Skip to content
ProductArena

Rank #3 of 5 in Team Chat

Buzz logo

Buzz

Open Source Built-in AI assistant

Block, Inc.

buzz.xyz ↗Try it →
PA Score26/100AGENT-READY28/100BUILT-IN AI31/100API0/100
MCP~CLI✓API~
★ 32.5k▲ 63.2k/yr
ArenasTeam Chat#3/5

Access

CLI docs ↗MCP docs ↗

Compare head-to-head

Slack logovs SlackDiscord logovs DiscordMicrosoft Teams logovs Microsoft TeamsZulip logovs Zulip

Alternatives to Buzz →

Products

Block, product by product →

Block ships more than one product — each judged line competes in its own arena on the same stories as everyone else.

LineArenaRankPA Score
Square PaymentsOnline Payments#3/1043/100
Square Point of SaleMobile & In-Person Payments#2/432/100
Buzzthis pageTeam Chat#3/526/100

Not yet judged (3 — no arena where they compete): Cash App · Afterpay · Square AI

Try itExperimental

See what an agent can do with Buzz before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$curl -s https://raw.githubusercontent.com/block/buzz/main/LICENSE | head -3recorded session — replayed, not live
recorded 2026-09-10 · exit 0 · captured verbatim by our probe harness, secrets redacted · pure-HTTP probe — ▶ run live re-runs it from our edge

Verified integrations

No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.

By theme — the product's score on each story themeBy theme

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

23.3/100

App platform — stories about app platform in this arenaApp platformevidence →

Stories about app platform in this arena

0.0/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

15.0/100

Bots integrations — stories about bots integrations in this arenaBots integrationsevidence →

Stories about bots integrations in this arena

37.1/100

Calls huddles — stories about calls huddles in this arenaCalls huddlesevidence →

Stories about calls huddles in this arena

10.3/100

Channels threads — stories about channels threads in this arenaChannels threadsevidence →

Stories about channels threads in this arena

16.0/100

Compliance exports — stories about compliance exports in this arenaCompliance exportsevidence →

Stories about compliance exports in this arena

5.1/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

54.4/100

Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limitsevidence →

Free-tier ceilings, usage caps, and rate limits before you have to pay

n/a

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

0.0/100

Search knowledge — stories about search knowledge in this arenaSearch knowledgeevidence →

Stories about search knowledge in this arena

10.8/100

Workflow automation — stories about workflow automation in this arenaWorkflow automationevidence →

Stories about workflow automation in this arena

0.0/100

Story verdicts — every judged story with its evidenceStory verdicts

What’s free: 2 free · 0 paid · 0 enterprise · 23 not stated in evidence

?

Sorted by importance (agentic first) (high → low) · 51/51 stories · click a row’s chevron for the rationale and evidence

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial6/10T

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial6/10T

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial6/10T

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial3/10T

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10T

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial5/10T

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial5/10T

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial4/10T

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial4/10X

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial3/10C

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1noneuntestednone yet

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3fullfree8/10T

Add an AI agent as a member of a channel that participates in conversations when mentioned C

Ai agents

ai-native userBots integrations — stories about bots integrations in this arenaBots integrations3full7/10X

Have an agent read and post channel messages through the official API using scoped tokens C

Ai agents

ai-native userBots integrations — stories about bots integrations in this arenaBots integrations3partial6/10T

Organize conversations into public and private channels with membership controls C

Messaging model

team-adminChannels threads — stories about channels threads in this arenaChannels threads3partial6/10X

Build a bot that receives messages and events in real time through an events API or gateway connection C

Bot api

developerBots integrations — stories about bots integrations in this arenaBots integrations3partial5/10T

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3partial5/10T

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3partialfree4/10T

Start an audio or video call directly from a channel or DM without leaving the app C

Calls

team-adminCalls huddles — stories about calls huddles in this arenaCalls huddles3partial4/10C

Search the full message history with filters like sender, channel, and date C

Search

team-adminSearch knowledge — stories about search knowledge in this arenaSearch knowledge3partial3/10C

