Claude Code Costs Up to $200 a Month. Goose Does the Same Thing for Free.
The artificial intelligence coding revolution comes with a catch: it’s expensive. Claude Code, Anthropic’s terminal-based AI agent that can write, debug, and deploy code autonomously, has captured the imagination of software developers worldwide. However, its pricing — ranging from $20 to $200 per month depending on usage — has sparked a growing rebellion among the programmers it aims to serve.
Now, a free alternative is gaining traction. Goose, an open-source AI agent developed by Block (the financial technology company formerly known as Square), offers nearly identical functionality to Claude Code but runs entirely on a user’s local machine. With Goose, there are no subscription fees, no cloud dependency, and no rate limits that reset every five hours.
“Your data stays with you, period,” said Parth Sareen, a software engineer who demonstrated the tool during a recent livestream. This comment captures Goose’s core appeal: it gives developers complete control over their AI-powered workflow, including the ability to work offline — even on an airplane.
The Rise of Goose
The project has exploded in popularity, boasting more than 26,100 stars on GitHub, with 362 contributors and 102 releases since its launch. The latest version, 1.20.1, shipped on January 19, 2026, reflecting a development pace that rivals commercial products.
Developers Frustrated with Claude Code’s Pricing
To understand why Goose matters, you need to grasp the Claude Code pricing controversy. Anthropic, the San Francisco AI company founded by former OpenAI executives, offers Claude Code as part of its subscription tiers. The free plan provides no access whatsoever, while the Pro plan, priced at $17 per month with annual billing (or $20 monthly), limits users to just 10 to 40 prompts every five hours.
The Max plans, costing $100 and $200 per month, offer more headroom: 50 to 200 prompts and 200 to 800 prompts respectively, plus access to Anthropic’s most powerful model, Claude 4.5 Opus. However, even these premium tiers come with restrictions that have inflamed the developer community.
Goose: A Free Alternative
Goose takes a radically different approach to the same problem. Built by Block, Goose is what engineers refer to as an “on-machine AI agent.” Unlike Claude Code, which sends queries to Anthropic’s servers for processing, Goose runs entirely on a local computer using open-source language models that users download and control themselves.
- No Subscription Fees: Goose operates without any financial cost to users.
- Local Operation: Users maintain complete control over their data, which never leaves their machine.
- Model Agnosticism: Goose can connect to various language models, including those from Anthropic, OpenAI, and more.
Setting Up Goose
For developers interested in a completely free and privacy-preserving setup, the process involves three main components: Goose itself, Ollama (a tool for running open-source models locally), and a compatible language model.
- Install Ollama: An open-source project that simplifies running large language models on personal hardware.
- Install Goose: Available as both a desktop application and a command-line interface.
- Configure the Connection: Set up Goose to connect with Ollama and start coding.
Why Goose Matters
Goose is not perfect; it requires more technical setup than commercial alternatives and depends on hardware resources that may not be available to every developer. However, it represents a growing desire among developers for tools that respect their autonomy.
As the AI coding tools market evolves, Goose offers a unique value proposition: genuine autonomy, model agnosticism, local operation, and zero cost. For many developers, these factors outweigh the limitations that come with using open-source tools compared to premium offerings like Claude Code.
The fact that a $200-per-month commercial product has a zero-dollar open-source competitor with comparable core functionality signifies a significant shift in the AI landscape.
Developers can explore Goose further by visiting GitHub for downloads and installation instructions.