Goose
ActiveDescription
Open-source extensible AI coding agent that goes beyond code suggestions — install, execute, edit, and test with any LLM.
Key Features
- Native desktop app — Native support for macOS, Linux, Windows desktop with full CLI and API interfaces
- 15+ model providers — Supports Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, Bedrock and more
- MCP extension ecosystem — Connect 70+ extensions via Model Context Protocol with custom tool support
- Rust high-performance core — Built in Rust for execution performance and cross-platform portability
- General-purpose AI agent — Not limited to code; supports research, writing, automation, data analysis and any task
- Custom distributions — Build custom goose distributions with preconfigured providers, extensions, and branding
Use Cases
💡 Daily office automation: Automate repetitive tasks like research, writing, and data organization with AI agents
💡 Software development assistance: Integrate via CLI into terminal workflows for code writing, debugging, and testing
💡 Cross-platform workflow orchestration: Orchestrate cross-tool, cross-service automated workflows in the desktop app
💡 Enterprise custom AI assistants: Build custom AI agents with enterprise branding and preconfigured tools via custom distributions
Strengths & Limitations
✅ Strengths
- • Actively maintained, recent updates
- • High community interest (53.9k stars)
- • Permissive open-source license (Apache-2.0)
- • Established track record (2 years in production)
Categories
Quick Start
# Install CLI
curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bash
# Start goose (will prompt to configure model provider)
goose session start
# Or download the desktop app
# Visit https://goose-docs.ai/docs/getting-started/installation