+Pros
- Broad model support1 · 100%
- Large MCP extension surface1 · 100%
- Open-source agent runtime1 · 100%
G
Goose
byBlock (Square)listed Jun 3, 2026
Coding AgentsFreeModerate setupClaude Sonnet, GPT-4o (user-configurable)
Goose is Block's open-source developer agent, designed as a fully autonomous CLI assistant that can execute tasks using a rich set of tools including shell commands, file editing, web browsing, and code execution. Built by the company behind Square and Cash App, Goose emphasizes extensibility and MCP (Model Context Protocol) integration. It is one of the few major coding agents backed by a large fintech company rather than a pure AI startup.
Freshness note: AI-agent behavior can change after model releases, client updates, pricing changes, or new default settings. Use the aggregate score as a historical baseline and check recent reviews plus model/runtime context before deciding.
- Pricing
- Free and open-source; you pay for your own LLM API keys
- Model backbone
- Claude Sonnet, GPT-4o (user-configurable)
- Setup complexity
- Moderate setup
- Last reviewed
- Aug 10, 2026
- Recent signal
- 1 in 90 days
What reviewers consistently say.
Top pros and cons surfaced from 1 review. Counts reflect how many loaded reviews cite each point.
−Cons
- Configuration affects reliability1 · 100%
- Permissions need team standards1 · 100%
1 reviews.
Reviews from users with 6+ months of usage or long-running production context.
RE
Ruling Editorial — Engineeringfresh
1-6 months usage·local extensible agent workflows with MCP-connected tools·Aug 10, 2026
8.4/10
An open agent runtime for builders who value extensibility
Ruling editorial benchmark: Goose is a strong open-source option for developers who want a local agent across desktop, CLI, and API surfaces with broad model-provider and MCP extension support. Its place in the Agentic AI Foundation strengthens the portability and open-ecosystem case. The same flexibility creates setup and reliability variance, so teams should standardize providers, extensions, permissions, and evaluation tasks before treating it as shared infrastructure.
+ ProsOpen-source agent runtime · Broad model support · Large MCP extension surface
− ConsConfiguration affects reliability · Permissions need team standards
18 helpfulReviewed Aug 10, 2026
Similar agents.
Coding Agents agents you might also consider, sorted by aggregate score.
Claude Code
Anthropic · Usage Based
Claude Code is Anthropic's CLI-native agentic coding tool, running directly in the terminal with deep filesystem and shell access. It reads the entire codebase context and can autonomously edit files, run tests, and commit code — making it a favourite among power users who prefer a terminal-first workflow. Claude Code is widely regarded as the most capable agent for complex, multi-file refactors.
9.6/10 · 1 reviewsCompare
Compare goose with claude-code
Cursor
Anysphere · Freemium
Cursor is the most popular AI-powered IDE, built as a fork of VS Code with deep model integration across autocomplete, chat, and inline edits. It supports multiple frontier models and has become the reference point for all coding agent comparisons. Its CMD+K and Composer features enable both single-file edits and full multi-file agentic workflows.
9.4/10 · 1 reviewsCompare
Compare goose with cursor
Codex CLI
OpenAI · Usage Based
Codex CLI is OpenAI's open-source terminal-based coding agent, positioned as direct competition to Claude Code and Aider. Running in your local terminal, it can read your codebase, write and edit files, and execute shell commands with configurable approval modes. As OpenAI's answer to Anthropic's Claude Code, it's generated significant interest among developers already in the OpenAI ecosystem.
9.2/10 · 1 reviewsCompare
Compare goose with codex-cli