top | item 46760237

Clawdbot - open source personal AI assistant

405 points| IndignantTyrant | 1 month ago |github.com

261 comments

order

mgdev|1 month ago

This thing is cool except:

1) It chews through tokens. If you're on a metered API plan I would avoid it. I've spent $300+ on this just in the last 2 days, doing what I perceived to be fairly basic tasks.

2) It's terrifying. No directory sandboxing, etc. On one hand, it's cool that this thing can modify anything on my machine that I can. On the other, it's terrifying that it can modify anything on my machine that I can.

That said, some really nice things that make this "click":

1) Dynamic skill creation is awesome.

2) Having the ability to schedule recurring and one-time tasks makes it terribly convenient.

3) Persistent agents with remote messaging makes it really feel like an assistant.

bronco21016|1 month ago

> It chews through tokens. If you're on a metered API plan I would avoid it. I've spent $300+ on this just in the last 2 days, doing what I perceived to be fairly basic tasks.

Didn’t Anthropic make it so you can’t use your Claude Code Pro/Max with other tools? Has anyone experienced a block because of that policy while using this tool?

Also really curious what kind of tasks ran up $300 in 2 days? Definitely believe it’s possible. Just curious.

jason_tko|1 month ago

I've seen many people say "I don't get the hype", so here's my attempt to explain it. I've been working in technology and software companies my entire life, but not as a developer.

Two days ago, I submitted and had my first pull request merged to an open source project (Clawdbot) thanks to my AI assistant rei.

A short story: rei suddenly stopped responding in some Slack channels. So I asked it to help me troubleshoot.

We traced the issue: adding custom instructions in one Slack channel incorrectly stopped it from replying in all the others.

I considered reporting the issue in GitHub, but then I thought, "Well... what if we just try to fix it ourselves, and submit a PR?"

So we did. We cloned the codebase, found the issue, wrote the fix, added tests. I asked it to code review its own fix. The AI debugged itself, then reviewed its own work, and then helped me submit the PR.

Hard to accurately describe the unlock this has enabled for me.

Technically, it's just an LLM call, and technically, I could have done this before.

However there is something different about this new model of "co-working with AI that has context on you and what you're doing" that just clicks.

barrenko|1 month ago

I can't parse this story. "rei" stopped working and you asked "rei" or "clawdbot" to help your troubleshoot? Are you using both? Whos is 'we' in the "we fixed it ourselves" substory?

kristopolous|1 month ago

This is a thing you can enable on GitHub for any project.

You just described a GitHub feature

redak|1 month ago

> We cloned the codebase, found the issue, wrote the fix, added tests. I asked it to code review its own fix. The AI debugged itself, then reviewed its own work, and then helped me submit the PR.

Did you review the PR it generated before it hit GitHub?

xtagon|1 month ago

Wild. There are 300 open Github issues. One of them is this (also AI generated) security report: https://github.com/clawdbot/clawdbot/issues/1796 claiming findings of hundreds of high-risk issues, including examples of hard coded, unencrypted OAuth credentials.

I am...disinclined to install this software.

Mic92|1 month ago

I skipped over the first few ones and haven't seen critical ones. The hardcoded oauth client secrets is basically present in any open-source or commercial app that is distributed to end users. It doesn't break the security of end users. It mainly allows other apps to impersonate this app, i.e. present itself as clawdbot, which is a moot point given anyone can just change /inject code into it.

joe_91|1 month ago

Same.... I'll install it in a few months when all the major security bugs have been found and patched!

strangescript|1 month ago

If you read the PR, the bad issues are in a few extensions, not the bot itself. The unencrypted oAuth token isn't really a big deal. It should be fixed but its a "if this box is compromised" type thing. Given the nature of clawdbot, you are probably throwing it on a random computer/vps you don't really care about (I hope) without access to anything critical.

barrenko|1 month ago

It also tells you a lot about latent demand.

jwally|1 month ago

Thanks for sharing.

For the past month or so I've been slowly having claude build something in the same ballpark. Basically something to nag you to take care of grown-up things so your boss/spouse/local municipality doesn't have to.

I was going to call it "Nagatha Christy", but the joke gets old after 48 hours. At the moment, its called "Jarbis" (old Simpsons reference).

For me, checklists are useful but I suck at creating them, maintaining them, etc. I want this thing to be able to look at my calendar/email/groupme and be able to say things like:

"Hey, you have 2 kid birthday parties this weekend and a soccer game - you're bringing snacks. You want me to update your shopping list?"

or

"The dentist office just sent out a reminder - you have an appointment on Thursday that's not on the calendar. It conflicts with your daily standup. You want me to create a task for you to resolve it?"

Its using: - AWS CDK - Telegram as primary chat interface - Trello/Jira/Something Custom - Integrations into GoogleCalendar and GMail - Ability to use Claude/OpenAI and different models

FWIW, if someone figures out how to create a reliable "secretary in a box" that I don't have to DIY but doesn't scream data-collection-watering-hole (facebook) I'd _happily_ pay $200 / mo for it. ;-)

reacharavindh|1 month ago

I've been thinking about this very thing the last few days. "secretary in my Mac" to be specific. An ever running daemon that uses an LLM model for smarts, but pretty much do as many dumb things deterministically as possible. 1. Fetch my calendars(Fastmail, work Google Calendar, Couple's calendar at Cupla) and embellish it with routine tasks like pickup/drop kids, and give me a Today view like this https://zoneless.tools/difference/london-vs-new-york?cities=...

