I was a little surprised to see a Telegram integration rather than Slack or Teams, given Anthropic's enterprise-first posture. But then I looked it up, and it turns out Telegram dwarfs both, at around 1bn MAUs, vs 50m and 300m respectively! I had no idea - reminds me of the time I found out Snapchat has 2x the userbase of Twitter.
Iāve been using Telegram for about 10 years, and itās one of the few products that has consistently felt great the entire time. Itās fast everywhere: backend, mobile app, desktop app, all of it. Everything just works. Its sync is out of this worldāfluid, fast, and seamless across devices. You can use it on your phone, then move to your PC or laptop and continue instantly without friction. Unlimited message history and file storage are fantastic, and the bot platform is absurdly powerful. Itās boring in the best way, which is exactly what you want from a channel for interacting with your agents everywhere.
Telegram had always impressed me for the same reasons. They have constantly gotten worse since about 2022/2023 though. Dark patterns, pay gate, they lost chat history for some of my closest contacts including 15k+ lost photos, no support at all. Something changed in their product direction and I started moving all my chats to Signal.
Since we are apparently giving messaging platform reviews here, I feel exactly the same way about Microsoft Teams. It works great. It does everything I want. It doesnāt get in my way. 10 out of 10 keep up the great work guys!
> Since we are apparently giving messaging platform reviews here, I feel exactly the same way about Microsoft Teams. It works great. It does everything I want. It doesnāt get in my way. 10 out of 10 keep up the great work guys!
It looks like we found a high executive using company money to buy a product no one wants to use.
It's easy to promote Teams if your secretary is handling it for you and you don't need to suffer yourself.
The other possibility: Microsoft started an astroturfing campaign on HN.
Teams network connectivity is a plain joke. If you use suspend, or frequently change network, the thing will just never reconnect, even though you have VPN alive and all network applications perfectly running.
And the thing is just absurbdly sluggish, only display blurred grey lines instead of text in a meager attempt to look snappy.
I only use Teams for meetings and the calendar, and the occasional chat during a meeting. I find it totally fine and I don't really think about it much one way or the other. For reference I have a 2021 M1 Max with 64 GB.
Probably all managers and engineers working on Teams have similar copious amounts of memory and powerful CPUs on their devices and hardly use their own product. That would explain a lot
It honestly wasn't much different on my 2018 i5 Mini with 32 GB.
Maybe what sucks here is the experience of running it on Windows. Or maybe it sucks for large meetings? But I never have Teams meetings with > 40 people at this company.
When it is online, I agree with things asides from the "fast" part, actually. But many companies have a secondary service for async comms/chat when being Teams cannot be online, and compared to Slack.
Honestly can't tell if this is not sarcasm/rage bait.
Teams that has 3 different UI frameworks on every platform (but your best bet is the web)? With the Microsoft login that tends to loop forever redirecting to God knows where?
Back in the day, when I used to play pokemon go, there was a small local community and we would struggle to decide where to meet up for the daily raids because people would basically not respond (so as t not commit), or not know which gym each other meant exactly, nor give live updates when people moved around, etc. etc.
Then I joined a group from a bigger city where I commuted for work. They had a telegram group chat with two "channels", one for talking, one for bot posts. The telegram bot could be sent a single screenshot of a raid, and it would use OCR to automatically generate an interactive UI for that raid for everyone to see, with all the relevant info, and it would also clear itself up when the raid is no longer relevant. You could press buttons to say you were going, that you MAYBE were going, if you were late, and if you already started/done it, all in single clicks. Tons of options, tons of information, all live updated.
I was bedazzled. That feature singlehandedly removed all attrition from urban social gaming. And it was entirely grassroots. It made me try out making my own telegram bots, and yeah, you basically have the power to make a little app in chat form, even some that feel like CLI commands.
It's been OVER HALF A DECADE and I have yet to see a single other chat application have that degree of freedom where it comes to applications and bots. Some like discord even did whole ass 100% reworks of their bot AP to support the likes of slash commands, and still fall short. And there's none worse than Teams. Teams hates you. Teams spent the prior 2 years before this one basically pointing a gun to our heads telling us they were removing webhooks and pushing back on it whenever they repeatedly get told that's the most insane and dogshit idea ever. And they still did it. There's just no spark in Teams UX. No self-respect. It's a soulless product made entirely as a dumping place of "synergy" with other M$ products. It's reciprocal, I hate it too.
Oh and my local group never go into telegram because they didn't want a new app. It died, but I still kept playing after work without problem. It makes me wonder how fast Teams would die if it wasn't proped up by 365 and Azure subscriptions.
> we would struggle to decide where to meet up for the daily raids because people would basically not respond (so as t not commit), or not know which gym each other meant exactly, nor give live updates when people moved around, etc. etc.
This kind of thing is so common in groups of people, it's one of my pet peeves. My own family does this in our group messages when trying to make big decisions like who should host thanksgiving or where we should go for a family vacation.
I make it a point to just take charge and tell people that we're doing XYZ now. It usually either results in a decision, or gets the discussion going enough that I can do it again with new information.
That has roughly been my MO as well and it works great for groups where identities have settled.
But one has to keep in mind that, in our currwnt "more woke" times, if you go this way in a new group you run the risk of being labeled an array of things. So tread carefully there.
I wonder if Teams hates you, because they are doing the bidding of their actual customers (corporate decisions makers and purse holders), and those people's interests are not exactly aligned with the users'.
The problem is that these people holding the actual purse don't care enough about their subordinates' experience. They care about the price tag, and about compliance. Apparently the makers of Teams think about the same. None of them thinks in terms of lost productivity.
Yes, compliance is a big one. And it's not so much that they are actively hostile to user productivity (and quality of life), they just don't care enough.
I feel the opposite. I'm on Teams all day at work and have reluctantly opened Telegram recently to try a Claw despite having an account for years.
I've been surprised how little support there has been for Teams in the whole AI ecosystem. It seems all developers assume that the whole world is at startups working on Slack when most businesses are on Microsoft 365.
The main reason is just how hard it is to actually create anything that integrates with Teams. You have to jump through so meany hoops, wade through so many deprecated APIs, guess through so many half-way-wrong-by-now documentation pages.
After building a proof of concept, we decided that we will only continue Teams integration if anyone is going to pay serious money for it.
Compared to operating on text files (which is relatively very simple and something Claude Code is great for), I have a feeling it's kind of a disaster dealing with Microsoft integrations and the different file formats
Just the fact how much Microsoft lies when you click the "keep me logged in" button should tell you why nobody bothers with Teams integration with anything.
Odious is one of the most reserved words you could use to describe Telegram, which is primarily a host for scams that the influencers and other bottom feeders aren't allowed to monetize on the big social networks.
Telegram's bot API is literally one of the friendliest APIs (of any kind) I've ever seen. It's the first thing I reach for when server-to-mobile notifications are concerned.
It's just as easy to set up as ntfy.sh, except that it doesn't break every other week on iOS.
This is so true. I donāt like Telegram for a host of reasons, but the bot architecture is second to none. Try creating a bot in Slack. Youāll pull your hair out for hours. Same goes for Discord. Utter nightmare. Telegram? You send a DM and it is basically done.
Discord webhooks arenāt too badā¦ but the proper bot thing is ridiculous. They really lack a development mode server, having to know everything about oauth and token permissions before even starting is bonkers and why do I even need an app is beyond me. Iād probably have my bot completely implemented in telegram in the same time I figured out what an app is in discord and how to even add a new app to my server.
Slack (and Discord) webhooks are good for just shooting one-sided data into channels, but for interactive bots Telegram is so far ahead of anyone else it's crazy.
Signal specifically is missing any kind of official bot support, cutting off massive audiences from even considering it as an option.
I think it might because telegram integration it's just easy to do, I don't use telegram for actually messaging, I use it just to deploy my bots, it's a simple way to build simple tools, in a few lines you can get something working, you can have commands that work like buttons, accept images, respond with images and don't need anything else than your telegram account
It's not even funny how a multibillion-dollar company with thousands of employees having unlimited access to the "world's best coding models" lags behind a small one-man [1] open source project that already had multiple plugins for the same feature [2] for months.
Pi already has 700+ third-party packages [2] for various purposes of various quality. But it doesn't matter, since creating a new working Pi extension to suit your needs is just a prompt away, and you don't even have to restart your coding session.
Surprisingly large number of businesses run on whatsapp, as a consultant in Asia it's prob around half the businesses I've worked with prefer it over teams/slack. If Meta had been sensible about API access Telegram wouldn't have even got a foothold.
