- An open‑source personal AI assistant that runs on your own computer. - Designed to be the "Siri that should have existed" – fully customizable, proactive, and capable of accessing any service you connect.

Claudebot: The Open‑Source, Local AI Assistant That Does It All

Matthew Berman

Jan 26, 2026

•

3 min read

YouTube video ID: MUDvwqJWWIw

Source: YouTube video by Matthew Berman — Watch original video

PDF

What is Claudebot?

An open‑source personal AI assistant that runs on your own computer.
Designed to be the "Siri that should have existed" – fully customizable, proactive, and capable of accessing any service you connect.

Core Features

Multi‑model support: Connect to Claude Opus, Gemini, OpenAI, or run local models (e.g., GLM‑4, Quen‑3) via LM Studio.
Persistent memory: Learns your preferences, habits, and frequently used tasks over time.
Proactive automation: Can monitor email, calendar, social media, and trigger actions (summarize urgent mail, draft replies, upload files, etc.).
Full computer access: Executes and iterates on code, interacts with Chrome, drives file operations, and more.
Custom personality: Define a "soul.md" file to give Claudebot any tone or behavior you want.
Extensive integrations: Works with WhatsApp, Telegram, Discord, Slack, Signal, iMessage, Spotify, Obsidian, Twitter/X, Google Workspace, Brave Search, and over 50 native plugins.

Installation & Setup

Visit clog.bot and run the provided curl command.
Answer prompts about:
Which parts of your computer to expose.
Which services (Gmail, Slack, etc.) to connect.
Preferred chat apps for interaction.
Choose your OS (macOS, Windows, Linux) – the installer handles the rest.
Optional: Deploy on a dedicated device (Mac mini, Raspberry Pi, VPS) for isolation, or install directly on your main machine.

Real‑World Use Cases Demonstrated

Video outline generation: Claudebot pulled tweets, view counts, and auto‑filled an ASA card.
Google Drive sync: Compared local video folder with Drive, identified 212 missing files, handled rate‑limit errors, and uploaded missing videos automatically.
Email cron job: Every 5 minutes it checks for urgent emails, summarizes them, drafts replies, and learns to filter out low‑priority outreach.
Model selection: Suggested a faster local model (Quen‑3) for lightweight tasks, downloaded it via LM Studio, and executed it on the fly.
Twitter engagement: Monitored replies to a specific tweet, drafted responses, and posted them with a "from Claude" prefix.

Advantages Over Competing Assistants

Open‑source & self‑hosted – full control over data and model choice.
Hybrid model strategy – mix cloud LLMs with cheap local models.
Memory + Proactivity – remembers you and acts without being prompted each time.
Full OS access – can write, run, and debug code just like a developer assistant.
Community‑driven skills – plug‑and‑play extensions for Google Workspace, Hacker News, Brave Search, etc.

Risks & Limitations

Security: Granting an AI access to Gmail, Drive, and other credentials is a non‑deterministic risk; mistakes can cause irreversible changes.
Cost: Using Claude Opus 4.5 can quickly consume millions of tokens (e.g., $130 in a day). Switching to cheaper or local models is essential to control expenses.
Stability: Early‑stage project (≈2 months old) may crash, enter tool‑call loops, or lose context when memory is compacted.
Voice support: Currently text‑only via chat apps; TTS exists but no dedicated hardware microphone/speaker integration yet.

Tips for Safe, Efficient Use

Ask for a plan before any destructive action (e.g., "Tell me exactly what you will do before uploading the file").
Start with low‑risk tasks to gauge reliability.
Use local models for cheap, repetitive jobs and reserve expensive cloud models for complex reasoning.
Regularly back up the memory file if you rely on long‑term context.
Consider isolated deployment (e.g., a Mac mini) if you want a sandboxed environment.

Future Outlook

Claudebot hints at the next generation of personal AI assistants: truly omnipresent, voice‑enabled, and capable of handling both mundane chores and sophisticated coding tasks. As the community expands and more skills land, the gap between today’s assistants and the vision of a Siri‑like, fully autonomous companion narrows rapidly.

Claudebot proves that a powerful, customizable AI assistant can live on your own hardware, integrate with any service you choose, and automate complex workflows—provided you manage security, cost, and occasional bugs responsibly.

Frequently Asked Questions

Who is Matthew Berman on YouTube?

Matthew Berman is a YouTube channel that publishes videos on a range of topics. Browse more summaries from this channel below.