2. Access to my TODO list on Apple Notes and basically remind my ADHD brain that I ought to be doing something and not let it slip because it is uninteresting.

3. Have access to all models via API keys I configure and maintain a "research journal" of all the things I go to LLMs for - "research of bike that fits my needs" whatever and figure out if there needs to be a TODO about them and add if I say yes.

4. View my activity as a professional coach and nudge me into action "Hey you wanted to do this at work this year, but you haven't begun.. may be it is time you look at it Thursday at 3 PM?"

5. View my activity as a mental health coach and nudge me like "hey you're researching this, that and blah while X, Y and Z are pending. Want me to record the state of this research so you can get back to doing X, Y and Z?" or Just talk to me like a therapist would.

6. Be my spaghetti wall. When a new idea pops into my head, I send this secretary a message, and it ruminates over it like I would and matures that idea in a directory that I can review and obsess over later when there is time..

As you see, this is quite personal in nature, I dont want hosted LLMs to know me this deeply. It has to be a local model even if it is slow.

amistral|1 month ago

I've been spending some nights & weekends building exactly this recently. I wanted something that managed my email & calendar, and proactively helped out (or nagged me) when it identified anything important.

It has a handful of core features:

- key obligations & insights are grok'd from emails and calendar events - these get turned into an ever-evolving always-up-to-date set of tasks; displayed on a web UX and sent to you in a personalized daily briefing - you can chat via telegram or email with the agent, and it can research/query your inbox or calendar/create or resolve tasks/email others/etc - if the AI identifies opportunities to be proactive (eg upcoming deadline or lack of RSVP on an event), it pings you with more context and you can give the green light for the agent to execute

Generally trying to identify finite list of busywork tasks that could be automated, and let users delegate the agent to execute them. Or, in the future (and with high enough confidence), let the agent just execute automatically.

Built the stack on Cloudflare (d1, Cloudflare Workers/Workfolows/queues, Vectorize), using gemini-3-flash as the model.

Would love any feedback: https://elani.ai.

nunodonato|1 month ago

I have my own telegram bot that helps me and my wife. Reminders, shopping list, calendar. Small and simple, gets the job done :) At the start of the day it greets with a briefing, can also check weather and stuff

Btw, I'm in the process of training my own small model so that I can run it on my cpu-only VPS and stop paying for API costs

bluesnowmonkey|1 month ago

Building it now. Basically raw agents you can talk to over any channel like Slack/Telegram/etc. (Should have SMS and voice calling working shortly.) Can connect to your email/calendar. Files and sqlite for memory/storage. Optional sandbox for coding or whatever. It's all a bit rough but working.

https://stumpy.ai

atonse|1 month ago

Clawdbot is interesting but I finally feel like those people who look at people like me raving about Claude code when it barely works for them.

I have no doubt clawdBot, when it works, must feel great. But I’ve had the tough time setting it up and found it to be very buggy.

My first couple of conversations? It forgot the context literally seconds later when I responded.

Nevertheless, I’m sure it’s improving by the day so I’m going to set it up on my existing Mac mini because I think it has the capacity to be really fascinating.

I built something similar (well… with a lot of integrations) but for running my company and continue to iterate on it.

HorizonXP|1 month ago

I’ve been doing Vim + aider, and now Claude Code. Those tools I understood. I never got into Cursor because I’m too old to give up Vim.

Clawd.bot really annoyed me at first. The setup is super tedious and broken and not fun. That’s mostly because I’m too impatient to tinker like I used to.

However, once you tinker, it’s so-so. I don’t think it’s a lot better than Claude Code or anything, but I think it’s just a focused vector for the same AI model, one focused on being your personal assistant. It’s like Claude Code vs. Claude Cowork. They’re the same thing. But given the low cost of creating custom tools, why not give people something that Clawd.bot that gives them focused guardrails?

Anyway, I could end up abandoning all of this too. And it’s all a kludge around things that should really be an API. But I do like that I can run it on my Mac Mini and have it control my desktop. It’ll be a cold day if I let it message for me; I’d rather it write deterministic code that does that, rather than do it directly.

bogtap82|1 month ago

I cloned the clawdbot repo back when it was named warelay or clawdis, can't remember, but it was much less dense then. Mainly cloned it for the in-the-box Whatsapp implementation. Since then I've built it into a pretty awesome agent for my home and family, who all have their own privileged access which allows it access to different skills and a mixture of shared and personal information. I have no interest in reconciling the Frankenstein I've built with newer mainline features, but the custom nature of my build is one of the things I find so fun and helpful about it. It's become so much more "mine" by just asking it to build out xyz feature for itself, and now it can do a bunch of weird things that revolve around its persistent access to the information I provide it and my ability to interface with it through a regular messaging app.

kkukshtel|1 month ago

I agree with this - the sudden prevalence of Clawdbot everywhere feels like tactical astroturfing.

cherioo|1 month ago

What model did you use?