WhatsApp is actually more popular than Slack, isnāt it? In my country, almost everyone uses Slack, and Iāve hardly ever heard of any companies using WhatsApp, so that was surprising to me.
Living in Japan has made me realize how different cultures can be ā even down to the apps and services people use.
It honestly surprises me, and now I kind of want to try WhatsApp too.
Honestly Whatsapp is nothing special. It works well, just like many other chat apps nowadays. The interest is that in some large parts of the world, everyone uses it already.
The only thing it's that creating bots for whatsapp it's not as easy as for telegram and it cost money. Actually that is the business plan for whatsapp making money from whatsapp business
Getting an agent working via an existing Slack setup is fairly effortless and the control over output format is useful
I had a look at getting same agent up in WhatsApp but it seems to need FB business acc to even start process, to get FB business you need an FB personal etc. ... looked like too much effort
Telegram has the best programmatic integration. Trivial to get working. You can be up and running in minutes. I use it to talk to a claw-style agent and it's truly unbelievable what you get for free.
Apples and oranges comparison, one is a messaging app, the other two are used for communication and collaboration across teams in a workspace. I have worked in 5+ companies who used either Slack and Teams, none used Telegram for any comms.
Telegram is 'bot friendly' since the beginning, gaining a lot of users with crypto boom a decade ago with coin drops and things like that, so it is very good to develop for, but I have your initial sentiment first - shame this hasn't launched with tools people actually use for work.
One issue is that 95% of the integrations will be fine with the default configuration. The others including some with high profit potential will have weird configs that will frustrate your customers the first time they try if not well tested/documented. It's better to take time and get it right. Enterprise customers love piloting and spending time, so best to approach that the right way too. Going with less complex options, that arguably have better APIs, makes it easier to develop your core product too and get real feedback from users.
I'm bullish on Claude. It will see a surge in users, and will likely surpass Perplexity this year. However I don't think it will catch up to even Meta AI (which had 10x the number of users) this year.
I use Claude. I use Codex. I've never heard of or used Meta AI. Nor do I have a Facebook account. Never have, never will.
I am also a software developer. So while the numbers of "people" that use one AI or another may be higher than either of these, it's not a useful metric for myself.
That's fine. I'm not making a value judgement about which LLMs you should use, if any.
I'm only pushing back against someone thinking "oh HN talks about Claude a lot, therefore Claude must be extremely popular". The information bubble is a real problem.
It's probably true that Anthropic's revenue is booming. But we need massive grains of salt:
a) they are private and revenue numbers for private companies are hopelessly unreliable, and
b) they are planning an IPO, so there's an extra incentive to big up the numbers. Anthropic always brings up ARR, which is very gameable when the year hasn't ended yet
Talk about a bubble. No one outside of programmers know what the heck is Claude. In Asia, ChatGPT and Gemini dominates LLM usage, followed by Perplexity.
Microsoft released a report with some numbers on Deepseek adoption globally. They say it's got ~90% market share in China, and is growing in popularity across Africa.
Telegram is more popular among "normal people", and it also has a laissez-faire attitude towards bots and bot development. Making a bot that you, or even other people, could add to their contact list and use is pretty easy.
It's wild, but "people who want to build and run their own one-off bot for something like home automation" are almost treated by Telegram like first class citizens.
Not really a meaningful comparison. Telegram is a personal messenger while Slack and Teams are for work. Telegram should be put alongside WhatsApp, iMessage, WeChat etc., which all have user bases in the billions.
You're telling me that Anthropic, one of the hottest companies on the planet right now couldn't field four teams of developers to integrate with Discord,
Slack, Telegram, and Teams? AI being such a productivity multiplier, seems like they could just choose to do it all. I mean, mythical man month and all that, but do it three times and have a retrospective and use Claude to refactor the pain points and centralize the learnings.
Telegram has a major issue with bots and bad actors though. They paywalled privacy features making it truly a terrible experience for users. 3-10 per day random messaging you.
This is actually great for *claws. When Anthropic changed their T&Cs to disallow using claude code oauth tokens in the Anthropic Agent SDK, you had a choice between violate the terms or pay a lot more for the model inference using an API key from platform.claude.com instead of claude.ai.
With this change, it looks like an officially sanctioned version of *claws. Connecting to whatever "channels" you want via MCP.
Architecturally it's a little different, most *claws would call the Agent SDK from some orchestrator, but with claude channels the claude code binary starts the MCP server used to communicate with the channel. So it's a full inversion of control where Claude code is the driver, instead of your orchestrator code.
I updated my nanoclaw fork to start the claude code binary in a docker container on PID 1, and you can read the docker logs straight from claude code stdout, but with comms directly to/from your channel of choice. It's pretty neat.
Claude is leaning into the idea of a local "session" being the host where everything connects.
I guess this makes sense for now. You can build integrations leveraging the user's personal access credentials. Later, once Claude takes over the world, they can move sessions to live in their own walled garden.
They certainly are. And this is likely to some degree a response to enterprise security desires. Enterprise endpoints are locked down already - no need for extra external API security if itās just the userās desktop communication as usual.
I feel like this is absolutely not the case. Our corporate infosec guys are freaking out, as developers and general users alike are finding all new ways to poke holes in literally everything.
We're finding out quickly that enterprise endpoints are not locked down anywhere near enough, and the stuff that users are creating on the local endpoints is quickly outpacing the rate at which SOC teams can investigate what's going on.
If you're using Claude via Anthropic's SaaS service it's near impossible to collect logs of what actually happened in a user's session. We happen to proxy Claude Code usage through Amazon Bedrock and the Bedrock logs have already proven to be instrumental in figuring out what led a user to having repeated attempts to install software that they wouldn't have otherwise attempted to install - all because they turned their brains off and started accepting every Claude Code prompt to install random stuff.
Sandboxing works to an extent, but it's a really difficult balance to strike between locking it down so much that you neuter the tool and having a reasonable security policy.
> If you're using Claude via Anthropic's SaaS service it's near impossible to collect logs of what actually happened in a user's session.
If you are big into logs, OpenAI might be more your speed. They've got an extremely good logging UI in their platform web app. I use it all the time to figure out what the hell copilot was thinking.
Look, as a software dev myself, I really like that my company lets us use our computers the way we see fit. Pre- or post-AI with no restrictive lockdown. Been there, hated that.
But I totally get the freaking out over "normal devs". The amount of stuff most people think is reasonable, AI or not, is mind boggling. For myself of course I like to just be able to be responsible myself. But as a security team I'd also be freaking out.
Like, the amount of people that find our super boring, totally corporate "security training videos", helpful and insightful and "oh dang I'd never have thought of that!" is mind boggling all by itself. Never mind any actual security training that'd be useful to someone with half a brain. You can literally just click through the 8+ hours of stuff you're supposed to watch / answer / do in 30 minutes.
It can. Go to the code tab, choose your repo, and have it write an image file to disk. If you tell it to read it, it should show in the chat. It works on the web version so hopefully it works on ios.
thats how Amazon worked its MCP setup - got everything onto oauth tokens, and then the harness knows how to to access the token to get permissions to whatever the user has.
the bad part is setting separate permissions for different user tokens
What these 'channels' do is essentially why I was running a nanoclaw at work: triggering a claude code based on events and getting feedback/review/analysis which nicely closes the loop with other agents.
Not sure why it has to be an mcp, but will be trying this out asap.
I'm using `pi` as my agent and build my entire agent orchestration on like 4 skills to start / stop / capture / await a set of tmux-bash & tmux-pi sessions.
This is the first time in a few months I might actually try `claude` cli again to try out this channels scheme.
Iāve been using opencodeās server command as a systemd unit on my home server. I connect to it with the desktop and mobile client. Use it for a bunch of openclaw-esq things, but with a nicer interface.
I think CC does have āremote controlā now which I think would work similar, but itās Max only right now
I tried various solutions around this. CloudCLI (ex claudecodeui) looked promising, but very buggy (disconnects, UI overlapping text, etc). Tried Claude Remote Control as well, but also very buggy, websocket disconnecting, UI broken.
I ended up just running Claude code in a dtach+ttyd session. Still not the best, as xterm.js has tons of issues with long scrollbacks, but it's at least somewhat _usable_.
Hello Galanwe, CloudCLI author here. This is a fair criticism and something we are actively working on. The older versions had real issues with websocket stability and the chat ui. We shipped a pretty big refactor yesterday that should fix most the disconnects and page rendering issues. Would be worth another look if you have a few minutes.
