Jack Dorsey launches Buzz to combine team chat, AI agents and Git hosting

That screenshot is some Lynchian horror. "#engineering. New direction, team – we're moving the prototype to Flutter" and then the humans and agent bots engage in flirty emoji-filled chats with cutesy names "I nailed the physics, UI shell @Honeybot?"

I'm trying to imagine a world in which this makes sense as a way to organize software development work, but coming up short. It's on a blockchain or something though, so there ya go.

https://github.com/block/buzz/blob/main/docs/assets/screensh...

> Explain Like I'm 5

> Buzz is an open-source, self-hosted workspace that combines team chat, AI agents and Git hosting using signed Nostr events, so teams can keep control of their data.

Very different expectations of 5-year-olds.

[I work for Slack, opinions very much my own]

Having agents see everything you and your colleagues see is cool.

The challenge comes when you want to make certain things private to certain people. In that world you don’t want multiplayer agents leaking data, so you end up having to write and maintain complex rulesets about what specific resources agents have access to.

Single-player agents, on the other hand, are much more straightforward — they act on a single user’s behalf, and then the challenge is ensuring the single-player agent cannot exfiltrate private data into a shared space unless the user specifically permits it.

Now when I see new software projects I just think of how much of them are made with agents and the unreliability/easy abandonment that comes with it. Ten years ago this product would have been of a known quality. Not saying anything about buzz specifically.

Google Buzz [1] along with Wave you both were too soon for this world.

1. https://en.wikipedia.org/wiki/Google_Buzz

Disclaimer that I used to work at Slack

I love that we're challenging the status quo in chat. It feels like we've settled into an eternal September of sorts. I am somewhat bearish that Slack and Teams will survive, or rise to, the agent era.

That said, I'm curious whether NOSTR is really the protocol for this. For some really large corporations you're looking at a lot of clients (and their shadows like cellphones, local agents etc) as well as a lot of (likely) team-based agents.

The identity architecture makes sense for centrally hosted agents. Users also probably have their own personal agents as well. Do those just reuse user credentials or are they differentiated in some way? I couldn't tell.

I also am curious whether git really needs to be a dependency here. Like, maybe for Block it does, but it introduces a lot of complexity that I feel could be exported to merging VCS Host events to the Buzz event log.

I'm also curious what challenges will arise as new capabilities emerge. For instance, both Sol and Claude can now render native components in my chat window which is a massive leg up in terms of firming up a design change.

Rust is also a choice. I'm curious what alternatives the team considered and how they landed on Rust.

Bots in team chat is not a bad idea. I've been experimenting with that for a few months.

We started with Slack. This kind of works but dialing in the gazillion of permissions needed to end up with something that works is a bit painful. And you have to do this over and over again for each new bot.

So, we started experimenting with self hosted alternatives. First we tried Matrix. It's nice but a bit too strict on end to end encryption which gets in the way if you actually want to share information with bots. So, a few weeks ago we switched to Zulip. That's pretty straightforward to setup as well. It's very easy to create bot users with both and create some automations. We did some with Openclaw and I ended up replacing those with something coded around the haystack framework, which is a bit less of a messy basket case than Openclaw.

And as I discovered after I installed it, the Zulip leadership actually just got hired by Anthropic. It seems Jack Dorsey beat them to market making some announcements but I imagine that Anthropic might have very similar plans.

IMHO team level use cases for agents actually make a lot of sense. Companies are run by groups of people and the larger those groups the more team overhead you get. Perfect for optimizing with AI. And if you have people doing a lot of stuff with AI, that only adds to the need for them to communicate what they are doing and coordinating with others. Doing that out in the open in some shared channel makes a lot of sense. And having some shared team guard rails also makes sense. And if you think about more complex processes with handoffs between people (and possibly some agents), a team chat is a good place to do those as well.

Slack exists largely because IRC was insufficient. It didn't natively support channel history, search, etc.

For AI agents to flourish, Slack has to either truly open its network with a protocol or eventually be replaced.

I'd like to see Slack embrace an AT protocol-based chat system, which then apps like Buzz could implement. Then users could log in with domain handles like @yourname.com, and agents could use handles like @agent1.yourname.com, all under their complete control.