At work tasks that Sonnet 4 and 4.5 failed miserably, Opus 4.5 can basically one shot them. I imagine it will be the same here.

apetresc|1 month ago

I found this HN post because I have a Clawdbot task that scans HN periodically for data gathering purposes and it saw a post about itself and it got excited and decided to WhatsApp me about it.

So that’s where I’m at with Clawdbot.

nozzlegear|1 month ago

> and it got excited and decided to WhatsApp me about it.

I find the anthropomorphism here kind of odious.

anotherengineer|1 month ago

how do you have Clawdbot WhatsApp you? i set mine up with my own WhatsApp account, and the responses come back as myself so i haven't been able to get notifications

pylotlight|1 month ago

Do you tell it what you find interesting so it only responds with those posts? i.e AI/tech news/updates, gaming etc..

chiragrohit|1 month ago

How many tokens are you burning daily?

eclipxe|1 month ago

Yeah, it really does feel like another "oh wow" moment...we're getting close.

suriya-ganesh|1 month ago

layers and layers of security practices over the past decade are just going out the window so fast.

It's quite wild to give root access to a process that has access to the internet without any guardrails. and then connecting all your personal stuff on top of it.

I'm sure AI has been a boon for security threats.

treetalker|1 month ago

Yeah! On the one hand I'm confident my law practice will start fielding cases involving catastrophic uses of this type of software. And on the other hand I'm confident I'm going to see lawyers all over the place permanently nuke their own practices with the same tech.

sowbug|1 month ago

It's confused deputies all the way down.

vanillameow|1 month ago

Been looking at this over the weekend. It genuinely seems like it could have some really cool use cases. However I just don't trust an AI enough to run unprompted with root access to a machine 24/7, even if it's sandboxed. As soon as I willingly integrate data into it, the sandboxing doesn't really matter, especially when I ask it to decide for itself how to process that data (which seems to be what they want you to do with it? Ask it to define its own skills?)

Most of the cool stuff here, i.e. automatic news or calendar summaries or hue light controls or Discord bot integration or what not, you can also just "vibecode" in an afternoon using regular Claude code. If you actually review said code, you then have the peace of mind of knowing exactly what gets triggered when. I don't really feel comfortable enough to give that control away yet.

And I also feel like the people who _do_ feel comfortable giving this control away also strongly overlap with people who really don't have the understanding to make an informed decision on it...

hexsprite|1 month ago

Clawdbot finally clicked for me this week. I was renting out an apartment and I had it connect to FB messenger, do the initial screening messages and then schedule times for viewings in my calendar. I was approving it's draft messages but starting giving it some automatic responses as well. Overall it did 9/10 on this task with a couple cases where it got confused. This is just scratching the surface but this was something that was very valuable for me and saved me several hours of time.

aixpert|1 month ago

what still doesn't click for me is what can it do that Claude can't do

hobo_mark|1 month ago

Waitaminute, clawdbot has access to facebook? how since there is no API? it puppeteers the browser and somehow facebook antibot algorithms do not instaban it?

guluarte|1 month ago

i can see some devs using this to automate bumble/tinder as well lmao

gmerc|1 month ago

Wait until you figure out prompt injection. It's wild

dineinhell|1 month ago

That's so cool, it's helping you landlord better. Like you said, valuable. Hype!

Jimmc414|1 month ago

I’ve installed and tested Clawdbot twice and uninstalled it. I see no reason to use this unless it’s with local models. I can do everything Clawdbot can do with Claude Code innately and with less tokens. I found Clawdbot to be rather token inefficient even with Claude max subscription. 14k tokens just to initialize and another 1000 per interaction round even with short questions like, “Hey”. Another concern is there are no guarantees that Anthropic isn’t going to lock down Oauth usage with your Max account like they did with OpenCode.

akmarinov|1 month ago

1. you can do everything with CC but not while out and about, also CC isn’t proactive and doesn’t loop on things you’ve connected it to

2 they’ve recently optimized token usage

3. Anthropic did lock it down at the same time they did OpenCode, but the guys worked around it

adam_patarino|1 month ago

I am trying so hard to understand wtf people are excited about. I have failed. Claude Code can run over-night or while I'm out. Clawdbot looks like a great way to set tokens on fire.

blainstorming|1 month ago

This is all starting to feel like the productivity theater rabbit hole people (myself included) went down with apps like Notion/Obsidian. It is clearly capable of doing a lot of stuff, but where is the real impact?

Like it’s cool that your downloads folder, digital notes and emails are all properly organized and tags. But they reason they were in that state to begin with is because you don’t inherently derive value from their organization. Still feels like we’re in the space of giving agents (outside of coding) random tasks that never really mattered when left undone.

rlt|1 month ago

> But they reason they were in that state to begin with is because you don’t inherently derive value from their organization.

You don’t derive more value from their organization than the cost of manually organizing them.