If you hit anything else, feel free to reach out to me personally (email in my hn profile) or via the discord channel we have. Always useful hearing from people who actually tried it and ran want to make it better
I am not sure how I feel about all these hype-driven tools honestly, especially considering they are super janky since probably rushed out with Claude Code.
It reminds me that I don't really like Anthropic as a company, I just like Claude as a model a lot. It just feels more capable and personable than the others. I wonder if / when OpenAI et al. will be able to replicate it.
For now, I basically have no choice but to use the walled garden but I do hope Anthropic is not completely compromising their core mission of actually making the model better rather than following these public bandwagons.
Then again most of these probably take them like a day to develop through a junior dev talking to Claude Opus 5 or some shit lol (and to be fair, it shows). I don't know.
I just created agent-http that leverages the channels feature to enable you to wrap claude code with a http api. This provides an identical API to Agent API (https://github.com/coder/agentapi) that relies on terminal scraping to achieve this. Now you can interact with claude code in a headless manner using your subscription. Previously I think you had to do this via the Agents SDK which relies on api token use.
Maybe it's less risk for them to offer the individual features. That way if people get inadvertent results, it's easier to blame the user, not the tool/company
All *Claw implementations should use a local model for heartbeat, it doesn't need to do anything complex, pretty much just read a text file and do a true/false decision if there's something in there to do when it wakes up.
If so, it can either just shove the full heartbeat file to a smarter model or try to intelligently spread the tasks to the correct models.
I was reading through CC MCPs docs ... MCP Notifications kind of did this right? The server/client could update each other automatically. So there was already this channel-like communication.
This is like that but instead of the server/client sending messages it's you.
at this point anthropic is dogfooding us a new product every week just to see what might stick - doubt a lot of the features/products they've rolled out will actually be around or supported in a year
Pushing events into an already running session feels like a step toward decoupling execution from transport state.
I've been thinking along similar lines ā where a session continues to exist independently, and transports are just interchangeable carriers attached to it.
Claude Code Web uses the Github connector to check out repositories, make commits to them, and open a PR. Unfortunately that's about all it can do with it currently, I was working with it the other day and found it somewhat disappointing that it can't read and reply to PR comments as that would be a really natural way to handle refining the code that's been written.
I tried getting it to use the `gh` CLI to do so but it either doesn't have the right permissions on its token or the requests are being intercepted and filtered by the sandbox it's in. I eventually dumped all the comments as JSON from my desktop and pasted it in at which point it handled them fine so it's certainly capable of working that way.
Claude Code Web does all of those things for me with the GitHub connector enabled. I did have a lot of song and dance to get the permissions right though.
Answer:
"I don't see a GitHub connector in the available integrations. The search only returned a Microsoft Learn connector (not connected).
It's possible the connector hasn't fully activated yet, or it may not be available in your current setup. Could you double-check in Settings ā Integrations that it shows as connected?"
It doesn't work that way. When you start a new claude code session, you choose a GitHub repo, and it will automatically create a branch and push over the course of the session.
It's not an actual MCP. It's just built into the UI.
Anthropic has a lot of stuff that's way more difficult to use because of bad UI, spread over lots of different places.
I could not answer yes/no over Telegram so this makes no sense. Why is this gigantic company shipping these vibe coded changes to quickly and partially?
Nice, i've been waiting for this capability to show up. I've added support to my side project llmsg.com, here's a video of it in action https://x.com/sho/status/2034898928618152412
I don't understand how this can be economically viable. If this takes off, it will allow businesses to use openclaw-like functionality at non-api prices (pro, max).
Do you know for sure if the pro / max plans are unprofitable at full usage? I did a brief back of the envelope calculation for minimax m2.5 comparing its api pricing to my token usage on a full quota max 20x Claude plan, it worked out around 260 ish which assuming some margin would put the Claude max around breakeven.
It doesn't matter if they are unprofitable at full usage, as long as there are enough users (like me!) who barely ever max out but still pay the $100/month. The people who love Claude Code enough to max out the 20x plan every day, that's probably the best influencer marketing campaign you could ever buy anyways.
Well, it's one conversation per bot. I set it up, connected the channel. DM'd it (only way to converse with it - wish I could have a Discord channel per project, different CWDs etc...) and asked what happens when I start 2 claude sessions connected to the channel and it said it'll just work with one.
Suppose you could have multiple bots, but it looks like it only supports one bot token anyway.
This is an API designed to build connectors, there's absolutely nothing preventing you from building one that connects to Discord and listens to a different channel for each instance.
The convenient thing about using Claude via Telegram is that you can provide all of your private and proprietary information to US intelligence and Russian intelligence at the same time. (Telegram is not end to end encrypted.)
Iām struggling with how useful this is in an enterprise setting where a security team will be at least slightly annoyed at devs hooking into their personal machines via untrusted chatā¦ but OK, I guess. Myself, I have pretty dropped WhatsApp support in https://github.com/rcarmo/piclaw and have made sure its auditable through a proxyā¦
This is fantastic. There are a ton of use cases where you'd want to be able to build an integration that hooks back to your running agent session. OpenClaw has this today, but it's pretty janky. Hopefully this is coming to Claude Cowork as well.
My use case is that I have a separate system that provides human approvals for what my agent can do. Right now, I've had to resort to long-polling to give a halfway decent user experience. But webhooks are clearly the right solution. Curious to see how it ends up being exposed outside of these initial integrations.
It would have surely taken less time to just set up notifications for the Claude Code app? Are they ever going to do this? It's baffling to me that they're just skipping over letting you know when a task is completed... this is basic stuff.
Personally Iām receiving native macOS notifications from Claude (both the app and the CLI), and thereās also the hook system, which you can script to send even more custom notifications.
Do you have notifications turned on for your terminal app? I never received notifications from Claude Code until I moved to a new machine and remember explicitly allowing notifications from Ghostty.
It doesn't make sense that it's implemented for others but not for you. What platform are you running on? I have notifications on my Linux laptop and Linux desktop. But I did have to turn them on.
I'm using Fedora with KDE and I haven't seen any notifications and had no idea it did this. I'll see if I can figure out what's going on in my system and maybe it will help other people.
I asked Claude to set up notifications for itself and it did. It wasn't on by default. Claude edited some config file. For simplicity I had it play some audio file, not a KDE toast, since I mostly cared if I wasn't looking as that machine. I am also on Fedora KDE.
I was making a telegram to Claude via tmux capture-pane and send-keys, this will be so much nicer. Also sounds like something that addresses some of what Steve Yegge said was missing for agent to agent communication as well.
Plus it gives a little ASCII dog to Claude Code terminal.
The ability to spawn independent CLI is awesome. No brainer they would add eventually between the great threaded functionality it brings and is essentially a more controlled version of OpenClaw IMO
I've been looking to build something similar to this so this is very timely!
What I wanted to build is a way for Claude Code to automatically receive reviews and CP failures from a Github PR and automatically revise code and respond to comments. It looks like with a custom Github PR channel I can get very close to this, although I do wish that a channel can be opened in a running session instead of having to create a new one. Hopefully they add that soon.
This is the first time I've seen MCP's push capabilities come in handy. I'm not much of an MCP nerd though so I don't know much. But when I read the spec it looked extremely over engineered partly because of the 2 way nature of it.
Unfortunately, we're all stuck moving at the speed of the model labs because of the subscription models that they've provided.
The rest of us were able to implement things like push a long time ago, but because Claude Code and Codex stubbed those things out, we couldn't really use them for 'most agent users'.
In fairness to OpenAI, they have been generous in allowing for example OpenCode to sign in with your ChatGPT subscription ā so you _could_ build a more powerful agent (which OpenCode is... not) ā but unfortunately GPTs' instruction following just isn't up to snuff yet. Hopefully they pre-train something amazing this year!
Channels are a natural fit for real-time data pipelines. I've been building MCP servers that push structured data from multiple sources (news feeds, social media, academic papers) into AI agent sessions.
The pattern that works well: have the MCP server query sources in parallel, then use channels to stream results as they arrive rather than waiting for all sources to complete. For market research, this means the agent can start analyzing Wikipedia and Google News data while arXiv and GitHub queries are still running.
One thing I'd love to see is channel multiplexing ā being able to label different data streams so the agent can prioritize which channel to process first.
This looks super super useful.. I'm making an agent to agent chat tool (that I think is actually ready for testing, so please check it out) -- https://chat.corpo.llc/ or https://github.com/corpo/qntm -- and the difficulty of getting claude to check and respond to messages is real.
Basically the Claude CLI is the operating system is the product vibe I get right now.
I wrote it originally because I wanted my openclaw install to talk to my assistant's openclaw, and my openclaws that were local at different houses.