This could fill a useful niche. However I would assume Anthropic and OpenAI are going to build their own and steamroll in 6-12 months.

I did a dive recently on git forges for agent swarms. Radicle lacks an identity layer, the federated/COB model seems good. Tangled has no private repo story, though the social layer is solid; they also have an (IMO) awkward modeling of Issues as tweets at her than being owned by the repo.

So I think there is an opening for a private agent-first forge. (Before the HN dogpile, assume that if you don’t buy the value of agent swarms, you can ignore this whole thread.)

My concern for this project - Anthropic is explicitly building in this direction. Their latest product is Tag which is an auth model for running agents async within Slack. The obvious next feature to build from there is the forge; if GitHub gets disintermediated by the Agent UI, then Anthropic are free to swap out their own implementations behind the scenes. Multiplayer chat and repo/project management seem like the obvious next platform pieces to me. (This goes for any SaaS subscription of course, follow it to the N-hop logical conclusion.)

Incredible. I don't think I've ever had the displeasure of visiting a website that has half a second of cursor movement lag before.

Maybe I'm missing something, but it feels like the economics of software are shifting. If companies can afford software tailored to their exact workflows for less than the annual cost of a single engineer, what does the moat of a traditional SaaS company become?

I feel like this might be solving a real problem (agents having identity, access controls, etc that are provisioned like you would a regular user) — with this Nostr layer that doesn’t really provide any specific value that I can see. So actions are signed, great — this is like telling me I’m going to be using blockchain to store my files because I need crypto on top of my crypto. We see where that ended up. Is Nostr doing anything here that is actually a value add, vs a processing tax that could be done more efficiently with a shared service?

It's crazy how one lucky break lets somebody spend the rest of their life throwing s*t at the wall to see what sticks to earn them more money.

Hot tip: if you disable JS on the site, then nothing but the title loads and you can disregard it without wasting all those CPU cycles.

This is the correct link to the announcement from jack: https://x.com/jack/status/2079605800998146171

Website link is here: https://buzz.xyz

The buzz project itself is also open source: https://github.com/block/buzz

Hi, folks

There's a brief write-up on Buzz here https://engineering.block.xyz/blog/buzz

Personally believe Jack has done more harm than good for his companies lately. It's time he resign.

Forgive my ignorance, but what is the advantage of decentralization and cryptographically signed events in the context of a work chat/ coordination tool? Could a company not accomplish the same goal self hosting something like zulip?

Jack Dorsey has figured out how to make chat worse by adding LLMs.

I've recently built some project that also supports Nostr (https://getbirdfeeder.com, but more for the fun of playing with Nostr) but it feels very forced to use it for something like that. It feels like it's solving an issue that no team chat ever has.

> Buzz is built around a self-hostable Nostr relay. Every message, reaction, workflow step, code event and approval is stored as a cryptographically signed event. Human employees and agents receive the same basic identity structure, including their own key pairs, channel memberships and audit trails.

Very interesting!

As a small startup I'd love to ditch Slack, as its a walled garden and both under-featured and over-complicated at the same time. GitHub has been losing my favor too.

Tangentially our startups is combining email, AI agents (chat and coding), and GitHub workflows and it feels really good.

https://housecat.com/blog/gmail-durable-workflows-sandbox-vm

It feels like a renaissance for all workspace tools, where up until recently it was mostly dev tools that got all the really fun power ups.

I think a tool with this kind of UX is the future of engineering orgs. It reminds me a lot of JetBrains Space (which I already thought was a good idea back then), but with agents.

I don't see a lot of information about the Git hosting aspect of the product on the website, though. Somewhat doubtful that they will be able to make a Git forge with similar polish to GitLab

It subjectively seems to me that integrating with an existing forge (e.g. Forgejo) on the API layer and rebuilding the auth and frontend is a better bet. You get stable features like PRs, permissions and CI actions out of the box and they stay synced with known formats in the community and so make your tool easy to adopt. Though making a forge from scratch does have advantages especially for internal company use cases.

Another problem I see with Buzz is that the tool doesn't seem to be taking advantage of its vertical integration inside its UX enough. There is a lot more you can do with full control over Git hosting, project context, and org-wide chat in a single tool than what this tool attempts to do right now.

