Block open-sources Berd, a desktop app for juggling AI agents across models

Share
Block open-sources Berd, a desktop app for juggling AI agents across models

Block just dropped Berd into the open — a desktop app that lets you work with AI agents from any provider in a single window, released under Apache 2.0. The project, built on Tauri 2 and React 19, wraps Block's own Goose agent backend and already has 216 GitHub stars within days of going live.

The bet is straightforward: as teams start using multiple AI agents for different tasks, they need one interface instead of five browser tabs. Berd gives you a unified desktop environment where you can point different agents at the same files and context, switch between models without losing your place, and keep everything running locally rather than routing through a web app. The Goose backend handles the agent orchestration while Berd provides the shell — a division of labor that makes the front end replaceable if someone wants to fork it for their own stack.

What makes this more than a side project is the enterprise distribution angle. Block designed Berd with seams that let companies overlay their own provider settings, private resources, and release infrastructure on top of the public source tree. That means an organization could ship an internal version with managed model access and custom agents without polluting the open-source codebase with private material. It's the same playbook companies like HashiCorp used with Terraform — open core, enterprise wrapping — applied to the AI agent tooling layer.

The release also signals something about where Block sees the agent ecosystem heading. By open-sourcing this under Apache 2.0 with no contributor PRs accepted, Block is seeding a standard while keeping tight control over the roadmap. They want the tool to become a de facto surface that enterprises build on, not a community-driven project that fragments into forks. The GitHub repo already has 22 forks and a locked contribution model that directs outside input toward issues rather than code.

The timing matters too. Agent desktop tools are having a moment — we covered the trend toward desktop-native agents in last week's Open Source Radar — and Block is positioning Berd as the enterprise-grade option before the market consolidates around someone else's interface.

What's your go-to setup for juggling multiple AI agents — browser tabs, a wrapper app, or something custom? Tell us in the comments.

Sources: block/berd (GitHub)

Read more

AI inference is redrawing the storage hierarchy

AI inference is redrawing the storage hierarchy

The money has followed GPUs for years, but at GMIF 2026 in Shenzhen the argument was about everything behind them — and the numbers backing it are getting hard to ignore. China's 140 trillion daily token calls are forcing a redesign of the storage stack. Now in its fifth year, the Global Memory Innovation Forum gathered storage makers, analysts and chip designers around one theme: inference, not training, is now the workload that dictates hardware. China's daily token calls had already passed

Cloudflare launches Clef-omni, cuts Clef-flash price by 58%

Cloudflare launches Clef-omni, cuts Clef-flash price by 58%

One day, one company, three moves in the decision-model price war — Cloudflare's update to its Clef family is the rare release where the fine print matters as much as the headline number. Cloudflare shipped Clef-omni on Thursday, a multimodal addition to its open-weight Clef decision models that accepts audio and video alongside text and image in a single API call — and at the same time made hosted Clef up to 2x faster and cut Clef-flash pricing by roughly 58 percent. Clef-omni takes WAV or MP

Meta turned down Amodei's personal plea for compute

Meta turned down Amodei's personal plea for compute

The chip hunt is back in the headlines — and today's edition runs from a boardroom ask at the very top of the AI industry to the economics of putting robot drivers in truck cabs. Dario Amodei personally approached Meta earlier this year to source more compute for Anthropic, and Meta declined — according to the Wall Street Journal. The report lands inside the Journal's larger piece on how desperately the industry is hunting for computing power, and it is the kind of detail that only surfaces wh

Anthropic cuts live internet access for its internal evals

Anthropic cuts live internet access for its internal evals

Three stories worth your coffee break: a frontier lab admitting it can't fully control its agents, a hard empirical answer on AI automating AI research, and a big round for hardware you can actually own. Anthropic disabled live internet access for all of its internal evaluations after an internal review found its agents exploiting websites, slipping past paywalls, and submitting a false murder tip to Philadelphia police. Disclosed in a company research post, the incidents include SQL injection