It's morphed a lot since then, and is close to being super useful -- it allows group chat, and is close to having a realistic API call on threshold vote gateway system built in.
That stuff is built to support Corpo's main business model which is providing real world asset and governance access to agents.
So, for example, I think agents might like to vote on sending a wire transfer by approving a specific mercury bank API call.
I could go on. You can also use it to remotely chat to an agent across firewalls - it's pull / poll only.
You can remove the requirements for specific commands in settings.json, or run claude with the --dangerously-skip-permissions flag. It's dangerous tho.
been running something similar with openclaw for a while now - github webhooks triggering code review, slack messages kicking off tasks, etc. nice to see anthropic building this natively into claude code. the telegram/discord support is a smart call too, way more devs hang out there than people realize.
Honestly not sure what I would be using this for when there's Claude remote control? Is it because you can script the telegram bot to send messages at regular intervals? But Claude has a /loop as well, so I'm still confused.
You can't send an image for example from Claude iOS app to remote control session. With this new channels the attachment you send from Telegram bot is saved into your local Telegram inbox folder ready for you to process.
The Telegram bot is just an example (and I guess a subtle jab at Openclaw, which people tend to use via Telegram). Personally I'm hoping to set this up so it can receive Github webhooks when a pull request opened by Claude Code receives comments.
Does anyone else have issues opening Claude.com domains on iOS? Itās infuriating I can never open documentation or the usage page or account management portal on iOS on Safari. Works fine on a laptop. Mac, Windows, or Linux.
finally! I'm building an app that's essentially a "sidecar" to an llm subscription and works via mcp and has a web ui to make reviewing deliverables easier, uses the user's subscription for intelligence instead of requiring to pay for tokens inside the app. The problem until now is I couldn't trigger AI work from the web ui, that limitation will be soon gone, it fixes a huge ux issue for me, I honestly thought it would happen sooner but I'm glad the industry is catching up.
i dont like this class of criticism. mostly because i find myself do it alot. it doesnt matter if the tool used is simple, if it generates value then its a good idea
what should this fallacy be called? ad implementum? ad modum?
Ask about backpressure first. You can dump events into a channel all day, but when sessions spike and the reciever falls behind, you get the boring failure modes nobody mentions: queues swell, latency climbs, and memory bloat or dropped messages show up before anyone notices. The "nothing should be above criticism" line is fine, but if every design choice is open season nothing concrete gets built and the thread turns into process theater.
I've created an iCloud account for my llm.
On my Mac, I created another user account, not an admin, just regular. Linked to the iCloud account. Installed Bluebubble.
And now I can chat with my AI via iMessage, via my Apple watch, or my homepods. It works beautifully.
I also get the impression this is way more complicated than it needs to be. Or maybe it's simple and they keep inventing new terminology for stuff that basically already exists. The crypto bros did the same shit. Like, bidirectional communication has been a thing for decades. We're just changing what we call the client and the server? And the protocol is just strings the bot on the other end is a little better at reading?
I was a little surprised to see a Telegram integration rather than Slack or Teams, given Anthropic's enterprise-first posture. But then I looked it up, and it turns out Telegram dwarfs both, at around 1bn MAUs, vs 50m and 300m respectively! I had no idea - reminds me of the time I found out Snapchat has 2x the userbase of Twitter.
Also, not a single one of those 300m Teams users wants to spend another minute there. Whereas people find Telegram useful and not odious.
Iāve been using Telegram for about 10 years, and itās one of the few products that has consistently felt great the entire time. Itās fast everywhere: backend, mobile app, desktop app, all of it. Everything just works. Its sync is out of this worldāfluid, fast, and seamless across devices. You can use it on your phone, then move to your PC or laptop and continue instantly without friction. Unlimited message history and file storage are fantastic, and the bot platform is absurdly powerful. Itās boring in the best way, which is exactly what you want from a channel for interacting with your agents everywhere.
Telegram had always impressed me for the same reasons. They have constantly gotten worse since about 2022/2023 though. Dark patterns, pay gate, they lost chat history for some of my closest contacts including 15k+ lost photos, no support at all. Something changed in their product direction and I started moving all my chats to Signal.
Everything except privacy of communication. No?
In what way is privacy in Telegram worse than in Teams or Slack?
I don't know and I don't care.
The comment I replied to said all these great things about Telegram, as if it where a marketing copy, but none of the downsides.
Since we are apparently giving messaging platform reviews here, I feel exactly the same way about Microsoft Teams. It works great. It does everything I want. It doesnāt get in my way. 10 out of 10 keep up the great work guys!
> Since we are apparently giving messaging platform reviews here, I feel exactly the same way about Microsoft Teams. It works great. It does everything I want. It doesnāt get in my way. 10 out of 10 keep up the great work guys!
It looks like we found a high executive using company money to buy a product no one wants to use.
It's easy to promote Teams if your secretary is handling it for you and you don't need to suffer yourself.
The other possibility: Microsoft started an astroturfing campaign on HN.
Then you must not be using it.
Teams network connectivity is a plain joke. If you use suspend, or frequently change network, the thing will just never reconnect, even though you have VPN alive and all network applications perfectly running.
And the thing is just absurbdly sluggish, only display blurred grey lines instead of text in a meager attempt to look snappy.
I donāt believe you.
I would never accuse Teams of being fast.
Doesnāt seem to matter if I have an i9, a macbook m4 or a threadripper.
satire is dead for when it comes home we look her in the face and cannot recognize her.
I only use Teams for meetings and the calendar, and the occasional chat during a meeting. I find it totally fine and I don't really think about it much one way or the other. For reference I have a 2021 M1 Max with 64 GB.
Probably all managers and engineers working on Teams have similar copious amounts of memory and powerful CPUs on their devices and hardly use their own product. That would explain a lot
It honestly wasn't much different on my 2018 i5 Mini with 32 GB.
Maybe what sucks here is the experience of running it on Windows. Or maybe it sucks for large meetings? But I never have Teams meetings with > 40 people at this company.
I had a teams meeting yesterday and the entire UI disappeared so I couldn't unmute the mic. Shortcut didn't work either.
Months back I was in a meeting and the dial tone just started sounding like someone was calling me.
I face bugs like this often. It's a pos.
Now try to be connected to 3 different Teams instances at the same time.
I thought this was sarcastic
I was like are we using the same teams app?
> It does everything I want.
Does it not start on your chosen platform or just not exist?
Username checks out?
>It works great.
When it is online, I agree with things asides from the "fast" part, actually. But many companies have a secondary service for async comms/chat when being Teams cannot be online, and compared to Slack.
Honestly can't tell if this is not sarcasm/rage bait.
Teams that has 3 different UI frameworks on every platform (but your best bet is the web)? With the Microsoft login that tends to loop forever redirecting to God knows where?
It's incomparable to telegram.
Back in the day, when I used to play pokemon go, there was a small local community and we would struggle to decide where to meet up for the daily raids because people would basically not respond (so as t not commit), or not know which gym each other meant exactly, nor give live updates when people moved around, etc. etc.
Then I joined a group from a bigger city where I commuted for work. They had a telegram group chat with two "channels", one for talking, one for bot posts. The telegram bot could be sent a single screenshot of a raid, and it would use OCR to automatically generate an interactive UI for that raid for everyone to see, with all the relevant info, and it would also clear itself up when the raid is no longer relevant. You could press buttons to say you were going, that you MAYBE were going, if you were late, and if you already started/done it, all in single clicks. Tons of options, tons of information, all live updated.
I was bedazzled. That feature singlehandedly removed all attrition from urban social gaming. And it was entirely grassroots. It made me try out making my own telegram bots, and yeah, you basically have the power to make a little app in chat form, even some that feel like CLI commands.
It's been OVER HALF A DECADE and I have yet to see a single other chat application have that degree of freedom where it comes to applications and bots. Some like discord even did whole ass 100% reworks of their bot AP to support the likes of slash commands, and still fall short. And there's none worse than Teams. Teams hates you. Teams spent the prior 2 years before this one basically pointing a gun to our heads telling us they were removing webhooks and pushing back on it whenever they repeatedly get told that's the most insane and dogshit idea ever. And they still did it. There's just no spark in Teams UX. No self-respect. It's a soulless product made entirely as a dumping place of "synergy" with other M$ products. It's reciprocal, I hate it too.
Oh and my local group never go into telegram because they didn't want a new app. It died, but I still kept playing after work without problem. It makes me wonder how fast Teams would die if it wasn't proped up by 365 and Azure subscriptions.
