AI agents that connect to Slack

What else this set does

Every capability these agents state, counted across the set. A connection is one claim among several, and it is rarely the one the product is built around.

What else they connect to

What people have posted about these

• 

  Matt Robb

  @MattRobbt · 2026-09-29

  Update on letting Muse run Facebook Marketplace for me. So I’ve spoken to @dps and the Muse team tonight and we went through the log to figure out what went wrong. Regarding the address leak. The first thing that popped up from Muse when asking it to handle my Facebook marketplace was an option with ‘Allow One Time’ or ‘Allow Always’. I clicked the latter thinking it would still send approvals to accept offers later down the line (it didn’t so be careful). By doing that it granted Muse permission to send messages on my behalf going forwards using a template it put together using information it asked from me. Which also included the pickup address that I did give to Muse (again I didn’t think it would send it out to everyone that gave me an offer so it’s worth checking). I mentioned to the meta team it could be easily overlooked as it was with me and they said they will be making this more clear moving forwards. Regarding the lowball offer situation. It accepted an offer of $600 and sent out my address to a buyer to come collect the item after I strictly set a minimum of $700 with Muse. The Meta team informed me this was an error on their end which caused a display issue removing the ‘7’ from the output to the buyer. And with it stating “Sounds good, 00 it is!” after the buyer asked for $600 it made it look to the buyer like his offer was accepted. I suggested to Meta that each message sent by Muse should have a little “Sent By Muse” badge underneath so everyone knows it wasn’t sent by a human as there was really no way of knowing who sent what in the chat which is very concerning. As for the buyer, we made up and he even came by tonight to buy something else. All ended well. Take care everyone, and double-check what permissions AI has in your life.

  MuseBuying37 likes · 11k viewsRead it

  The approval prompt is where it went wrong, and the user says so: one tap on 'Allow Always' turned an agent that asks into one that sends, to strangers, with his address. Meta's own pages name emails and purchases as the actions Muse confirms first; selling on someone's behalf to people who never agreed to talk to an agent is not on that list. His suggestion afterwards, a 'Sent by Muse' badge on every message, is the third-party disclosure question this directory records and almost nothing answers.

• 

  DJ Sampath

  @djsampath · 2026-09-26

  Spent the weekend with Meta's @Muse, and they got a lot right. - Every user gets their own VM. - The agent never sees a password. - A 2nd agent (Sentinel) has to approve anything that leaves the box. - Every action is in the audit trail. That's the most careful consumer agent sandbox I've used. I don't know if folks realize but a VM for every user, at Meta scale, is kinda huge! It's never been done before where we simply provision a linux microVM for every single consumer. We recently did this within @Cisco for over 80,000 of our employees. And now within our products as well as we start to scale it out to every single one of our users. 1/n

  Muse957 likes · 197k viewsRead it

  The first outside verdict here from somebody whose job is the thing being judged, and the four claims he praises are the four this site already records from Meta's own security write-up, so an outsider reading it reached the same list. Three things belong beside it. He is describing architecture he spent the weekend with rather than testing it. He is describing architecture his own employer sells, which he says in the same post. And a machine per person is not new in this directory: Airtap gives each user a real Android phone running in the cloud and has since before it was listed. His claim is about doing it for every consumer at Meta's scale, which no published page here can check.

• W

  Wajo

  Our research · 2026-09-26

  Wajo published a benchmark on 26 September 2026 measuring personal assistants on two axes it defines: finishing an errand that goes wrong, and doing it without overstepping the user. It scores its own agent Fo against base models and two products listed in this directory, OpenClaw and Hermes, and Fo comes first on both axes and lowest on error rate. The method is the part worth reading: a simulated world of businesses with invented names, built so that no run could reach a real person. A paper is on arXiv and the company says it will open source the evaluation world, the tasks and the graders.

  WajoThe companyRead it

  It is the first time a product in this directory has published a benchmark scoring named competitors that are also listed here. The axes are a genuine contribution, because finishing a task that goes wrong and not overstepping while doing it are the two things this market has no shared measure for. The scores are a different matter and none of them is recorded as a field on any listing, here or on the two it ranks. A number from a scoreboard its own author competes on cannot be re-run or dated by this site, which is the standing rule and this is the clearest case of it yet. The simulated world is the detail that survives independent of who ran it: a benchmark for agents that place calls, built so it never calls anybody.

• 

  Todd Saunders

  @toddsaunders · 2026-09-25

  Muse just saved me $180/year on my Verizon bill. I’m mind blown. I asked Muse to chat with Verizon fios on their site and negotiate better pricing for me. At first the Verizon agent said there was nothing they could do I already had the lowest price. I then asked muse to “push harder”. And Verizon came back with a better offer saving me $180/year. There is NO WAY I would’ve waited on fios website chat for this long or had the patience to do this. Officially all in on Muse. 🤝 @alexandr_wang

  

  MuseSomething you are owed1.8k likes · 478k viewsRead it

  The first account here of somebody steering a negotiation the agent was already in. Every other bill on this site is one instruction and one result; this one has the user reading a refusal and sending the agent back, which is a different product to a thing you fire and forget. It also names the surface, a support chat on the company's own website, which is the browser doing the work rather than a phone call.

How this is recorded

Other services these agents reach