Build no-code workflows triggered by events, schedules, or form submissions inside the chat tool C

Workflow builder

team-adminWorkflow automation — stories about workflow automation in this arenaWorkflow automation3none0/10

Export the full message history of my workspace in machine-readable formats, including private conversations where policy allows C

Exports

team-adminCompliance exports — stories about compliance exports in this arenaCompliance exports3noneuntestednone yet

Install prebuilt integrations from an app directory or marketplace C

Apps

team-adminApp platform — stories about app platform in this arenaApp platform3noneuntestednone yet

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3noneuntestednone yet

Reply in threads so side discussions stay attached to the original message C

Messaging model

team-adminChannels threads — stories about channels threads in this arenaChannels threads3noneuntestednone yet

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2full8/10T

Catch up on busy channels efficiently because every conversation is organized under a named topic or thread C

Messaging model

team-adminChannels threads — stories about channels threads in this arenaChannels threads2partial7/10C

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial6/10T

Review audit logs of admin and user actions across the workspace G

Compliance

platform-engineerCompliance exports — stories about compliance exports in this arenaCompliance exports2partial3/10C

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2none0/10

Post a message into a channel with a simple incoming webhook URL C

Bot api

developerBots integrations — stories about bots integrations in this arenaBots integrations2none0/10

Share my screen during a call for live collaboration C

Calls

team-adminCalls huddles — stories about calls huddles in this arenaCalls huddles2none0/10

Build apps with rich interactive UI inside chat — modals, buttons, and structured message layouts C

Apps

developerApp platform — stories about app platform in this arenaApp platform2noneuntestednone yet

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Collaborate with external partners through guest accounts or shared channels with limited access C

External collaboration

team-adminChannels threads — stories about channels threads in this arenaChannels threads2noneuntestednone yet

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Enforce message retention policies and legal holds for compliance and eDiscovery C

Compliance

platform-engineerCompliance exports — stories about compliance exports in this arenaCompliance exports2noneuntestednone yet

Get AI-generated notes and recaps from meetings and huddles I attended or missed C

Ai notes

ai-native userCalls huddles — stories about calls huddles in this arenaCalls huddles2noneuntestednone yet

Get AI-generated summaries and recaps of channels and threads I missed C

Ai catchup

ai-native userSearch knowledge — stories about search knowledge in this arenaSearch knowledge2noneuntestednone yet

Keep my team on a free tier without losing access to older message history G

Pricing

team-adminPricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits2n/auntestednone yet

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Register custom slash commands that users invoke from the message box C

Apps

developerApp platform — stories about app platform in this arenaApp platform2noneuntestednone yet

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2noneuntestednone yet

Tune notifications per channel, keyword, and schedule so only what matters interrupts me C

Notifications

team-adminChannels threads — stories about channels threads in this arenaChannels threads2noneuntestednone yet

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1partial5/10C

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 46 stories with headroom

What would move Buzz’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools

    partialq3/10moves agent-readyimpact 31.5

    Missing: detailed docs on configuring/adding MCP servers, examples of tool usage via MCP, and community or hands-on validation.

  2. App platform — stories about app platform in this arenaInstall prebuilt integrations from an app directory or marketplace

    nonemoves PA Scoreimpact 30

    Missing: any mention of an app directory, marketplace listing, or one-click integration install flow.

  3. Workflow automation — stories about workflow automation in this arenaBuild no-code workflows triggered by events, schedules, or form submissions inside the chat tool

    nonemoves PA Scoreimpact 30

    Evidence shows Buzz has developer-oriented 'workflows' tied to CI/CD and code review (e.g., 'buzz workflows trigger/approve' CLI commands, 'run workflows' in agent capabilities) but nothing describing a no-code workflow builder for team-admins with triggers from events, schedules, or form submissions.

  4. Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models

    nonemoves PA Scoreimpact 30

    No evidence in the pack addresses AI training data usage or opt-out controls for Buzz; nothing discusses data being used to train models or a way to prevent it.

  5. Channels threads — stories about channels threads in this arenaReply in threads so side discussions stay attached to the original message

    nonemoves PA Scoreimpact 30

    Missing: any mention of a reply/thread UI or API, docs on thread creation, or community confirmation of threading behavior.