Does this page include the full transcript of the video?

Yes, the full transcript for this video is available on this page. Click 'Show transcript' in the sidebar to read it.

Helpful resources related to this video

If you want to practice or explore the concepts discussed in the video, these commonly used tools may help.

Raspberry Pi 4 Model B 8gb Recommended

Provides an inexpensive, isolated device to run Claudebot locally, keeping your main computer safe while still offering enough power for most AI tasks

Amazon →

Apple Mac Mini M2

A compact Mac mini gives a dedicated, secure environment for Claudebot with native macOS support and easy integration with iMessage and other Apple services

Amazon →

Dell Precision 7865 Tower Workstation

High‑end workstation with powerful CPUs and NVIDIA RTX GPUs, ideal for running large local models and handling heavy AI workloads without cloud costs

Amazon →

Links may be affiliate links. We only include resources that are genuinely relevant to the topic.

Summarize another video

Full Transcript YouTube

This is Claudebot, the ultimate personal
AI assistant that is open-source, runs
locally, and can basically do
everything. It is what Siri should have
been. I'm going to break down everything
you need to know about it. I'm going to
show you how to use it. And by the end
of this video, you are also going to be
beyond impressed with Claudebot. It
actually helped me researching and
preparing for this video. I connected it
to my ASA. I connected it to Grock. So,
it has all current information, current
tweets, current exposts that I wanted to
include. And check this out. So, I said,
put together a video outline. And here
it is. And it even said, okay, you're
using Obsidian. Here's your hourly cron
job. You're using LM Studio with GLM
4.7. So, it knew everything about
itself. It put it all in here. It pulled
specific tweets, told me how many views
they have, and it added it all
programmatically to this ASA card. It
can run on your machine. You can then
connect it to any of the chat services
that you use like WhatsApp, Telegram,
Slack, and chat with it directly from
those channels. It is so cool to see. It
is essentially cloud code plus cloud
co-work but wrapped up with so much more
capability and then directly accessible
from wherever you are even if you're not
home. And so there are a number of ways
in which this is better than other AI
assistants that I've seen in the market.
One, it is fully open source and you run
it on your own machine. You can connect
models from Gemini, from OpenAI. You can
even run models locally and use those
and you can mix and match as you wish.
So if you have really complex tasks that
you need accomplished, go with Claude
Opus 4.5. But if you're running a cron
job, for example, you could just run it
locally and just have it going. And I'm
doing that with LM Studio. It also has
persistent memory. So as you're using
it, it learns about you. It learns what
you like. It learns what you don't like.
It learns different tasks that you do
often. And that leads me to the third
point, which is it is very proactive.
You could tell it to do things like,
"Check my email and anytime you think I
got a very urgent, important email, go
ahead and message me, give me a summary
of it, and in fact, draft a reply." And
of course, all of this requires you
giving it access to a lot of different
services that you use. And yes, you're
giving your credentials to a
non-deterministic system. So, there are
some risks there. I'll talk about that a
little bit later. And then last and
probably most important is it has full
computer access. You can limit it. You
can put some guardrails on it, but you
are essentially giving Claudebot access
to your computer. But that also means
that it could write code. It can execute
code. It can iterate on that code. It is
essentially what cursor or claude code
or codeex is doing locally. So if you're
already using one of those systems, this
is not that much different. And it has
kind of a unique personality. And that
personality is determined through
something they call a soul.md file. This
is what that looks like. Be genuinely
helpful, not performatively helpful.
Have opinions. Be resourceful before
asking. Earn trust through competence.
Get some boundaries. We have a vibe. And
you can edit it to be anything you want.
So if you have a certain personality in
mind for your Claudebot, you could just
tell it and it will behave like that. It
can be more proactive. It can ask more
questions up front. It can verify things
before trying things. Fully customizable
and again because it's open source and
it already has a thriving community.
There are basically daily updates for
Claude. And it seems everybody on X is
talking about it right now and also
buying Mac minis. I'll explain that in a
moment. So Cloudbot is a 24/7 assistant
with access to its own computer. What if
there were 10 or 100 or a thousand all
running 24/7 in the cloud with access to
your files, your Gmail calendar,
everything about you? Now, I'm going to
break down exactly what access I gave it
and so you can kind of get a sense of
