Claude Code costs up to $200 a month. Goose does the same thing for free.
GetDeal Team
Contributor
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. But its pricing — ranging from $20 to $200 per month depending on usage — has sparked a growing rebellion among the very 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. No subscription fees. No cloud dependency. 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. The comment captures the core appeal: Goose gives developers complete control over their AI-powered workflow, including the ability to work offline — even on an airplane. The project has exploded in popularity. Goose now boasts more than 26,100 stars on GitHub, the code-sharing platform, 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. For developers frustrated by Claude Code's pricing structure and usage caps, Goose represents something increasingly rare in the AI industry: a genuinely free, no-strings-attached option for serious work.
Anthropic's new rate limits spark a developer revolt To understand why Goose matters, you need to understand the Claude Code pricing controversy. Anthropic, the San Francisco artificial intelligence company founded by former OpenAI executives, offers Claude Code as part of its subscription tiers. The free plan provides no access whatsoever. The Pro plan, at $17 per month with annual billing (or $20 monthly), limits users to just 10 to 40 prompts every five
Related Articles
Anthropic was illegally blacklisted by the Trump administration, court rules
On Thursday, a judge ruled that the Pentagon's blacklisting of Anthropic earlier this year was unconstitutional, delivering the AI lab a win in a monthslong rollercoaster of a battle with the Trump administration. The lawsuit, filed in March in a California district court, accused the Trump administration of unlawfully retaliating against Anthropic for setting "red lines," or unacceptable military use cases of its AI technology. "The empty invocation of national security is not a blank check to punish and retaliate against government critics," Judge Rita F. Lin, a district judge in the northern district of California, wrote in the ruling … Read the full story at The Verge.
Enterprise AI's real risk isn't autonomous agents. It's the complexity between them.
Presented by Gravitee Agent complexity is the insidious shadow lurking inside enterprises right now that needs a light shone on it. That’s because enterprises don't deploy a single agent and watch it run, they deploy fleets, each one calling APIs, calling other agents, reaching into applications that were never built with a machine decision-maker in mind. That's the failure mode that should keep you up at night: a windy, complicated system nobody can see clearly enough to govern. But why do things get so opaque so quickly? Add a second agent to a system, and you've added one connection. Add a tenth, and you haven't added ten connections, you've potentially added dozens, because now any agent might call any other, and each of those calls can trigger a call somewhere else. Complexity doesn't creep up with agent headcount. It compounds with the number of paths between agents, and nobody's job is to draw that graph. A support ticket that used to touch one system might now pass through four agents before a human ever lays eyes on it, and every one of those handoffs is a decision point nobody approved. Most enterprise AI programs stall when the humans responsible for their agents lose the thread. Ask a security team a simple question: which agents can reach which systems, and watch the silence. Ask which agent triggered which downstream action three hops ago. More silence. The instinct is to treat this like a checklist. Approve the agent. Log the agent. Move on. I'd argue this is the wrong instinct. A checklist checks a single point in time. Complexity runs across a chain, and you can't govern a chain with a stack of one-time approvals any more than you can call a diet successful because you had a vegetable once. So where does it actually break down? Permissions creep first. Somebody builds an agent to summarize support tickets, grants it broad API access because scoping it properly would've taken another sprint, and forgets about it. Six months later, that same agent h
Socure hits $5.2bn valuation on investment; buys AI fraud platform Fravity
Socure, the identity and risk intelligence infrastructure platform, has raised funding from investors including Goldman Sachs Alternatives and Wells Fargo at a $5.2 billion valuation. The firm has also acquired Fravity, an agentic platform that automates fraud, risk, and compliance operations.