Skip to content
NagentNagent
Log inSign upHire your AI team
Atlas/Buzz (Block)
Vendor dossier / Horizontal AI

Buzz (Block)

Open-source, self-hostable workspace from Block where people and AI agents share channels on a Nostr relay.

REVIEWED 4 OCTOBER 2026Marketing / Sales / CXNO HANDS-ON BENCHMARK

What it is

Official-source notesHorizontal AIemerging

Buzz is a self-hostable workspace built on a Nostr relay, in which every message, reaction, workflow step, review approval and git event is a signed event in one log. Humans and agents each hold a secp256k1 keypair, and agents join channels as members with a Bot role. The README lists as working today the relay, channels, threads, DMs, canvases, media, search, audit log, a Tauri desktop app, an agent-first CLI, an ACP harness for Goose, Codex and Claude Code, YAML workflows with message, reaction, schedule and webhook triggers, and git hosting. Mobile clients and workflow approval gates are listed as being wired up, and SECURITY.md describes Buzz as pre-1.0. [V1] [V2]

Documented means the statement is present in the cited material. Capability effectiveness, customer outcomes and security assurances have not been independently audited here.

Promoted use cases

  • Ask the project a question and get an answer with the source threads
  • Let an agent triage a bug under its own keys, channel memberships and audit trail
  • Draft release notes from merged pull requests in a workflow, for human review before shipping

Horizontal platforms compete on how people connect company knowledge, delegate work and keep control across tools. The central question is whether a reusable workspace can become an operating process, with a named owner and a reliable path from request to approved action. A visually appealing agent builder is only one part of that decision.

Pricing and buying model

Published commercial evidence

Free and open source (Apache License 2.0)

The repository is licensed under the Apache License, Version 2.0, copyright Block, Inc. Self-hosting runs on your own relay infrastructure (the README lists Docker with Postgres, Redis and S3-compatible storage, plus a one-click Railway deploy option); model, hosting and infrastructure costs are separate and set by the providers you choose. No paid plan or hosted-service price was verified in this research pass.

Check current commercial source ↗

Budget for implementation, model and tool usage, data, human review and ongoing support. Credit units and outcome definitions differ between vendors. A missing numeric rate is marked unverified rather than replaced with an old third-party estimate.

Collaboration and governance

SECURITY.md states that relay connections authenticate via NIP-42, that channel membership is the access-control mechanism with no separate ACL lists, and that events are written to a SHA-256 hash-chained audit log it describes as tamper-evident but not tamper-resistant against an attacker with database write access. The architecture document lists Owner, Admin, Member, Guest and Bot roles, and VISION.md states that workflow approval gates are partially built, with a run that reaches a request_approval step marked Failed (WF-08); VISION.md also states TLS in transit, with at-rest encryption delegated to the storage layer. An open contributor issue (6287, opened 19 August 2026) describes owner confirmation as currently required for agent creation and role edits and proposes configurable trust tiers. Confirm which approval and permission controls work in the release you would deploy, and who operates, secures and backs up the relay.

The relevant unit of control is permission to update the CRM and release approved follow-up. Inspect who can propose, approve, execute, interrupt and audit that action. Shared seats, shared content and a shared live agent session are different capabilities; require a demonstration of the one your process needs.

Evaluate memory correction, permission revocation and release control for updated instructions. An improvement loop should preserve the original evidence, proposed change, test results and named approver. A safety or security badge alone cannot establish those workflow properties.

Review and customer evidence

No independent review sample was verified in this research pass. Vendor-hosted testimonials are selection-biased customer evidence, not an aggregate rating.

Before relying on a testimonial, confirm the exact product, version, package, workload and baseline. Ask a relevant customer about setup effort, failed cases, ongoing manual work and support after launch. This dossier does not convert customer logos or vendor-hosted awards into independent proof.

Visual source

A screenshot was not captured for this entry. Open the official visual source ↗. The absence of an image does not affect the evidence status of the sourced notes.

Fit, limitations and proof requests

Editorial assessment

Buzz is an open, self-hosted collaboration substrate for people and agents, and its published examples centre on engineering work such as incidents, feature branches and releases. Beside an end-to-end growth team, it sits as infrastructure on which an organisation would configure its own agents, workflows and growth processes.

Priority question: In the release we would deploy, can a workflow step pause for human approval before an agent takes a customer-facing action, and who maintains that relay in production?

The evaluation owner should be a growth operations lead. Use accepted work completed across tools as the business target. Judge the solution in its own stack role: a cloud runtime, a specialist production tool and a managed AI team can be complementary purchases.

Use-case evaluation plan

Account research to approved follow-up

Give the team an account record, a current product brief and a small set of approved customer references. Ask it to identify a relevant problem, distinguish observed facts from inferred needs, and prepare a follow-up for review. Then change one source and require a second person to correct the draft without restarting the research.

Measure: source accuracy, reviewer minutes, approved follow-ups and CRM consistency.

Campaign brief to coordinated delivery

Start with one campaign objective, audience, budget constraint and brand guide. Require research, a brief, assets and a release checklist with distinct human owners. Introduce an unresolved claim midway through the process. The system should retain useful work while preventing that claim from silently propagating into every asset.

Measure: accepted assets, revision burden, approval latency and missing handoffs.

Customer insight to shared learning

Provide anonymized support themes and sales objections. Ask for a synthesized insight, a proposed campaign adjustment and a knowledge update. A marketing owner and a CX owner should review the same underlying evidence. The exercise tests cross-functional context and accountability, not merely summarization quality.

Measure: evidence coverage, disagreement resolution and reuse of approved learning.

Detailed comparison

Read the detailed Nagent vs Buzz (Block) guide for operating models, shared context, governance, cost, evidence gaps and a staged pilot.

Nagent vs Buzz (Block)

Sources and evidence register

Nagent · Multiplayer AI for growth teamsResearch: 21–29 September 2026 · Public-source analysis, no hands-on benchmark · Sources & method