how I'm using it. But why is everybody
buying Mac minis and putting Cloudbot on
it? Well, they basically want an
isolated environment in which to install
Claudebot and to just go crazy, give it
access to the entire system and not
really worry about, ooh, is it going to
also have access to things that I don't
want it to. Now, I took a different
approach. which I just installed it on
my main computer because my thinking is
if I'm giving it access to all of my
credentials anyways, Gmail, Slack,
Telegram, then it is going to have that
even if I put it on its own machine. But
there's something cool also about
thinking that Claudebot has its own
machine. It's kind of living in this
device. So, how do you actually install
it? Well, of course, it depends on what
OS you have. It does support Mac,
Windows, and Linux. So, you just go to
clog.bot. You grab this curl command and
it will install. The installation
process is dead simple. It's going to
ask you a few questions. What areas of
your computer do you want to give it
access to? What services do you want to
install? Which chat apps you want to use
to communicate with it? And more. And so
here are just a few examples of the apps
that it works with. So here's WhatsApp,
Telegram, which is what I'm using,
Discord, Slack Signal, iMessage, which
is really cool. Any of the Frontier
models that I mentioned, you could also
use it with local models. I'll show you
how to do that. In fact, it kind of set
it up itself. It's kind of wild to see
this stuff. Spotify, Obsidian, you can
give it access to Twitter. You can also
give it Chrome access. So, you install a
little Chrome extension and it can
browse Chrome on your behalf. Remember,
again, because it's installed locally,
so it's basically operating your
computer on your behalf. It already has
50 native integrations. And what's
really cool is, as I mentioned, there's
a community and they're already
releasing skills that people have
already tested and proven work really
well. And so if this all sounds very
familiar, if it sounds like claude code
or other agentic coding assistants that
you've used, it basically is. It's just
Claude code wrapped in a bunch of
functionality that makes it really easy
to use as a personal AI assistant. So
here's Claude Hub where you can download
a bunch of skills. So if we go to browse
skills, we could see some that are
available. So here are some of those
examples. We have self-improving agent
which captures learnings, errors, and
corrections to enable continuous
improvement. Now Claudebot has that
built in natively, but this might be a
better version of it. We have Gogg,
which allows you to connect to Google
Workspaces. So that's Gmail, Calendar,
Drive, and I'll show you a use case that
I just did with Google Workspace. Remind
me, you can connect to your home
assistant bird if you want to connect to
Twitter. We have hacker news. We can
connect to Obsidian. We can use Nano
Banana Pro. We can do Brave Search. All
of this stuff is just dead simple. And
the more tools, the more skills that you
give Claudebot, the better it is. So,
one of my favorite things that I gave it
was access to the Gro G
API. And thus, as it's doing research
for me, it has access to X. It has
access to Twitter and everything going
on there. So, it really is incredible at
doing real-time research for me. Here is
my Clawbot running in Telegram. And
remember, I can run this even if I'm not
home. And I can just say, "Hi." And it
starts typing back.
And so, it's actually reminding me about
a previous task that I had going with
it. So, let me tell you about this task
and see if we can get it finalized. So,
this is an example of something really
useful that it can help you with. I have
a bunch of videos locally. Basically,
all the videos I've ever made for my
YouTube channel, I save them on a hard
drive. I zip it up. Then now what I'm
trying to do is upload them to Google
Drive. And I tried to do that, but there
are a lot of videos as you know. And so
halfway through the upload broke. So
some files have been uploaded, others
have not. And I didn't really see an
easy way to do that comparison. So I
asked my Cloudbot to do it. And I said,
"Run a comparison. Here's the folder in
Drive. Here's the folder locally. Let me
know which videos have been uploaded and
which have not. And it ran a bunch of
comparisons and it figured out that
there are 212
missing. So now I'm testing it and I'm
saying, okay, let's try to upload one.
Maybe Claude can do that directly for
me. So we ran into some Google API
errors because we got rate limited. But
now I just said hi again about 15
minutes later and it says rate limit
should have been reset by now. Do you
want me to try to upload again? Sure. So
now just imagine cloud code running in
the background and it's writing code to
actually do the upload and it does say
okay still hitting the rate limit. Let
me check if simple API calls work. Okay,
so this is in fact a Google Drive
problem because I've been uploading so
much recently. You're only allowed to
upload 750 GB per day and I hit that
rate limit and so that's what we're
