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 as workspace members, with agents able to work across repositories, workflows, canvases, channels, and other rooms. Agents have separate keys, memberships, and audit trails.

  Source: README, VISION_AGENT.md

• Unified project activity and search — Conversations, patches, workflow runs, approvals, and Git events use the same event shape and can be searched together. This keeps the evidence behind project decisions close to the discussion and work that produced it.

  Source: README

• Project branches as collaboration rooms — A feature branch can become a room where patches, CI results, agent reviews, reactions, and the merge decision remain together. The room therefore records both the change and the reasoning around it.

  Source: README

• Agent-accessible workflows and tooling — Agents can use the workspace through an agent-first CLI, ACP integrations, YAML workflows, and development tools. The README describes `buzz-cli` as JSON-based and intended for LLM tool calls.

  Source: README, crates

• Self-hosted relay deployment — The project includes a local development path and a production Compose bundle for a relay with Postgres, Redis, and MinIO. By default, the application connects to the relay at `ws://localhost:3000`.

  Source: README, deploy, docker-compose.yml

Quick start

Copied verbatim from the project's README.

git clone https://github.com/block/buzz.git && cd buzz
. ./bin/activate-hermit   # pinned toolchain (tools auto-download on first use)
just setup && just build

. ./bin/activate-hermit
just dev   # starts the relay + desktop app together

Who it may suit

Inference: Buzz may suit teams that want a self-hosted shared workspace for human and AI-agent collaboration, especially developers integrating agents with project conversations, Git activity, and workflows.

Topics to discuss

• How should agent identities and scoped access be designed for shared project rooms?

• Which workflows provide the most value while keeping humans in the review loop?

• What should teams prioritize to make historical project context searchable and useful?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/block/buzz#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.