Block has open-sourced Berd, a desktop application that unifies access to multiple AI models and agents in one workspace, with conversation history stored locally on the user's machine.
Originally built for Block's internal teams, the tool is now available free under an Apache 2.0 license for macOS, Windows, and Linux, allowing anyone—including commercial users—to adopt, modify, and redistribute it.
What happened
Block, the company behind Square and Cash App, released Berd as open-source software under the Apache 2.0 license. The desktop application lets users work with AI agents across different models and tools in a single environment, with locally stored conversation history. It is available now for macOS, Windows and Linux on GitHub, and has reached version 0.6.2 with 91 contributors.
Why it matters
Berd was originally built for Block's own employees to standardize how they interact with multiple AI models and agents. By open-sourcing it, Block makes the tool available to any developer or organization—including for commercial use—reducing friction for teams juggling different AI systems and avoiding the need to switch between browser tabs or applications.
What to watch
The tool is desktop-first by design, running and storing data locally rather than in the cloud. This choice reflects Block's focus on letting users work directly with projects, local files, and agents on their own computers, which may appeal to teams concerned about keeping AI work and data on-premises.
Ask the AI about this article →
Block originally built Berd as an internal tool to solve a specific problem: its employees needed a unified way to interact with multiple AI models and agents without constantly switching between different applications. By open-sourcing the tool under a permissive license, Block is betting that the same friction exists for developers and organizations elsewhere, and that sharing the tool openly will build goodwill and community contribution.
The choice of a desktop-first architecture rather than a browser-based workspace reflects a deliberate design philosophy. According to Brad Axen, Head of AI Capabilities at Block, the value of Berd comes from "working directly with projects, local files, tools, repositories, and agents running on or connected to the user's computer." This approach appeals to teams that prefer to keep their AI work and data local rather than sending it to cloud servers, and it avoids the latency and security considerations of a web application.
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytime
Ask AI anything about this article. Q&As are published on this page for other readers too.
Anthropic is privately hoping to file for its initial public offering by the end of this month, targeting a ra…
Broadcom is reportedly seeking to borrow up to $100 billion in debt financing to support growth efforts at Ant…
As AI technology matures, the bottleneck in the industry is moving beyond semiconductor constraints like GPUs…
Elice Group, a South Korean AI infrastructure provider, announced the launch of the country's first AI data ce…
Tencent Holdings is receiving shipments of Nvidia H200 AI chips under a new Chinese policy that permits limite…
On August 12, AT&T's Chief Data and AI Officer said OpenAI models power about 25% of the telecom's total AI us…