getting. When we try to upload it's
hitting the rate limit. Okay. And so now
the rate limit for Google Drive has been
removed, and it is working flawlessly.
It ran a comparison of all the files
that I've already uploaded to Google
Drive against all the files that I have
locally, made a list, saved it to my
desktop, and now I'm just saying, go
ahead, upload it for me, then update the
list. Look at this. The .tterar file
says 211 files remaining. I said, okay,
do it again. Choose a larger file. It
shows this video right here. Uploaded
it. Linked me to it. There it is in my
drive. Let's do it again just so you can
see. Okay, do one more. There we go.
Cloud's working. So, I had it start to
tell me which model it's using. So,
that's why it says Opus right there.
Uploading cloud 3.7.zip.
773 megabytes. If we look up here, I can
actually see my internet is going burr.
20 megabytes per second, which actually
on the slower side, but soon enough,
what we're going to see right here is
the uploaded file. Okay, so it's
complete. It gave me the drive link. And
if I check back here, there it is. Just
makes everything so easy. But let me
show you what else we can do. You can
set up different cron jobs. So, for
example, every 10 minutes, go check my
email, look for any urgent emails,
summarize them, draft a reply, and then
let me know. Here I say set up a cron
job for every 5 minutes to check my
email for any urgent emails that need
response, summarize them and then draft
a reply and show me here. So I hit enter
and it starts working. It creates that
crown job. It creates the code to go get
those urgent emails. It does the
determination itself of what counts as
an urgent email versus not. And I
actually tested it. I said, "Okay, tell
me how you define urgent verse not." And
it went out. It grabbed a bunch of
example emails and it said this is
urgent. This is middle priority and this
is low priority. And it was extremely
accurate. Done. Created CROM job
scheduled every 5 minutes. Here's my
account. Check unread emails. Want me to
do a manual check right now. Sure. Okay.
So, found one unread email. Let me get
the full context. So, this is
interesting. It actually didn't find an
urgent email and it corrected itself and
it said this is not urgent. Standard
cold outreach. No draft needed unless
you want me to write one. I'll update
the cron job to better filter out
pitches. And this is another benefit of
using cloudbot. It self-improves as it
goes. And I can simply say remove this
cron job. And now it's not going to run
anymore. And so you can start to get
very creative with the tasks that you
give it with the combination of memory
and cron jobs and access to your
computer, the ability to write and
execute code locally. All of this stuff
is really cool. One other thing I
mentioned is you can run local models.
By the way, if you want to run this
locally, you can also run it on the
sponsor of today's video. And a special
thank you to Dell Technologies for
sponsoring this portion of the video.
Dell's ProMax family of PCs are
incredibly powerful for AI workloads
using the new Grace Blackwell series of
Nvidia GPUs, including GB300 and GB10.
These are absolute monster GPUs in your
desktop. Learn more about DellPro Max
GB10 and GB300 and the Dell Pro Max
lineup of workstations with Nvidia RTX
Pro GPUs. Click the link in the
description below. Let them know I sent
you. Check it out. So, I'm running LM
Studio. I downloaded GLM4, which is a
mixture of experts model with built-in
thinking, which I can't seem to disable
the thinking. And I actually had
Claudebot tell me like, "Hey, is this
the best model to use since I want to
use this? I want really fast responses
and I want to use it for easier tasks,
less sophisticated tasks." And it said,
"Well, it takes about 4 to 6 seconds on
average to get a response. I think we
can get a better model." And literally
through Telegram, I had it tell LM
Studio to download whatever model it
wanted. And it chose Quen 3 mixture of
experts without thinking. So it's very
fast. It downloaded this, remember,
completely remotely. I was out. I was at
a restaurant and I was telling it to do
this. It was really mind-blowing. So, LM
Studio downloaded it and now we have
access to it. So, just to show you it's
working, run this prompt on Quen 3 and
LM Studio. Tell me a short story, then
reply back with its response. Now, I
shouldn't have to explicitly tell it to
run Quen 3 on LM Studio. And in fact,
you can actually set up a daisy chain.
In my daisy chain of large language
models, I'm using Opus 4.5 Haiku and I'm
using Quen 3 locally. So here it is,
Quen 3 response. And if I open up LM
Studio, we can see the developer logs.
This is it. So we know it actually used
the local model. And I can explicitly
tell it use the local model for cron
jobs for easy tasks. And it will
remember to do that. Now, it's not
perfect. I will say that sometimes it
just thinks, okay, I think I'm just
going to use Haik coup here or I'm going
to use Opus 4.5. And I think with
subsequent versions, subsequent updates
of Claude, it's going to be better at
knowing when to use which model. And if