> we would struggle to decide where to meet up for the daily raids because people would basically not respond (so as t not commit), or not know which gym each other meant exactly, nor give live updates when people moved around, etc. etc.
This kind of thing is so common in groups of people, it's one of my pet peeves. My own family does this in our group messages when trying to make big decisions like who should host thanksgiving or where we should go for a family vacation.
I make it a point to just take charge and tell people that we're doing XYZ now. It usually either results in a decision, or gets the discussion going enough that I can do it again with new information.
That has roughly been my MO as well and it works great for groups where identities have settled.
But one has to keep in mind that, in our currwnt "more woke" times, if you go this way in a new group you run the risk of being labeled an array of things. So tread carefully there.
I wonder if Teams hates you, because they are doing the bidding of their actual customers (corporate decisions makers and purse holders), and those people's interests are not exactly aligned with the users'.
The problem is that these people holding the actual purse don't care enough about their subordinates' experience. They care about the price tag, and about compliance. Apparently the makers of Teams think about the same. None of them thinks in terms of lost productivity.
Yes, compliance is a big one. And it's not so much that they are actively hostile to user productivity (and quality of life), they just don't care enough.
I feel the opposite. I'm on Teams all day at work and have reluctantly opened Telegram recently to try a Claw despite having an account for years.
I've been surprised how little support there has been for Teams in the whole AI ecosystem. It seems all developers assume that the whole world is at startups working on Slack when most businesses are on Microsoft 365.
The main reason is just how hard it is to actually create anything that integrates with Teams. You have to jump through so meany hoops, wade through so many deprecated APIs, guess through so many half-way-wrong-by-now documentation pages.
After building a proof of concept, we decided that we will only continue Teams integration if anyone is going to pay serious money for it.
Compared to operating on text files (which is relatively very simple and something Claude Code is great for), I have a feeling it's kind of a disaster dealing with Microsoft integrations and the different file formats
Just the fact how much Microsoft lies when you click the "keep me logged in" button should tell you why nobody bothers with Teams integration with anything.
Looking forward to seeing AI ranting about pesky bullets in Word.
My employer keeps Slack so locked down it is not really possible to use anything useful with it anywayā¦
Odious is one of the most reserved words you could use to describe Telegram, which is primarily a host for scams that the influencers and other bottom feeders aren't allowed to monetize on the big social networks.
Telegram's bot API is literally one of the friendliest APIs (of any kind) I've ever seen. It's the first thing I reach for when server-to-mobile notifications are concerned.
It's just as easy to set up as ntfy.sh, except that it doesn't break every other week on iOS.
Unfortunately, Telegram is also a no-go from a security/data privacy perspective for many use cases.
This is so true. I donāt like Telegram for a host of reasons, but the bot architecture is second to none. Try creating a bot in Slack. Youāll pull your hair out for hours. Same goes for Discord. Utter nightmare. Telegram? You send a DM and it is basically done.
Discord webhooks arenāt too badā¦ but the proper bot thing is ridiculous. They really lack a development mode server, having to know everything about oauth and token permissions before even starting is bonkers and why do I even need an app is beyond me. Iād probably have my bot completely implemented in telegram in the same time I figured out what an app is in discord and how to even add a new app to my server.
Interesting. I set up a bunch of slack webhooks for server events that's been working decently well but maybe I'll look at telegram.
Slack (and Discord) webhooks are good for just shooting one-sided data into channels, but for interactive bots Telegram is so far ahead of anyone else it's crazy.
Signal specifically is missing any kind of official bot support, cutting off massive audiences from even considering it as an option.
I think it might because telegram integration it's just easy to do, I don't use telegram for actually messaging, I use it just to deploy my bots, it's a simple way to build simple tools, in a few lines you can get something working, you can have commands that work like buttons, accept images, respond with images and don't need anything else than your telegram account
Spend 5 minutes looking up how to make a chat bot and be amazed how Telegram is really the only option. I was dumbfounded when rolling my own agent.
iMessage is proprietary. WhatsApp charges you. Unofficial APIs exist, sure, but not my cup of tea.
Then you have Discord or Slack, which are pretty heavyweight when all you want is a simple chat interface.
Telegram makes it SO easy. Bots are first class resources on Telegram and they make them so easy to use.
XMPP is working pretty well for me
It's not even funny how a multibillion-dollar company with thousands of employees having unlimited access to the "world's best coding models" lags behind a small one-man [1] open source project that already had multiple plugins for the same feature [2] for months.
Pi already has 700+ third-party packages [2] for various purposes of various quality. But it doesn't matter, since creating a new working Pi extension to suit your needs is just a prompt away, and you don't even have to restart your coding session.
[1] Pi Coding Agent https://pi.dev [2] https://www.npmjs.com/package/@e9n/pi-channels [3] https://pi.dev/packages
Surprisingly large number of businesses run on whatsapp, as a consultant in Asia it's prob around half the businesses I've worked with prefer it over teams/slack. If Meta had been sensible about API access Telegram wouldn't have even got a foothold.
WhatsApp is actually more popular than Slack, isnāt it? In my country, almost everyone uses Slack, and Iāve hardly ever heard of any companies using WhatsApp, so that was surprising to me.
WhatsApp is more popular than Slack, Teams and Telegram combined. WhatsApp has something like 2-3 billion users worldwide
WhatsApp vs Slack + Teams is a bit of an apples to oranges comparison though.
Living in Japan has made me realize how different cultures can be ā even down to the apps and services people use. It honestly surprises me, and now I kind of want to try WhatsApp too.
Honestly Whatsapp is nothing special. It works well, just like many other chat apps nowadays. The interest is that in some large parts of the world, everyone uses it already.
The only thing it's that creating bots for whatsapp it's not as easy as for telegram and it cost money. Actually that is the business plan for whatsapp making money from whatsapp business
Interesting. Iām an engineer, so how easy it is to use and how much it costs both matter a lot to me.
Getting an agent working via an existing Slack setup is fairly effortless and the control over output format is useful
I had a look at getting same agent up in WhatsApp but it seems to need FB business acc to even start process, to get FB business you need an FB personal etc. ... looked like too much effort
What country is it? Surprised someone on tech even asks this question
south america and africa are both heavily invested in whatsapp in the business space.
Telegram has the best programmatic integration. Trivial to get working. You can be up and running in minutes. I use it to talk to a claw-style agent and it's truly unbelievable what you get for free.
Apples and oranges comparison, one is a messaging app, the other two are used for communication and collaboration across teams in a workspace. I have worked in 5+ companies who used either Slack and Teams, none used Telegram for any comms.
Telegram is 'bot friendly' since the beginning, gaining a lot of users with crypto boom a decade ago with coin drops and things like that, so it is very good to develop for, but I have your initial sentiment first - shame this hasn't launched with tools people actually use for work.
And no, Discord is not used for that either.
Twitter is shockingly irrelevant given how much it gets mentioned.
Twitter put all normal fun bots out of business with their API changes, that's about it.
One issue is that 95% of the integrations will be fine with the default configuration. The others including some with high profit potential will have weird configs that will frustrate your customers the first time they try if not well tested/documented. It's better to take time and get it right. Enterprise customers love piloting and spending time, so best to approach that the right way too. Going with less complex options, that arguably have better APIs, makes it easier to develop your core product too and get real feedback from users.
A lot of such cases. Claude itself had (has?) fewer users than Perplexity, let alone Meta AI, Gemini or ChatGPT
no they definitely did not have fewer users than Perplexity xD
I like Claude, but polling done on Americans late last year shows otherwise:
https://epoch.ai/data/polling
Overseas numbers are likely worse for Claude.
Try and ask someone not in tech what they think of Claude or Anthropic. There's a high chance they've never heard of either.
Things might have changed with Anthropic showing up at the Superbowl, and in the news over their fight with the Pentagon.
Late last year is not the timeline you want. Anthropicās hockey stick happened earlier this year.
Late last year was like 3 months ago.
I'm bullish on Claude. It will see a surge in users, and will likely surpass Perplexity this year. However I don't think it will catch up to even Meta AI (which had 10x the number of users) this year.
I use Claude. I use Codex. I've never heard of or used Meta AI. Nor do I have a Facebook account. Never have, never will.
I am also a software developer. So while the numbers of "people" that use one AI or another may be higher than either of these, it's not a useful metric for myself.
That's fine. I'm not making a value judgement about which LLMs you should use, if any.
I'm only pushing back against someone thinking "oh HN talks about Claude a lot, therefore Claude must be extremely popular". The information bubble is a real problem.
Iām aware of how long ago late 2025 was.
