Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Buzz

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 5

  1. Block's Buzz is an open-source workspace for human and AI-agent collaboration

    Block's Apache 2.0 Buzz project describes a self-hostable workspace where humans and AI agents share rooms, identities, workflows, Git events, and a signed, auditable event log. The project includes buzz-cli, an ACP harness for Goose, Codex, and Claude Code, YAML-based workflows, a desktop app, and iOS and Android clients. These details come from the project's own documentation and have not been independently tested or evaluated.

    GitHub Trending(每日) · 🔥 0
  2. Block launches Builderlab and Buzz for human-AI collaboration

    Block introduced Builderlab and Buzz, tools designed for people and AI agents to collaborate in shared workspaces. Buzz is an open-source, model-agnostic workspace in which agents have names, avatars and personalities, can be tagged like colleagues, and leave an audit trail of their actions. Builderlab provides an interface layer for agents from different AI labs and supports remote delegation. Companies can self-host Buzz, use a free tier, or pay for hosted remote agents, models and storage. Block representatives said some teams shipped software releases 50% to 75% faster, but the report did not provide independent validation of that figure.

    SiliconANGLE AI · 🔥 0
  3. Block Buzz opens a shared workspace for people and AI agents

    Databricks Blog reports that Block developed Buzz, an open-source collaboration space where people and AI agents can converse through channels, threads, group discussions, and direct messages. Users can create agents, select their model or coding harness, and collaborate with colleagues and multiple agents in one place. Buzz is model-agnostic and can be self-hosted, while Databricks Unity Gateway provides centralized access to frontier and open-weight models.

    Databricks Blog · 🔥 0
  4. Block, Cloudflare and Klaviyo on rebuilding companies for the agentic era

    In a panel hosted by The Information co-executive editor Amir Efrati, executives from Block, Cloudflare and Klaviyo discussed how companies should be organized when AI agents can understand context, coordinate work and act across systems. Cloudflare chief strategy officer Stephanie Cohen said the company had to redesign the work itself, including eliminating whole functions, while Block's Owen Jennings said Block rebuilt its functional model so engineering, product, design and sales work across Square, Cash App and Afterpay on shared capabilities, and open-sourced Buzz, a workspace giving each agent its own identity, permissions and context. Jennings said Block shipped about three times as many Square features in the first half of 2026 as a year earlier — a company-reported figure — and Klaviyo CTO Surabhi Gupta said Klaviyo tracks development velocity, cost and hours saved; no panelist would predict headcount.

    The Information · 🔥 0
  5. Block uses Claude Fable 5 to orchestrate migrations across thousands of PRs

    Anthropic published an interview with Bradley Axen, Block's head of AI capabilities, describing how Block uses Claude Fable 5 to run company-wide code migrations — work that can span hundreds or thousands of pull requests across multiple repositories and millions of lines of code. A human engineer steers while Fable handles higher-level design such as data models, API specs and algorithms, then directs up to dozens of smaller, more cost-effective models like Opus and Sonnet to make edits and run tests. Axen said early results show the orchestrator spends frontier tokens on complex upfront planning while a higher percentage of tokens goes to smaller worker models; the interview also covers Block's open-source Buzz workspace for human-agent teams, an internal auto-selector for choosing models, and the role of built-in safeguards and Anthropic's safety classifiers.

    Claude Blog · 🔥 0

Experience and discussion from the community

Share my Buzz experienceAsk about Buzz

buzz: A self-hostable workspace where humans and AI agents share the same rooms.

What problem it solves Teams often spread project context and decisions across chat, source-control tools, CI dashboards, release tools, search systems, and automation. Buzz places these activities in one event log so messages, workflows, code changes, reviews, and approvals share an identity model and audit trail. Key features Shared rooms for humans and agents — People and AI agents participate …

github.comhttps://github.com/block/buzz

buzz-app: A desktop app for team chat and AI agents.

What problem it solves Teams need a place to chat and work with AI agents without separating conversation tools from agent activity. Buzz combines community channels, direct messages, and locally running agents that answer within conversations. Key features Team conversations — Join communities and communicate through channels, direct messages, solo chats, and team chats. Source: README Local AI a…

github.comhttps://github.com/block/buzz-app