11.1 Goose: Open-Source Alternative (Block)
For developers hitting Claude Code's subscription limits or needing model flexibility, Goose is a notable open-source alternative worth understanding.
What Is Goose?
An on-machine AI coding agent developed by Block (formerly Square), released under Apache 2.0 license. Unlike Claude Code, Goose runs entirely locally and is model-agnostic: it can use Claude, GPT, Gemini, Groq, or any LLM provider.
| Metric | Value (Mar 2026) |
|---|---|
| GitHub Stars | 33,000+ |
| Contributors | 400+ |
| Releases | 175+ since Jan 2025 |
| License | Apache 2.0 (permissive) |
| Primary Language | Rust (64%) + TypeScript (26%) |
Claude Code vs Goose: Key Differences
| Aspect | Claude Code | Goose |
|---|---|---|
| LLM Flexibility | Claude only | Any LLM (GPT, Gemini, Claude, Groq, local models) |
| Deployment | Cloud (Anthropic servers) | Local only (on your machine) |
| Cost Model | Subscription ($20-$200/mo) | Free + your LLM API costs |
| Rate Limits | Anthropic's weekly/5-hour caps | Your LLM provider's limits |
| Token Visibility | Opaque (no per-prompt tracking) | Full transparency |
| MCP Support | Native (growing ecosystem) | Thousands of MCP servers available |
| Setup Complexity | Simple (npm install) | Moderate (Rust toolchain, API keys) |
When to Consider Goose
Good fit:
- You're hitting Claude Code's weekly limits frequently
- You need model flexibility (e.g., GPT for some tasks, Claude for others)
- You require full cost visibility and control
- You work with large, multi-language codebases requiring aggressive refactoring
- You want offline capability (with local models like Ollama)
Poor fit:
- You want simplicity over flexibility
- You prefer fixed monthly cost vs. variable API billing
- You value Claude's specific reasoning capabilities and can't substitute
- You don't want to manage LLM API credentials
Recipes: Goose's Equivalent of Skills + Commands
Goose has a workflow primitive called Recipes: versionable, shareable, parameterized multi-step workflows. Unlike Claude Code's skills (which define agent capabilities) or slash commands (which trigger one-shot actions), Recipes define complete execution sequences: what to do, in what order, with which model at each step. They can be shared as deeplinks, imported by teammates, and checked into source control. Closest Claude Code analogy: a skill that chains multiple commands in a defined sequence, with state carried between steps.
Subagent Orchestration
Since mid-2025, Goose supports spawning specialized subagents within a workflow. A parent agent can delegate subtasks to subagents with different roles (Planner, Architect, Frontend Dev, Backend Dev), each potentially running a different LLM optimized for its task. This differs from Claude Code's Agent tool (which spawns a subagent with the same model). Goose enables heterogeneous agent teams where model choice is per-role, not per-session. See §9 for Claude Code's native multi-agent patterns.
Skill Portability
Both Claude Code and Goose support the Agent Skills open standard (agentskills.io). Skills you create with SKILL.md are portable across 26+ platforms including Cursor, VS Code, GitHub, OpenAI Codex, and Gemini CLI. Claude Code-specific fields (context, agent) are ignored by other platforms but don't break compatibility.
Trade-offs
| Goose Advantage | Goose Limitation |
|---|---|
| No subscription limits | LLM API costs can escalate unpredictably |
| Model choice | Requires self-managed API keys |
| Full token transparency | No built-in cross-session memory |
| Open source (contribute back) | Smaller user base, fewer tutorials |
| Offline with local models | Local models inferior for complex tasks |
Hardware Requirements
Goose itself is lightweight (Rust binary). The requirements depend on your LLM choice:
| LLM Type | Requirements |
|---|---|
| Cloud APIs (Claude, GPT, Gemini) | Minimal (just network access) |
| Local models (Ollama, etc.) | 16-32GB RAM, GPU recommended for larger models |
Quick Start
# macOS
brew install goose
# Or via cargo
cargo install goose-cli
# Configure LLM provider
goose configureSee Goose Quickstart for detailed setup.
Positioning
Goose is an alternative to Claude Code, not a replacement, and it comes with different trade-offs. The right choice depends on your priorities:
| Priority | Choose |
|---|---|
| Simplicity, Claude's reasoning | Claude Code |
| Cost control, model flexibility | Goose |
| Fixed monthly budget | Claude Code subscription |
| Pay-per-use, no limits | Goose + API |
For most developers already invested in Claude Code workflows, the switching cost is significant. Goose is most valuable for teams needing model diversity or developers frequently hitting Claude Code's limits.