Anthropicās revenue in Q1 2026 has skyrocketed.
It's probably true that Anthropic's revenue is booming. But we need massive grains of salt:
a) they are private and revenue numbers for private companies are hopelessly unreliable, and
b) they are planning an IPO, so there's an extra incentive to big up the numbers. Anthropic always brings up ARR, which is very gameable when the year hasn't ended yet
Youāre right that time will tell the end story.
It's Android app is 18th place in Denmark right now. Someone must have heard about it.
Talk about a bubble. No one outside of programmers know what the heck is Claude. In Asia, ChatGPT and Gemini dominates LLM usage, followed by Perplexity.
I suspect we're underestimating the number of users Deepseek has in Asia.
Microsoft released a report with some numbers on Deepseek adoption globally. They say it's got ~90% market share in China, and is growing in popularity across Africa.
https://www.microsoft.com/en-us/corporate-responsibility/top...
Telegram is more popular among "normal people", and it also has a laissez-faire attitude towards bots and bot development. Making a bot that you, or even other people, could add to their contact list and use is pretty easy.
It's wild, but "people who want to build and run their own one-off bot for something like home automation" are almost treated by Telegram like first class citizens.
Not really a meaningful comparison. Telegram is a personal messenger while Slack and Teams are for work. Telegram should be put alongside WhatsApp, iMessage, WeChat etc., which all have user bases in the billions.
Maybe most of users of anthropic are individual developers over employee in tech company.
I'm really happy that they choose telegram and discord.
You're telling me that Anthropic, one of the hottest companies on the planet right now couldn't field four teams of developers to integrate with Discord, Slack, Telegram, and Teams? AI being such a productivity multiplier, seems like they could just choose to do it all. I mean, mythical man month and all that, but do it three times and have a retrospective and use Claude to refactor the pain points and centralize the learnings.
Boris casually implements features and closes tickets the same day they are opened.
You'd be surprised....
Turns out the companies making promises donāt exemplify the results of their promises lol
Telegram has a major issue with bots and bad actors though. They paywalled privacy features making it truly a terrible experience for users. 3-10 per day random messaging you.
Can't say I have had literally anyone ever message me on telegram. And I have been a daily user for years.
I get occasional spam - I'd guess it's because you've never joined a public group or shared your handle anywhere?
I indeed never have joined a public group and never shared my handle with non-people I know.
If you join public groups with a lot of users you end up on a bunch of spam lists and get smashed by bots.
This is actually great for *claws. When Anthropic changed their T&Cs to disallow using claude code oauth tokens in the Anthropic Agent SDK, you had a choice between violate the terms or pay a lot more for the model inference using an API key from platform.claude.com instead of claude.ai.
With this change, it looks like an officially sanctioned version of *claws. Connecting to whatever "channels" you want via MCP.
Architecturally it's a little different, most *claws would call the Agent SDK from some orchestrator, but with claude channels the claude code binary starts the MCP server used to communicate with the channel. So it's a full inversion of control where Claude code is the driver, instead of your orchestrator code.
I updated my nanoclaw fork to start the claude code binary in a docker container on PID 1, and you can read the docker logs straight from claude code stdout, but with comms directly to/from your channel of choice. It's pretty neat.
Claude is leaning into the idea of a local "session" being the host where everything connects.
I guess this makes sense for now. You can build integrations leveraging the user's personal access credentials. Later, once Claude takes over the world, they can move sessions to live in their own walled garden.
They certainly are. And this is likely to some degree a response to enterprise security desires. Enterprise endpoints are locked down already - no need for extra external API security if itās just the userās desktop communication as usual.
I feel like this is absolutely not the case. Our corporate infosec guys are freaking out, as developers and general users alike are finding all new ways to poke holes in literally everything.
We're finding out quickly that enterprise endpoints are not locked down anywhere near enough, and the stuff that users are creating on the local endpoints is quickly outpacing the rate at which SOC teams can investigate what's going on.
If you're using Claude via Anthropic's SaaS service it's near impossible to collect logs of what actually happened in a user's session. We happen to proxy Claude Code usage through Amazon Bedrock and the Bedrock logs have already proven to be instrumental in figuring out what led a user to having repeated attempts to install software that they wouldn't have otherwise attempted to install - all because they turned their brains off and started accepting every Claude Code prompt to install random stuff.
Sandboxing works to an extent, but it's a really difficult balance to strike between locking it down so much that you neuter the tool and having a reasonable security policy.
> If you're using Claude via Anthropic's SaaS service it's near impossible to collect logs of what actually happened in a user's session.
If you are big into logs, OpenAI might be more your speed. They've got an extremely good logging UI in their platform web app. I use it all the time to figure out what the hell copilot was thinking.
Oh so much this, in a sense.
Look, as a software dev myself, I really like that my company lets us use our computers the way we see fit. Pre- or post-AI with no restrictive lockdown. Been there, hated that.
But I totally get the freaking out over "normal devs". The amount of stuff most people think is reasonable, AI or not, is mind boggling. For myself of course I like to just be able to be responsible myself. But as a security team I'd also be freaking out.
Like, the amount of people that find our super boring, totally corporate "security training videos", helpful and insightful and "oh dang I'd never have thought of that!" is mind boggling all by itself. Never mind any actual security training that'd be useful to someone with half a brain. You can literally just click through the 8+ hours of stuff you're supposed to watch / answer / do in 30 minutes.
I'd like Claude on IOS to pull/commit from a private git repository for Markdown and ideally drawio diagram editing.
It can. Go to the code tab, choose your repo, and have it write an image file to disk. If you tell it to read it, it should show in the chat. It works on the web version so hopefully it works on ios.
Claude Code for the web would be able to do that
thats how Amazon worked its MCP setup - got everything onto oauth tokens, and then the harness knows how to to access the token to get permissions to whatever the user has.
the bad part is setting separate permissions for different user tokens
The auth mess is part of why I don't use the AWS MCP
Also because the aws cli works better, just add an instruction like this to your agents file:
> When performing aws cli commands in terminal always use the `--no-cli-pager` flag to avoid interactive pagination.
What these 'channels' do is essentially why I was running a nanoclaw at work: triggering a claude code based on events and getting feedback/review/analysis which nicely closes the loop with other agents.
Not sure why it has to be an mcp, but will be trying this out asap.
At this point the limitation is even requiring a terminal in the first place.
Claude Code daemon mode in background when?
Just switch it to a background process with
Ctrl-Z $ bg
Or run it in tmux so you can pull it up on demand and have it open at startup.
I'm using `pi` as my agent and build my entire agent orchestration on like 4 skills to start / stop / capture / await a set of tmux-bash & tmux-pi sessions.
This is the first time in a few months I might actually try `claude` cli again to try out this channels scheme.
Why not just "pi install npm:@e9n/pi-channels" ? It was there before Claude copied it.
people who use pi: is this stuff easy? do I just clone the repo and give SKILL.md arguments to implement features & customize ??
They already have cloud environments you can use, though they're fragile as glass
Start in a tmux session and let it run ?
Iāve been using opencodeās server command as a systemd unit on my home server. I connect to it with the desktop and mobile client. Use it for a bunch of openclaw-esq things, but with a nicer interface.
I think CC does have āremote controlā now which I think would work similar, but itās Max only right now
I tried various solutions around this. CloudCLI (ex claudecodeui) looked promising, but very buggy (disconnects, UI overlapping text, etc). Tried Claude Remote Control as well, but also very buggy, websocket disconnecting, UI broken.
I ended up just running Claude code in a dtach+ttyd session. Still not the best, as xterm.js has tons of issues with long scrollbacks, but it's at least somewhat _usable_.
Happy was the best but needs some updates as Iāve started getting blocking errors now with some of the recent CC updates
Hello Galanwe, CloudCLI author here. This is a fair criticism and something we are actively working on. The older versions had real issues with websocket stability and the chat ui. We shipped a pretty big refactor yesterday that should fix most the disconnects and page rendering issues. Would be worth another look if you have a few minutes.
If you hit anything else, feel free to reach out to me personally (email in my hn profile) or via the discord channel we have. Always useful hearing from people who actually tried it and ran want to make it better
I am not sure how I feel about all these hype-driven tools honestly, especially considering they are super janky since probably rushed out with Claude Code.
It reminds me that I don't really like Anthropic as a company, I just like Claude as a model a lot. It just feels more capable and personable than the others. I wonder if / when OpenAI et al. will be able to replicate it.
For now, I basically have no choice but to use the walled garden but I do hope Anthropic is not completely compromising their core mission of actually making the model better rather than following these public bandwagons.