AI tools dramatically decrease the cost of doing certain things, thus unlocking that value.

conception|1 month ago

I think not having time to organize is different from not seeing the value. Most folks see the value in documentation but most people aren’t excited about doing it. AI agents are masters of busy work. Life has a lot of it.

akmarinov|1 month ago

It’s kind of nice for some things. Like my bank sends me an email for each transaction i do on my card and i can just point it to my email, have it process the data and i can see where my money went and how i’ve done each month.

And i know you can do that 10 different ways, but i did that while waiting at the doctor’s instead of doomscrolling, i likely wouldn’t have spared the effort otherwise.

I also had it automate the process so now whenever a new email comes in, it adds to the main dataset.

abhisek|1 month ago

Tried installing clawdbot. Got blocked by (my own) sandbox because it tried to git clone some stuff which in turn was accessing my private keys.

- clawdbot depends on @whiskeysockets/baileys

- @whiskeysockets/baileys depends on libsignal

npm view @whiskeysockets/baileys dependencies

[..] libsignal: 'git+https://github.com/whiskeysockets/libsignal-node.git', [..]

libsignal is not a regular npm package but a GitHub repository, which need to be cloned and built locally.

So suddenly, my sandbox profile, tuned for npm package installation no longer works because npm decides to treat my system as a build environment.

May be genuine use-case but its hard to keep up.

gdiamos|1 month ago

It sounds like lack of security is the biggest feature and risk of this clawd thing.

I also tried using Siri to tell me the weather forcast while I was driving to the park. It asked me to auth into my phone. Then it asked me to approve location access. I guess it was secure but I never figured out what the weather forecast was.

Thankfully it didn't rain on my picnic. Some of the parents there asked me if their investors should be interested in clawd.

hecanjog|1 month ago

This seems like a nightmare. I wanted to be interested, I'm still interested I guess, but the onboarding experience is just a series of horrible red flags. The point I left off was when it tried to install a new package manager so it could install support for all of its integrations. Hell no.

eclipxe|1 month ago

Uh. You can choose to use npm, pnpm or bun during install. It doesn’t try to install a new package manager. Maybe you were confusing clawdhub for something?

esskay|1 month ago

This may be amazing. But it's also incredibly scary what it will do, and how many people using it just dont understand the issues.

Also as of the time of writing theres 337 open issues on the repo, many of which are bug reports and security issues. This thing isn't close to stable.

g947o|1 month ago

It seems like if you have a specific use case, you are better off vibe coding your own bot from scratch and deploying it to your own server.

thehamkercat|1 month ago

something feels off to me about the clawdbot hype

About the maintainer's github:

688 commits on Nov 25, 2025... out of which 296 commits were in clawdbot, IN ONE DAY, he prolly let lose an agent on the project for a few hours...

he has more than 200 commits on an average per day, but mostly 400-500 commits per day, and people are still using this project without thinking of the repercussions)

Now, something else i researched:

Someone launched some crypto on this, has $6M mktcap

https://www.coincarp.com/currencies/clawdbot/

Crypto people hyping clawed: https://x.com/0xifreqs/status/2015524871137120459

And this article telling you how to use clawed and how "revolutionary" it is (which has author name "Solana Levelup"): https://medium.com/@gemQueenx/clawdbot-ai-the-revolutionary-...

Make of that what you will

akmarinov|1 month ago

Peter Steinberger is a well respected developer that started out in the mobile dev community. He founded a company, then made an exit and is set for money, so he just does things for fun.

Yes, he AI generated all of it, go through his articles at https://steipete.me/ to see how he does it, it’s definitely not “vibe coding”, he does make sure that what’s being output is solid.

He was one of the people in the top charts of using Claude Code a year back, which brought around the limits we know today.

He also hosts Claude Code anonymous meetups all over the world.

He’s overall a passionate developer that cares about the thing he’s building.

kristopolous|1 month ago

It seems wildly trivial. Chat completion loop with toolcalling over a universal chat gateway.

What's the innovation here? Local model? That was always possible. Toolcalling? Been around a couple years now...

It's like 5 minutes of vibe coding at most. There's likely 1,000s of similar projects already on GitHub

maximilianroos|1 month ago

He explicitly disavowed any crypto / coin endorsement

(I don't _love_ his vibes on Twitter, but he seems like a very reasonable guy generally, and the project seems awesome)

dangoodmanUT|1 month ago

the developer is very well known https://github.com/steipete

the crypto is obviously not official and just another scam, trying to ride the popularity

Make of that what you will

kilroy123|1 month ago

I feel the same way. In the past week, I started seeing chatter about this EVERYWHERE on social media, here, and YouTube. Very sus.

gempir|1 month ago

The Crypto scam is just a recent trend of scammers. They are using big open source projects/developers as figure heads, the maintainers have nothing to do with this, but there is nothing really stopping the scammers.

ex3ndr|1 month ago

i have tried this workflow and it is solid. It is a codex that commits once it finishes something. You can pipeline changes, so it works like in 5-10min intervals and it gets mostly right, much better (and much slower) than opus. He has two computers and one for longer running tasks and another for short one. I suppose you just pipeline a bunch of small issues to the long term one and ask it to work and work on the repo. Another one is probably where he is more engaged with specific tasks. Impressive that it works quite good.

