑only service with managed scaling and no local installation.
- Your workflow depends on a specific proprietary AI platform without MCP/ACP support.
- You require a lightweight library rather than a full‑featured application.
Facets
application · maturity active
cli gui api-framework agent-framework artificial-intelligence developer-tools windows cli rust mcp acp extensible model-context-protocol agent-client-protocol ai-agents macos linux desktop
10 sources
- readme: https://github.com/aaif-goose/goose · fetched 2026-10-12 · fdbfddb8685d
- homepage: https://goose-docs.ai/ · fetched 2026-09-07 · c6bf6bb66e34
- site_page: https://goose-docs.ai/docs/quickstart · fetched 2026-09-07 · 5b70af9194a0
- site_page: https://goose-docs.ai/docs/category/guides · fetched 2026-09-07 · 1218ebf79bcf
- site_page: https://goose-docs.ai/docs/category/tutorials · fetched 2026-09-07 · 541c3eb30ffb
- site_page: https://goose-docs.ai/docs/getting-started/installation · fetched 2026-09-07 · 273d1d406726
- site_page: https://goose-docs.ai/docs/guides/context-engineering/using-skills · fetched 2026-09-07 · 1af30f876237
- site_page: https://goose-docs.ai/docs/tutorials/custom-extensions · fetched 2026-09-07 · a77e8eb37845
- site_page: https://goose-docs.ai/docs/guides/acp-providers · fetched 2026-09-07 · df02dc48b66d
- site_page: https://goose-docs.ai/docs/guides/recipes/session-recipes · fetched 2026-09-07 · a5a2d263d752
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| aaif-goose/goose | main | 86 |
| aaif-goose/goose-mobile | sdk | 63 |
For agents
markdown · JSON · MCP: product_card(name="aaif-goose/goose")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem