Block's open-source, provider-agnostic agentic CLI donated to the Linux Foundation AAIF. MCP reference implementation. Ships multiple releases per week. 33K+ stars, v1.28.0 released 2026-03-18.
68/100
Trust
33K+
Stars
2
Evidence
Videos
Reviews, tutorials, and comparisons from the community.
Goose Is Destroying Pi.dev and Claude Code
How Block’s custom AI agent supercharges every team, from sales to data to engineering
Goose: AI-Powered Developer Agent from Block
Repo health
10h ago
Last push
313
Open issues
3,073
Forks
401
Contributors
Editorial verdict
Best choice for teams who want a fully open, auditable, provider-agnostic agentic CLI that is not controlled by a model vendor. Linux Foundation governance adds institutional credibility. No published benchmarks and limited verified install data keep it in Tier 2.
Source
GitHub: block/goose
Docs: block.github.io
Public evidence
Goose donated to the Linux Foundation AI & Automation Initiative Fund as a founding member. Governance entirely outside Block or any model vendor — highest open governance standard in the category.
Provider-agnostic, extensible agentic architecture with MCP as the extension protocol. Open-source under Apache 2.0.
How does this compare?
See side-by-side metrics against other skills in the same category.
Where it wins
Linux Foundation AAIF founding member — governance entirely outside any model vendor
Provider-agnostic: any OpenAI-compatible endpoint, local models via Ollama
MCP reference implementation — deepest MCP integration in category
Ships multiple releases per week (v1.28.0 released 2026-03-18)
Block (Square/Cash App) institutional backing beyond typical OSS
Apache 2.0 license — enterprise-friendly
Where to be skeptical
No published SWE-bench or Terminal-Bench scores
Install volume unverified — Homebrew installs (~4,939/30-day) dwarfed by Claude Code's 8M npm/week
'Super jank' reputation in HN comments — UX roughness acknowledged
Institutional backing hasn't yet translated to adoption scale
Ranking in categories
Know a better alternative?
Submit evidence and we'll run the full pipeline.
Similar skills
Aider
91Open-source AI pair programming CLI. The only tool in the coding CLI category with a fully verifiable, independent download number: 191,828/week PyPI installs, 5.7M lifetime, 15B tokens/week (homepage stat). Multi-model, git-native, no vendor lock-in. v0.86.2 released 2026-02-12.
Claude Code
90Anthropic's official agentic coding CLI. Terminal-native, tool-use-driven, with deep file system and shell access. #1 SWE-bench Pro standardized (45.89%), ~4% of GitHub public commits (SemiAnalysis), $2.5B annualized revenue (fastest enterprise SaaS to $1B ARR). 8M+ npm weekly downloads. Opus 4.6 with 1M context.
Gemini CLI
86Google's open-source terminal agent with Gemini 3 models, 1M token context, built-in Google Search grounding, and the best free tier in the category (1K req/day). 97.9K stars, 444 contributors. SWE-bench Pro standardized 43.30% (#2 behind Claude Code).
Codex CLI
85OpenAI's open-source coding agent built in Rust. Terminal-Bench 77.3% (GPT-5.3-Codex), SWE-bench Pro standardized 41.04%. 3-4x more token-efficient than Claude Code, 60-75% cheaper per task. Free with ChatGPT subscription, sandbox-first execution, 619 releases in 10 months.
Raw GitHub source
Constrained peek so you can sanity-check the source material without leaving the site.
a local, extensible, open source AI agent that automates engineering tasks
<p align="center"> <a href="https://opensource.org/licenses/Apache-2.0" <a href="https://discord.gg/goose-oss" <a href="https://github.com/block/goose/actions/workflows/ci.yml" </p> </div>goose is your on-machine AI agent, capable of automating complex development tasks from start to finish. More than just code suggestions, goose can build entire projects from scratch, write and execute code, debug failures, orchestrate workflows, and interact with external APIs - autonomously.
Whether you're prototyping an idea, refining existing code, or managing intricate engineering pipelines, goose adapts to your workflow and executes tasks with precision.
Designed for maximum flexibility, goose works with any LLM and supports multi-model configuration to optimize performance and cost, seamlessly integrates with MCP servers, and is available as both a desktop app as well as CLI - making it the ultimate AI assistant for developers who want to move faster and focus on innovation.
Why did the developer choose goose as their AI agent?
Because it always helps them "migrate" their code to production! 🚀