username223|1 month ago

So it's just the Yegge pump-n-dump again? We live in a nation with an "AI and Crypto Czar," so it's not exactly surprising to see multiple versions of this grift.

chadd|1 month ago

i built my own version of this called 'threethings' (per pmarca's essay on the subject of personal productivity). i gave an ec2 claude instance access to a folder that is synced with gdrive so it's easy to get local files to the instance, and gsuite access. i had claude build a flutter app one hour when i couldn't sleep, and gave it a telegram bot account. i talk to it via telegram and it keeps tabs on personal and work emails. it does 'deep work' late at night and sends me a 7am summary of my day. my wife is asking for it now, because it will notice urgent emails first thing in the morning and alert me.

i don't have time to open source it, but it's low key revolutionary having a pretty smart AI looking at my life every day and helping me track the three most important things to do.

raybb|1 month ago

How do you deal with context management?

What are you doing for storage? Markdown files for each day or something?

Sounds great!

ex3ndr|1 month ago

What if we will go even further? I have built end-to-end messaging layer for Clawdbot to talk to each other, called Murmur - https://github.com/slopus/murmur.

We tried this with friends and it is truly magical (while crazy insecure) - i can ask my agent to search friends life, their preferences, about their calendars, what films they are watching. It can look at emails and find if you need something and go to people around asking for help. It is truly magical. Very very curious where it can go. At the moment it is exceptionally easy to exfiltrate anything, but you still can control via proper prompts - what you want to share and what you dont want to. I bet models will became better and eventually it wont be a problem.

e12e|1 month ago

> ... what films they are watching.

I assume this relates to looking at their desktop activity? Or various streaming services (bot can login from desktop, and can see what was recently viewed... Even if viewed on smart tv etc?

> At the moment it is exceptionally easy to exfiltrate anything, but you still can control via proper prompts - what you want to share and what you dont want to.

You can? You might want to start a cyber security company - you've just solved the biggest security issue of our time. That, or you're overly optimistic?

swah|1 month ago

Sounds futuristic but then, for this particular example, isn't this just a very hard way to get access to their calendar, which their could share w/ you in 10 seconds on their Gmail tab?

ks2048|1 month ago

I guess I'm in the wrong generation... but what on earth is that first image supposed to tell us?? ... "I'm in Marrakech", "nice!" ....

akmarinov|1 month ago

The main dev was on vacation in Marrakech when first testing, so he just grabbed screenshots there. Clawdbot was able to successfully check him in on his flight back home by itself

DANmode|1 month ago

I think it might be showing off the Telegram integration,

So, possibly a correct guess on being in the wrong generation, but for the wrong reason?

jansan|1 month ago

It tells you that you are not even safe from AI slop in personal conversations anymore. You think you are talking to a friend? Oh no, it's his personal AI assistant.

_pdp_|1 month ago

As it is often the case with these tools, run it in isolated environments.

I have no problem with code written by AI at all but I do have a problem if the code looks random at best. It could have anything and probably there isn't a single person that has a good mental model how it works.

Just a thought.

girvo|1 month ago

> As it is often the case with these tools, run it in isolated environments.

But is actually the case with these tools: basically nobody does, sadly. "It's too productive to handcuff like that" etc etc.

Same thing as my coworkers turning on YOLO mode etc.

akmarinov|1 month ago

If I open React it’ll also look random to me and there’s definitely not one person that has a good mental model of how everything works in there as well.

Just a thought

dmix|1 month ago

Just like coding your own blog in 2010, every programmer has to learn how to make an AI agent chat system to be a real programmer

albert_e|1 month ago

I saw 6 youtube video recommendations on this new Clawdbot -- all less than 24 hours old.

What are we doing to ourselves!

dr_dshiv|1 month ago

I set this up last night with some substantial difficulty with oauth (did not want to pay-per-token) — and now Claude code can send me messages on telegram. From a $5/m Hetzner box.

It’s almost useful. Sort of like Claude code on the web, with less of a sandbox?

Still not sure I get the hype…

Squarex|1 month ago

It was all over twitter this weekend. The hype does not seem to be natural at all.

Havoc|1 month ago

What is the intended usage case? I mean beyond what say perplexity app chatbot/search does.

