Jack Dorsey’s financial tech and media firm Block (formerly Square) has released a platform for building AI agents: Codename Goose. Previously available in beta, Goose is primarily designed to build agents for coding and software development, but Block built in many basic features that could be applied to general purpose pursuits. Because it is open source and offered under Apache License 2.0, the hope is that developers will apply it to varied use cases. A leading feature of Codename Goose is its flexibility. It can integrate a wide range of large language models, letting developers use it with their preferred model.

It can work with “pretty much any conceivable large language model (LLM) as the intelligence on the backend, whether that be DeepSeek or a proprietary model from the likes of OpenAI, Google or Anthropic,” reports VentureBeat.

It uses Anthropic’s Model Context Protocol (MCP), “which lets agents access data stores, developer spaces, and business applications” and “lets users connect new tools midway during a session (as opposed to delineating them at the beginning, as is necessary with closed-source tools),” writes ZDNet.

“You can be in the middle of a conversation, realize that you need to pull in something from your Google Docs or connect it to Slack or something, and you can just, say, click through, enable a new extension, and then goose suddenly has these new capabilities it can go run with,” Brad Axen, Goose’s lead engineer at Block, tells ZDNet.

Like the developer platform Blitzy, Goose can write code in real time, simultaneously “executing tasks autonomously — reading and writing files, running code and tests, refining outputs, installing dependencies, and handling additional actions as needed,” Block explains in a blog post on GitHub.

According to Block, Goose can do the following:

• Conduct code migrations such as Ember to React, Ruby to Kotlin, Prefect-1 to Prefect-2, etc.
• Dive into a new project in an unfamiliar coding language.
• Transition a code-base from field-based injection to constructor-based injection in a dependency injection framework.
• Conduct performance benchmarks for a build command using a build automation tool.

VentureBeat says Codename Goose’s move from beta to general availability marks “a significant step toward democratizing AI-powered systems for developers and beyond.”