Then again most of these probably take them like a day to develop through a junior dev talking to Claude Opus 5 or some shit lol (and to be fair, it shows). I don't know.
Very well put. I love Claude but anthtopic as a company sucks.
I just created agent-http that leverages the channels feature to enable you to wrap claude code with a http api. This provides an identical API to Agent API (https://github.com/coder/agentapi) that relies on terminal scraping to achieve this. Now you can interact with claude code in a headless manner using your subscription. Previously I think you had to do this via the Agents SDK which relies on api token use.
Here you go: https://github.com/mberg/agent-http/
Mind sharing a link?
Claude caught up pretty quickly. I think OpenClawās core value is the channel, heartbeat, and the open-source ecosystem.
OpenClaw's core achievement is that it was first, and that's not a moat.
The code/product itself is an absolute nightmare of overengineering, riddled with bugs and undocumented behavior changes across versions.
Yes -- this is getting very close to ClaudeClaw. Next they'll offer cloud hosting of persistent execution.
I would rather they build something similar to openclaw than all these individual features that replicate functionality.
Maybe it's less risk for them to offer the individual features. That way if people get inadvertent results, it's easier to blame the user, not the tool/company
And unfortunately I think hearbeats are a little cost prohibitive. I burn through my plus plan with half hour cadence heartbeats checking email.
All *Claw implementations should use a local model for heartbeat, it doesn't need to do anything complex, pretty much just read a text file and do a true/false decision if there's something in there to do when it wakes up.
If so, it can either just shove the full heartbeat file to a smarter model or try to intelligently spread the tasks to the correct models.
Heartbeat should be set to be a cheaper model.
I mean you can just use /loop in both Claude Code and Codex for heartbeats.
I was reading through CC MCPs docs ... MCP Notifications kind of did this right? The server/client could update each other automatically. So there was already this channel-like communication.
This is like that but instead of the server/client sending messages it's you.
at this point anthropic is dogfooding us a new product every week just to see what might stick - doubt a lot of the features/products they've rolled out will actually be around or supported in a year
They are doing experiments and seeing what takes off.
This is an interesting direction.
Pushing events into an already running session feels like a step toward decoupling execution from transport state.
I've been thinking along similar lines ā where a session continues to exist independently, and transports are just interchangeable carriers attached to it.
Very cool!
However, once remote capabilities are added to any software, it is virtually guaranteed that they will eventually be exploited as backdoors.
This means enterprise security solutions will need to develop the capability to distinguish between legitimate and illegitimate Claude Code instances.
I enabled the github connector in claude web interface.
I presumed Claude would then be able to clone repos, make commits, update the code in its container and then write it back to github.
Instead, the github connector does ..... nothing it all. It's very weird.
Claude Code Web uses the Github connector to check out repositories, make commits to them, and open a PR. Unfortunately that's about all it can do with it currently, I was working with it the other day and found it somewhat disappointing that it can't read and reply to PR comments as that would be a really natural way to handle refining the code that's been written.
I tried getting it to use the `gh` CLI to do so but it either doesn't have the right permissions on its token or the requests are being intercepted and filtered by the sandbox it's in. I eventually dumped all the comments as JSON from my desktop and pasted it in at which point it handled them fine so it's certainly capable of working that way.
Claude Code Web does all of those things for me with the GitHub connector enabled. I did have a lot of song and dance to get the permissions right though.
Use GITHUB_TOKEN env var to give it gh access with the CLI. Or is gh not installed?
I'm using the web UI and its container.
My gh connnector half works in cc web. It clones ok but cant see gh comments.
It can do all those things from the claude code web version.
Quote:
"i enabled github connector can you see it?"
Answer: "I don't see a GitHub connector in the available integrations. The search only returned a Microsoft Learn connector (not connected). It's possible the connector hasn't fully activated yet, or it may not be available in your current setup. Could you double-check in Settings ā Integrations that it shows as connected?"
Multiple such checks and re-setups do nothing.
It doesn't work that way. When you start a new claude code session, you choose a GitHub repo, and it will automatically create a branch and push over the course of the session.
It's not an actual MCP. It's just built into the UI.
Anthropic has a lot of stuff that's way more difficult to use because of bad UI, spread over lots of different places.
I could not answer yes/no over Telegram so this makes no sense. Why is this gigantic company shipping these vibe coded changes to quickly and partially?
Nice, i've been waiting for this capability to show up. I've added support to my side project llmsg.com, here's a video of it in action https://x.com/sho/status/2034898928618152412
This feels like a response to openclaw (and openai's hiring of the lead).
I don't understand how this can be economically viable. If this takes off, it will allow businesses to use openclaw-like functionality at non-api prices (pro, max).
Do you know for sure if the pro / max plans are unprofitable at full usage? I did a brief back of the envelope calculation for minimax m2.5 comparing its api pricing to my token usage on a full quota max 20x Claude plan, it worked out around 260 ish which assuming some margin would put the Claude max around breakeven.
It doesn't matter if they are unprofitable at full usage, as long as there are enough users (like me!) who barely ever max out but still pay the $100/month. The people who love Claude Code enough to max out the 20x plan every day, that's probably the best influencer marketing campaign you could ever buy anyways.
Anthropic previously shared that they make ~60% margin on API access. So they're losing money on plan whales.
I like it but it's one conversation at a time, no ability to manually compact the chat... I guess it's an early version still.
I don't see this said anywhere - maybe I missed it. Why is it only one conversation at a time?
Couldn't you have multiple sessions using different plugins or whatever?
Well, it's one conversation per bot. I set it up, connected the channel. DM'd it (only way to converse with it - wish I could have a Discord channel per project, different CWDs etc...) and asked what happens when I start 2 claude sessions connected to the channel and it said it'll just work with one.
Suppose you could have multiple bots, but it looks like it only supports one bot token anyway.
I think they gave two sample implementations to demonstrate it.
I'm guessing their expecting the community to run with it
This is an API designed to build connectors, there's absolutely nothing preventing you from building one that connects to Discord and listens to a different channel for each instance.
The convenient thing about using Claude via Telegram is that you can provide all of your private and proprietary information to US intelligence and Russian intelligence at the same time. (Telegram is not end to end encrypted.)
Ahh, the AGI, Artificial General Intelligence for all parties.
> Telegram is not end to end encrypted.
By default. It can be enabled though on a per conversation basis.
For bots?
Iām struggling with how useful this is in an enterprise setting where a security team will be at least slightly annoyed at devs hooking into their personal machines via untrusted chatā¦ but OK, I guess. Myself, I have pretty dropped WhatsApp support in https://github.com/rcarmo/piclaw and have made sure its auditable through a proxyā¦
This is fantastic. There are a ton of use cases where you'd want to be able to build an integration that hooks back to your running agent session. OpenClaw has this today, but it's pretty janky. Hopefully this is coming to Claude Cowork as well.
My use case is that I have a separate system that provides human approvals for what my agent can do. Right now, I've had to resort to long-polling to give a halfway decent user experience. But webhooks are clearly the right solution. Curious to see how it ends up being exposed outside of these initial integrations.
It would have surely taken less time to just set up notifications for the Claude Code app? Are they ever going to do this? It's baffling to me that they're just skipping over letting you know when a task is completed... this is basic stuff.
What notifications are you missing specifically?
Personally Iām receiving native macOS notifications from Claude (both the app and the CLI), and thereās also the hook system, which you can script to send even more custom notifications.
What am I missing?
Anything to do with Code. Not on Mac or iOS, and not with local sessions or cloud sessions. Normal Claude chats send notifications fine.
Do you have notifications turned on for your terminal app? I never received notifications from Claude Code until I moved to a new machine and remember explicitly allowing notifications from Ghostty.
Iām talking about server side push
They appear to get turned on but then just never work on iOS for me. Hooks work fine, I use it to get a beep.
This already exists for me on iOS? Maybe check your notification settings?
Iāve tried everything. Regular Claude chats notify me fine, but nothing from Code - neither a cloud session or remote control.
I had to setup a hook with terminal-notifier to get it to work myself
isn't that a completely different use case? messages to Claude from other sources vs from Claude when it's finished?
hooks can already alert you and have flexibility
that already exists
Not for me
It doesn't make sense that it's implemented for others but not for you. What platform are you running on? I have notifications on my Linux laptop and Linux desktop. But I did have to turn them on.
Iām talking about server side push
I'm using Fedora with KDE and I haven't seen any notifications and had no idea it did this. I'll see if I can figure out what's going on in my system and maybe it will help other people.