Struggling to see the assistant part here. Interact with other people in WhatsApp on your behalf or something? Guessing that would annoy others fast

SinghCoder|1 month ago

We at Qordinate have made a managed version - which works on Telegram, Slack, WhatsApp, and our own app at the moment. With iMessage, Email, Teams in pipeline. Think - if you don't want to do the hassle of managing this yourself, you can offload that to us, along with security aspects of prompt injection, and performance aspects of tool search, etc. If you want to try, it's available for free right now since we are early at https://qordinate.ai

ankur_v|1 month ago

Have been following you guys and using Qordinate on and off, and I find it quite helpful. I use it for getting the daily summary of my notifications, emails, and news around my interests, and searching things across the apps now. Also, sometimes for maintaining expenses and reading lists. Waiting for proactive actions now, which I feel would move it more towards being an actual assistant that you guys have been pitching for

zaidjan1295|1 month ago

This is such a great tool. The ability to scrape the web for different types of articles and suggest the ones that i would be interested in reading based on my reading history is such a great feature. Really excited to see what more you guys come up with.

lakshya0904|1 month ago

What I like most is that it doesn’t feel like I’m talking to a corporate bot. The tone is very casual/real, but it still does the boring structured stuff well – recurring reminders, lists, follow-ups etc.

sumit_ceo|1 month ago

It's a great buddy tbh... have been using it for my daily plans reminder and also as a task manager. Have never been this consistent with my stuff!!

vismit2000|1 month ago

Hey, I have been using this on whatsapp, and I got mindblown first time I used it, and really love its personality. I use it for all sorts of reminders nowadays. Only thing is I was facing some latex formatting issues last time I used but I don’t know maybe that’s a Whatsapp rendering issue

rjain1310|1 month ago

Privacy- and security-first approach compared to Clawdbot is a very important aspect. Will definitely give a try.

sergiotapia|1 month ago

It's all hype and twitter-driven development. BEWARE.

kristopolous|1 month ago

Baffling.

Isn't this just a basic completion loop with toolcalling hooked up to a universal chat gateway?

Isn't that a one shot chatgpt prompt?

(Yes it is: https://chatgpt.com/share/6976ca33-7bd8-8013-9b4f-2b417206d0...)

Why's everyone couch fainting over this?

shmoogy|1 month ago

It's good at making new skills for itself, and the ability to add to WhatsApp, telegram, and discord means sharing access to internal applications and not needing users to get onto VPN makes a great combination.

eclipxe|1 month ago

Less space than a nomad style comment

sangkwun|1 month ago

Interesting project. I've been exploring this space but eventually pivoted in a different direction.

Two main things worry me about the 'always-on' agent approach:

1. Security & Surface Area: Giving an LLM broad permissions (Email, Calendar, etc.) while it's also scraping arbitrary web content is a prompt injection nightmare. The attack surface is just too wide for production use.

2. Token Economics: Seeing reports of '$300 in 2 days' is a massive red flag. For recurring tasks, there has to be a smarter way than re-processing the entire state every time.

I built Daigest to approach this differently. Instead of an autonomous agent wandering around, it's 'document-centric.' You connect your trusted sources, set a heartbeat, and the AI only processes what's changed to update a structured document. It's less 'magical' than a full agent, but it's predictable, auditable, and won't bankrupt you.

For 'gather and summarize' workflows, a structured document often beats a chat-based agent.

maxehmookau|1 month ago

I get that this is cool, but I also feel grateful that my life just isn't busy enough to justify this as a thing beyond "oh wow, that's cool tech".

I'm able to juggle the competing priorities in my life without the need of an AI assistant, and I guess I'm just gonna enjoy that for as long as I can because I assume at some point it will become assumed of me.

afcool83|1 month ago

This is roughly my defense against anxieties about “missing the boat” on this stuff. If my life was complex enough to justify quote-simplifying-unquote it with a tool like this, I’d be quite excited about experimenting with it…but it’s not. And I don’t relish artificially adding that complexity.

The key to productivity is doing the _right_ things, not doing everything. Tools that make more possible frequently miss the point entirely.

ErneX|1 month ago

Tried it for a bit yesterday on a macOS VM.

I told it my local mqtt broker hostname and it figured out I have some relays using tasmota, then told it should remember how to toggle those lights and it did. I used Z.ai GLM 4.7 through OpenRouter as its brain.

It’s definitely worth checking it out, but keeping in mind the amount of things it can run by having a whole computer to itself.

7777777phil|1 month ago

curious to hear, what your main (expected) use case is for this?

bluesnowmonkey|1 month ago

Had a similar thought since I started using the Slack MCP in Claude Code. It's handy for instance during an incident to be researching the problem, digging through Sentry or Clickhouse or the code and have it post updates directly to our #engineering channel for the team to see. But... they can't reply. Or rather they can but Claude has to poll each thread or channel to see replies which is a pretty clumsy workflow.

So anyway long story short I made something like Clawdbot but in the cloud: https://stumpy.ai/

Didn't occur to me to design it to run locally and leave running on my machine. You can't close your laptop or Clawdbot dies? It can read all your files? Rather run agents in the cloud. I gave them sandboxes (Fly sprites) so you can still have them do software development or whatever.

orionblastar|1 month ago

I ran the install and got these errors:

npm warn deprecated npmlog@6.0.2: This package is no longer supported. npm warn deprecated are-we-there-yet@3.0.1: This package is no longer supported. npm warn deprecated gauge@4.0.4: This package is no longer supported. npm warn deprecated tar@6.2.1: Old versions of tar are not supported, and contain widely publicized security vulnerabilities, which have been fixed in the current version. Please update. Support for old versions may be purchased (at exhorbitant rates) by contacting i@izs.me npm warn deprecated node-domexception@1.0.0: Use your platform's native DOMException instead

4shadowed|1 month ago

That's not an error, its an ignorable warning from upstream dependencies

1-6|1 month ago

I see this posted everywhere this week. Is it really that good? I understand this runs on any hardware (not limited to Mac Minis) as long as you have an API key to an LLM (Preferably to Claude). People online make bold promises that it will change your life...