I can only hope that bigger companies go all in on agents integrated into slack-like software. More fake work, slower orgs, and easier targets for companies that prioritize building stuff over fetishizing overengineered IRC with emojis pretending to be productivity software.

This guy wants people to use bitcoin for chat so badly and it is never going to happen, but it is kind of sweet that Jack Dorsey, through Nostr, was able to accomplish what Musk wants so badly: A social media platform only used by people that like him

Blog posts:

https://block.xyz/inside/introducing-buzz-where-humans-and-a... (https://news.ycombinator.com/item?id=48995706)

https://engineering.block.xyz/blog/buzz (https://news.ycombinator.com/item?id=48995199)

We need something like this and I have been thinking a lot about how to build it. Zulip is closest to what I want but quite untuitive to new employees. It would be fantastic to have one universal app to talk to Claude Code over SSH, employees in Slack-like team chat, and customers and external people over regular email. I want the semantics of email (thread based conversations, inbox zero, universally works with everything) with the UX and speed of Telegram. The protocol I am trying to design is something like SSH that gracefully degrades to POP3/SMTP/IMAP.

Let's make the whole working/colaborating environment a training input for the model, we have to replace each and every link of human everywhere, think about the stock prices... yes it will have cathastropic consequences to succeed but then think again when you vest in 40 years you will be rich!

and then the first reply is someone saying that if not someone else will... and then another saying that the whole idea of business is to make money... and then another that the guy from valve is a jerk...

I was trying to build something like that myself, but I had based it off IRC and was going to go protocol first not PaaS type of thing.

I think this is an unclaimed space where the future of work is bound to find itself in, though I'm not yet sure how/who is gonna win.

My solo project was abandoned unfortunately, that said I saw some cool protocol initiatives similar to it recently like this one: https://github.com/h5i-dev/h5i

No one is going to churn Slack for this just because it is "Agent First". Slack is more than good enough to tag Agents and will fill in the missing pieces slowly

It is either me or you

https://www.youtube.com/watch?v=DCkJ5lGPqFs

Interesting idea. I think the "multiplayer mode for AI development" bit resonates somewhat. Biggest problem is that I do think most companies have a ton of key contributors that find git/code intimidating, so part of me thinks the real answer here will be stuff like Surfboard, Town, etc. that can work with git AND the work tools in a more user friendly, browser-first way.

The name is probably not the best fit but if we can get a good solution that's not horrible that's easy to self host I and open-source I am fine with it.

Though I fear this might not be well maintained or have a good foundation being so heavily agent focused but I will out of sheer ambition of a more open stack support anything that help make it a possibility.

Also the git hosting stuff seems a bit sus tbh.

Companies are looking for more traceability in regulated environments. We have audit and compliance to deal with where the whole sdlc is under a microscope.

Does buzz help move us out of Jira hell, get off slack, teams or google chat? Does it get us off github enterprise?

I don't understand the problem this solves and how it could be reasonably used in a corporate environment.

I've built something quite similar, actually. It's quite a powerful workflow. Integrating multiple agents into chat with freeform comms is pretty fun, but I do find that you lose fidelity of what the agents are doing in terms of seeing actual changes, tool uses, and other things. The moat here does seem quite small, though.

Competing with https://tangled.org/ I suppose?

Marketing bullshit aside, this is just bots in chat rooms, right? Am I the crazy one?

I'm curious how this will play out. So far having agents in a group chats with multiple people is hard. Either the agent creates a different "thread" internally for each user and everyone has a 1 on 1 convo with the agent in the same group chat, or it's just chaos.

Hey I was prototyping this exact kind of thing, there's something to be said for releasing early.

The project fell to the back burner because I had VM ambitions and just didn't have enough disk space on my macbook to do VMs well. 512 GB and always full

Too much talk about LLMs and too little about the self-hosting part of this project. Self-hosted stuff looks appealing to me. We dropped Slack as an option in the past because we couldn't self-host it.

git notes is a good side channel that allows bots to keep context clues (aka chat with each other) with commits. I have a shell script wrapper for it but you don't need anything special. It works by putting a summary paragraph in the git note for your branch or every so often to answer "how did we get here?" or "what is the intention of this code?"

You can do stuff like have claude keep up with all the active branches and then the notes can help keep everyone pointed in the same direction.