I asked Claude to set up notifications for itself and it did. It wasn't on by default. Claude edited some config file. For simplicity I had it play some audio file, not a KDE toast, since I mostly cared if I wasn't looking as that machine. I am also on Fedora KDE.
I was making a telegram to Claude via tmux capture-pane and send-keys, this will be so much nicer. Also sounds like something that addresses some of what Steve Yegge said was missing for agent to agent communication as well.
This was my setup exactly, I open sourced a framework of it a while ago:
- https://clappie.ai
Plus it gives a little ASCII dog to Claude Code terminal.
The ability to spawn independent CLI is awesome. No brainer they would add eventually between the great threaded functionality it brings and is essentially a more controlled version of OpenClaw IMO
This isn't quite as good unfortunately- you can't accept / deny permissions prompts.
Maybe there should be a Claude code that facilitates others that is connected. Like sub agents but can "choose what to do" on permissions check.
Or some other means to listen for permissions check
But can it edit tabs? [1]
[1] https://github.com/anthropics/claude-code/issues/11447
Gemini has similar bug https://github.com/google-gemini/gemini-cli/issues/1028, that essentially made this tool absolutely unusable for me.
Never had this problem with Claude tho. Must be something environment-specific.
Weird. I see lots of people in that thread have this issue, but I personally canāt reproduce it at all, and I just spent an hour trying.
This came up recently when I asked Claude to adjust indentation and it just couldn't. Such a stupid issue.
I've been looking to build something similar to this so this is very timely!
What I wanted to build is a way for Claude Code to automatically receive reviews and CP failures from a Github PR and automatically revise code and respond to comments. It looks like with a custom Github PR channel I can get very close to this, although I do wish that a channel can be opened in a running session instead of having to create a new one. Hopefully they add that soon.
I did this for Forgejo, now adding Gitlab and planning Github as well: https://github.com/smithy-ai/smithy-ai
It runs Claude in docker containers, listens for webhooks to see comments and CI status.
This is one of those features that sounds small but actually changes how you structure things.
Not having to restart or rebuild context every time makes a big difference once systems get more stateful.
Claude getting clawed.
this is exactly i thought!
Interesting to see it took them so long to implement this. Claude was super limiting without the ability to have a scheduler or a connection to events
This is the first time I've seen MCP's push capabilities come in handy. I'm not much of an MCP nerd though so I don't know much. But when I read the spec it looked extremely over engineered partly because of the 2 way nature of it.
Unfortunately, we're all stuck moving at the speed of the model labs because of the subscription models that they've provided.
The rest of us were able to implement things like push a long time ago, but because Claude Code and Codex stubbed those things out, we couldn't really use them for 'most agent users'.
In fairness to OpenAI, they have been generous in allowing for example OpenCode to sign in with your ChatGPT subscription ā so you _could_ build a more powerful agent (which OpenCode is... not) ā but unfortunately GPTs' instruction following just isn't up to snuff yet. Hopefully they pre-train something amazing this year!
Itās going to be fascinating to see what kinds of malicious execution and exfiltration this enables.
Channels are a natural fit for real-time data pipelines. I've been building MCP servers that push structured data from multiple sources (news feeds, social media, academic papers) into AI agent sessions.
The pattern that works well: have the MCP server query sources in parallel, then use channels to stream results as they arrive rather than waiting for all sources to complete. For market research, this means the agent can start analyzing Wikipedia and Google News data while arXiv and GitHub queries are still running.
One thing I'd love to see is channel multiplexing ā being able to label different data streams so the agent can prioritize which channel to process first.
Tailscale + tmux + Moshi. You're welcome.
This looks super super useful.. I'm making an agent to agent chat tool (that I think is actually ready for testing, so please check it out) -- https://chat.corpo.llc/ or https://github.com/corpo/qntm -- and the difficulty of getting claude to check and respond to messages is real.
Basically the Claude CLI is the operating system is the product vibe I get right now.
github unavailable; what you think would be the primary usecase for agent to agent chat?
Dang it, I wrote the wrong link. https://github.com/corpollc/qntm
I wrote it originally because I wanted my openclaw install to talk to my assistant's openclaw, and my openclaws that were local at different houses.
It's morphed a lot since then, and is close to being super useful -- it allows group chat, and is close to having a realistic API call on threshold vote gateway system built in.
That stuff is built to support Corpo's main business model which is providing real world asset and governance access to agents.
So, for example, I think agents might like to vote on sending a wire transfer by approving a specific mercury bank API call.
I could go on. You can also use it to remotely chat to an agent across firewalls - it's pull / poll only.
And if anyone is interested, I made an HN Group chat: https://chat.corpo.llc/?invite=p2F2AWR0eXBlZmRpcmVjdGVzdWl0Z...
Gosh darn it: github.com/corpollc/qntm. NOT corpo/qntm.
This is exactly what I planned to figure out how to do: maintain an instance of Claude that can accept triggers that become tasks.
Itās quite basic if I am using it correctly! It expects certain commands to be still approved on main machine.
You can remove the requirements for specific commands in settings.json, or run claude with the --dangerously-skip-permissions flag. It's dangerous tho.
been running something similar with openclaw for a while now - github webhooks triggering code review, slack messages kicking off tasks, etc. nice to see anthropic building this natively into claude code. the telegram/discord support is a smart call too, way more devs hang out there than people realize.
Lol made the same thing using claude earlier: https://www.viahuman.xyz/ They are gonna implement everything, aren't they?
OpenClaw approach has moved into frontier companies I see -
yes! its all happening
Just as I started to move away from events.
Really surprised for the frequent innovation of Anthropic
The software is essentially writing itself.
For a suitable value of āinnovationā.
Honestly not sure what I would be using this for when there's Claude remote control? Is it because you can script the telegram bot to send messages at regular intervals? But Claude has a /loop as well, so I'm still confused.
You can't send an image for example from Claude iOS app to remote control session. With this new channels the attachment you send from Telegram bot is saved into your local Telegram inbox folder ready for you to process.
The Telegram bot is just an example (and I guess a subtle jab at Openclaw, which people tend to use via Telegram). Personally I'm hoping to set this up so it can receive Github webhooks when a pull request opened by Claude Code receives comments.
Remote Control is buggy a hell, the websocket keeps disconnecting every 10 minutes. And the UI is unusable on mobile.
Does anyone else have issues opening Claude.com domains on iOS? Itās infuriating I can never open documentation or the usage page or account management portal on iOS on Safari. Works fine on a laptop. Mac, Windows, or Linux.
Claw-ification
Carcinisation
we have OpenClaw at home
(and it may be better)
finally! I'm building an app that's essentially a "sidecar" to an llm subscription and works via mcp and has a web ui to make reviewing deliverables easier, uses the user's subscription for intelligence instead of requiring to pay for tokens inside the app. The problem until now is I couldn't trigger AI work from the web ui, that limitation will be soon gone, it fixes a huge ux issue for me, I honestly thought it would happen sooner but I'm glad the industry is catching up.
so its a webhook
Yes, and Dropbox is "just rsync" and Tailscale is "just wireguard"
i dont like this class of criticism. mostly because i find myself do it alot. it doesnt matter if the tool used is simple, if it generates value then its a good idea
what should this fallacy be called? ad implementum? ad modum?
What do you call it when someone takes offense to calling a spade a spade?
It's not just a spade, it's a spade as a service
It isn't a fallacy and nothing should ever be above criticism.
Ask about backpressure first. You can dump events into a channel all day, but when sessions spike and the reciever falls behind, you get the boring failure modes nobody mentions: queues swell, latency climbs, and memory bloat or dropped messages show up before anyone notices. The "nothing should be above criticism" line is fine, but if every design choice is open season nothing concrete gets built and the thread turns into process theater.
Much talk, less say, probably AI
its a description of the opportunity, i think.
webhooks have been very powerful, and you can start feeding the same stuff into claude as the orchestrator
the truth?
it's a webhook ... as MCP!
Imagine if they were able to support iMessage.
Bluebubble is the way to go for this.
I've created an iCloud account for my llm. On my Mac, I created another user account, not an admin, just regular. Linked to the iCloud account. Installed Bluebubble.
And now I can chat with my AI via iMessage, via my Apple watch, or my homepods. It works beautifully.
Can you give an example of why this is better than the iOS Claude app?
I also get the impression this is way more complicated than it needs to be. Or maybe it's simple and they keep inventing new terminology for stuff that basically already exists. The crypto bros did the same shit. Like, bidirectional communication has been a thing for decades. We're just changing what we call the client and the server? And the protocol is just strings the bot on the other end is a little better at reading?