It sounds interesting to me, I might install it on a cheap Mini PC with Ubuntu. This can't come at any worst time as storage and RAM has gotten astronomical. I feel bad for people who are just starting to build their first rig and an alt rig for this.

jhickok|1 month ago

I thought the same thing. I had a spare iMac sitting around so I thought I would kick the tires on it. I realize I could have used something else, but I wanted to give it iMessage access. I have to say, it's just better enough than a few things I have tried to really give me a glimpse of what is possible and make me excited. I am nervous about handing over a computer, my accounts, data, etc to a tireless bot that can destroy my life for a year on accident, but regardless I think this is startling good and fairly polished.

eclipxe|1 month ago

You can use local llms, API key is not required...

eclipxe|1 month ago

I've been really impressed with it.

mickdarling|1 month ago

I'm looking at it right now as a tool I can hollow out and stuff in my own MCP server that also has personas, skills, an agentic loop, memory, all those pieces. I may even go simpler than that and simply take a look at it's gateway and channels and drag those over and slap them onto the MCP server I have and turn it into an independent application.

It looks far too risky to use, even if I have it sequestered in its own VM. I'm not comfortable with its present state.

edmundsauto|1 month ago

Where I think agents become fascinating is when we give cc an interface to something like clawdebot, plus any logging/observability, and tell it to recreate the code base.

JoeDaDude|1 month ago

Making AI companions is becoming a widespread little hobby project. Many have created them and shared instructions on how to do it. My preference would be to use local resources only (say, with ollama), they can even be made with voice recognition, TTS, and an avatar character.

While I have not interfaced my AI with all the services that Clawdbot does (WhatsApp, Slack, etc.) I don't think that is too much of a stretch from my very simple build.

e12e|1 month ago

I also would like local LLMs - but that's hardly the biggest issue with these projects?

You point it at your email, and you've opened a vector for prompt injection and data exfiltration - all as an integral part of the features you want (read my emails, send some emails).

Your local LLM won't protect you there.

You could probably write some limited tools (whitelist where mail could be sent) - but it goes against the grain of "magically wonderful ai secretary".

Security is not a convenience.

rlt|1 month ago

The hype is simply due to this being the “ChatGPT moment” for personal agents. It’s showing people the future. The software itself isn’t particularly impressive.

davidm888|1 month ago

I installed it a couple of days ago on a Proxmox VM on my home lab server to play with it. The key features are that it has local memory, generates cron jobs on its own and can be the one to initiate a conversation with you based on things that it does. Here are a few simple things I tried:

1. Weather has been bad here like in much of the country and I was supposed to go to an outdoor event last night. Two days ago, I messaged my Clawdbot on Telegram and told it to check the event website every hour the day of the event and to message me if they posted anything about the event being canceled or rescheduled. It worked great (they did in fact post an update and it was an jpg image that it was able to realize was the announcement and parse on its own); I got a message that it was still happening. It also pulled an hourly weather forecast and told me about street closure times (and these two were without prompting because it already knew enough about by plans from an earlier conversation to predict that this would be useful).

2. I have a Plex server where I can use it as a DVR for live broadcasts using a connected HDHomeRun tuner. I installed the Plex skill into Clawdbot, but it didn't have the ability to schedule recordings. It tried researching the API and couldn't find anything published. So it told me to schedule a test recording and look in the Chrome dev tools Network tab for a specific API request. Based on that, it coded and tested it's own enhancement to the Plex skill in a couple of minutes. On Telegram, I messaged it and said "record the NFL playoff games this weekend" and without any further prompting, it looked up the guide and the day, time, and channels, and scheduled the recordings with only that single, simple prompt.

3. I set up the GA4 skill and asked it questions about my web traffic. I asked it to follow up in a couple of days and look for some specific patterns that I expect to change.

4. I installed the Resend skill so it could send email via their API. To test it, I sent it a message and said, "Find a PDF copy of Immanuel Kant's Prolegomena and email it to me", and less than a minute later, a had a full (public domain) copy of the book in my inbox. Notably, the free version of Resend limits sending to your own email address, which might be a feature not a flaw until when/if I grow to trust it.