  6. Compliance exports — stories about compliance exports in this arenaExport the full message history of my workspace in machine-readable formats, including private conversations where policy allows

    nonemoves PA Scoreimpact 30

    Missing: export/download tooling, machine-readable format documentation, admin controls over private conversation export, compliance/legal-hold features.

  7. Agenticness — how well agents can access and operate the productPoint an agent at llms.txt or agent-oriented docs

    nonemoves agent-readyimpact 30

    Missing: an llms.txt or equivalent agent-readable docs endpoint, any mention of agent-oriented documentation standards.

  8. Agenticness — how well agents can access and operate the productSubscribe to events via webhooks

    nonemoves agent-readyimpact 30

    Missing: any documentation of a webhook API, subscription endpoint, or event push mechanism.

Showing the top 8 of 46 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map4 surfaces · 25 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

GitHub README25 stories

OpenAPI spec5 stories

Hacker News5 stories

llms.txt3 stories

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$curl -s https://raw.githubusercontent.com/block/buzz/main/LICENSE | head -3reproduced
$ curl -s https://raw.githubusercontent.com/block/buzz/main/LICENSE | head -3
                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/
proves: Read the product's source under an open licenserecorded 2026-09-10
$curl -s https://raw.githubusercontent.com/block/buzz/main/README.md | head -20reproduced
$ curl -s https://raw.githubusercontent.com/block/buzz/main/README.md | head -20
<h1 align="center">Buzz 🐝</h1>

<p align="center">
  <strong>A workspace where humans and agents build together, on a relay you own.</strong>
</p>

<p align="center">
  <a href="VISION.md">Vision</a> ·
  <a href="VISION_SOVEREIGN.md">Sovereign</a> ·
  <a href="VISION_PROJECTS.md">Forge</a> ·
  <a href="VISION_AGENT.md">Agents</a> ·
  <a href="ARCHITECTURE.md">Architecture</a> ·
  <a href="RELEASING.md">Releasing</a> ·
  <a href="LICENSE">Apache 2.0</a>
</p>

<p align="center">
  <img src="docs/assets/screenshots/channel-thread.png" alt="A Buzz project channel where people and an agent coordinate on a release plan" width="100%">
</p>
proves: Point an agent at llms.txt or agent-oriented docsrecorded 2026-09-10
$curl -s https://raw.githubusercontent.com/block/buzz/main/deploy/compose/README.md | head -8reproduced
$ curl -s https://raw.githubusercontent.com/block/buzz/main/deploy/compose/README.md | head -8
# Buzz Docker Compose deployment

This is the single-node/VPS deployment bundle. It is intentionally separate from
the root `docker-compose.yml`, which remains local development infrastructure.

## Quick start

```bash
proves: Self-host the core productrecorded 2026-09-10

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

7 of 9 testable claims verified · 0 contradicted → integrity 78/100

12 distinct capability claims found in Buzz’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

7

Verified

2

Unverified

0

Contradicted

16

Undersold

Verified (7)
Unverified (2)
Undersold (16)
Claims outside our story set (4)

Real capability claims found in Buzz’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • “Feature branches become dedicated channels combining patches, CI runs, code review and merge decisions as the project's record”

    source ↗

  • “All project activity (chat, code, CI) lives in one self-owned platform instead of stitching GitHub/Discord/etc together”

    source ↗

  • “Videos can be shared in-app with frame-anchored comments shown in a side panel”

    source ↗

  • “CLI supports configuring repo branch protection rules like push permissions, force-push and delete restrictions”

    source ↗
Suggest a story for these →

Business model

open-source

Free and Apache-2.0 open source from Block: self-host the whole workspace (Docker Compose relay + desktop apps from GitHub releases); no paid tiers or pricing page as of launch.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Scoretracked since Sep 10 '26 — no movement recorded yet
Agent-readytracked since Sep 10 '26 — no movement recorded yet

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

This page as markdown/llms.txt

Data

Evidence (JSON)Verdicts (JSON)