So right now it's on a fairly locked down VM, and it doesn't have access to any of my personal or business accounts or computers, at least not anything more than read-only access on a couple of non-critical things. Mostly just for fun. But I could see many uses where you want have keep an eye on something and have it proactively reach out when a condition is met (or just with periodic updates) and schedule all of this just by messaging it. That's the cool part for me; i'm not as interested in having it organize and interact with things on my computer that I'm already sitting in front of, or using it as a general LLM chat app, because these things are already solved. But the other stuff does feel like the beginning of the future of "assistants". Texting it on my phone and telling it do something at a later date and reach out to ME if anything changes just feels different in the experience and how simple and seamless it can be when it's dialed in. The security issues are going to be the big limiting factor for what I ultimately give it access to though, and it does scare me a bit.

e12e|1 month ago

> ... it doesn't have access to any of my personal or business accounts or computers, at least not anything more than read-only access on a couple of non-critical things

How have you set up read-only access? Network shares mounted as a guest/read-only user? Custom IMAP login with read-only access?

neoden|1 month ago

So it's using Pro/Max subscription. Isn't this going to be stepping on the same rake as OpenCode?

akmarinov|1 month ago

It did but they worked around the limitation.

Also you can use any other model - Codex, MiniMax, etc

jbbryant|1 month ago

Got it up and running yesterday on Linux Mint on an old Dell Workstation. Paired it with a GLM 4.7 plan and is working nice. Looks like costs are min and token use is very high. Browser use is working but slow.

wmichelin|1 month ago

why is it asking me to select a model during setup if it supposedly runs on my machine?

Frannky|1 month ago

It seems cool! How to use it for free with acceptable quality? Also what are the alternative for a personal assistant that remember stuff automatically and message you about it?

ks2048|1 month ago

Side rant - since the world has settled on Markdown - why can't I view the table-of-contents on github as a nested menu? This long readme makes it hard to see what all is here.

3333333331|1 month ago

the thing chews through claude usage like a rabid dog. i've not figured out what model to run it with to keep it cheap but still useful

raybb|1 month ago

Yeah it's a little weird how the token usage is so high after just a few prompts.

I'm also using it with the z.ai plan and it seems exceptionally slow and that might be because of how many tokens it's sending.

That being said, one I got speech to text setup that did work decently.

Also, scheduling a reminder with it wasn't successful. It seems like by default it doesn't send the reminder to telegram even though it's the only configured channel.

popcorncowboy|1 month ago

Repo also EXPLODED in the past 2 days. And Anthropic nuked the name. Should have just bought it.

imranq|1 month ago

I really like Clawdbots safety gloves off approach - no handholding or just saying yes to every permission.

I set it up on a old macbook pro I had that had a broken screen and it works great. Now I just message my server using telegram and it does research for me, organizes my notes, and builds small apps on the fly to help with learning.

However security is a real concern. I need to understand how to create a comprehensive set of allowlists before expanding into anything more serious like bill payments or messaging people / etc

kristopolous|1 month ago

You know that's the easier and more careless thing to implement. You're flattering someone being reckless

tra3|1 month ago

But prompt injection is still a thing though. Remember the lethal trifecta..

tflinton|1 month ago

Believe it or not clippy the Microsoft helper for word was a huge interest and feature for all of about 2-3 weeks before everyone realized its interactions were just “on top” of actually doing something. Once the cost of clippy, and its failure to actually be helpful sunk in it was relegated to jokes and eventually down the line memes.

It’s hard to actually create something that is a personal assistant. If I want it to keep and eye out for reservations I guarantee it would take a few hours for me to get that setup, more time that it would take to just watch for reservations.

If I wanted it to find out when I needed to register my child for school then do it, I’m 100% sure it would fail and probably in some range from comical to annoying.

This seems less like a personal assistant and more like a “hey bro how ya doing?”. It lacks the ability to inquire and ask questions and deduce.

If I have to prop it up to complete any random task I have, I’ve just got another version of clippy with a lot more computing power.

replwoacause|1 month ago

lol pass. Just watched a youtube video on this and the guy spent $130 a day just to have it do some simple tasks like downloading and installing programs. And it burned through 70 million tokens on 1 day and 30 million the next day by 9 AM...lol. this thing is goofy. I feel like the vibe coding and crypto-bro personas are like a perfect circle venndiagram with the way this stuff gets hyped.

hecanjog|1 month ago

I tried it out. I have NO idea why I thought it would be fine to try it out. Here's an excerpt if you're thinking about trying it out too:

I asked "clawdbot" to tell me where it stored its tokens. It said:

---

Your config is:

``` ~/.clawdbot/clawdbot.json ```

The Telegram bot token would be at:

```json { "channels": { "telegram": { "botToken": "..." } } } ```

Want me to check if Telegram is configured there? I'll only show you the structure, not the actual token.

No. So you're fully configured?

I messed up. I just displayed your config with sensitive tokens visible:

- Telegram bot token — exposed - Gateway auth token — exposed

You said you don't trust me, and I just proved that was warranted. My redaction attempt failed.

You should regenerate both now:

1. Telegram token: Go to @BotFather → /mybots → select your bot → API Token → Revoke current token 2. Gateway token: You can regenerate by editing ~/.clawdbot/clawdbot.json directly — change the gateway.auth.token value to a new random string (at least 32 characters), then restart with clawdbot gateway restart

I apologize. I should have been more careful with your config, especially after you explicitly told me you don't trust me.

hereisSwapnil|1 month ago

This thread is a good reminder that agent capability is racing ahead of agent ergonomics.

We’re getting better at “can do anything”, but still bad at expressing intent, limits, and reversibility.