I tell it to use a specific model, it's
going to be much better at actually
listening to what I'm telling it. But
for now, it's pretty good. Here's what
that looks like. I have Claude opened
and it suggested using Quen 3 and I
said, "Can you install it for me?" I
didn't even know if it was possible.
Downloading now. And it was downloading
it. It gave me updates along the way. It
said it stalled, but then said, "Nope,
it downloaded. Here it is. LM Studio."
And it updated tools.md to say when to
use that local model. I also gave it
access to my Twitter and I asked it,
okay, every few minutes grab all the
replies to this post, tell me the ones
that I haven't replied to, draft a
reply, and then wait, let me tell you if
I want to publish it or not. So, here's
an example. Someone said, "Hide
Claudebot," and it said, "Hey, drafted
and sent with Claude." Here's another
one. Drafted and sent with Claude.
Greetings, Claude. Drafted and sent with
Claude. So, what's the best utility you
found so far? Email plus calendar
awareness. Boring, but immediately
useful. It checks my three inboxes and
tells me what actually needs attention.
Drafted and sent with glad. That is
based on what it is actually doing for
me. So, I asked it to show me its memory
file. So, let's take a look at what it
knows about me so far. So Matt's
preferences writing always use the
humanizer skill. So that's something
that I installed to make it sound more
human, less AI. And that's a skill that
you can install on cloud code. And
because you can install it on cloud
code, you can install it in cloudbot. I
use superhuman for email. I use Slack.
Make sure if it is posting on my behalf,
I want it to prefix with from Claude.
Here are my email accounts. Not going to
show those. I am an early bird. usually
up at 7:00, probably earlier, but that's
the first I want to hear from it. I have
a show called Forward Future Live. My
wife and I often times share calendars,
so sometimes stuff she's doing shows up
on mine and I don't want it to get
confused about that and think I'm busy.
So, it's using its judgment as it says
here. If it looks like a joint event or
something, he'd attend, remind him.
Remember I said, okay, it determined
what is high priority versus medium and
low here. That is so meetings and
calendar invites high priority partner
communication medium priority sponsor
pitches guest bookings and then low
newsletters LinkedIn and marketing
access to Grock. It has access to
Twitter and that is what it knows about
me so far. And then I said show me your
soul. Again the cool thing is you can
basically modify it all you like
directly from Telegram. So it it's like
selfch changing self- evvolving. It's
kind of wild to think about. A couple
other things, it uses sub agents, so you
can have a conversation with it, kick
off a sub agent, it's going to go do its
thing in parallel, and then come back
when it's done, and you can continue
talking. It does not lock up
synchronously. You can also cue up
multiple tasks. So, if I type, tell me
the date, and then I say, tell me the
date again, I can cue those up and it
will do it and then go to the next one.
So, there you go. So, you can ceue up as
many tasks as you want. Obviously, this
is quick and easy, but if you have a
more complex task, you can set it off
and do your next thing. It's not all
perfect. Let me break down some of the
issues. One, certainly there is a
security risk. You're dealing with
non-deterministic systems and you're
giving it access to really important
things like Gmail and Calendar and Drive
and whatever other services you want to
give it access to. You're basically
giving it to an AI to act on your
behalf. Sometimes it's going to make
mistakes. Sometimes it's going to make
an irreversible change that is painful
for you. So, this is really right now
for more power users. You really have to
understand the consequences of what
you're asking it. And it's really
important to think about it as you're
prompting it. So, for example, for that
Google Drive task, I said, "Okay, tell
me exactly what you're going to do
before you do it." and let's test it
with one file before trying to upload
all of them. It also has rough edges. It
is far from perfect. It is a project
that is only 2 months old. I believe
it's only a solo developer building it,
but there is a growing community. But
that means there are problems. And just
like any artificial intelligence system,
there are things where you're looking at
it, you're like, I I'm pretty sure you
should be able to do this or how did you
make that mistake? How did you forget
about that? And speaking of forgetting,
memory compaction still is an issue. And
it's not specific to Claude, but any AI
system when you're compacting the
memory, when you're taking all of the
memory that you have given it, and at a
certain point, it needs to start
compressing that memory because you've
hit the context window limit. When you
compress the memory, it loses detail.
So, it might forget something that you
told it in the past, and you're like,
"Oh my god, how do I have to keep
telling you that?" And the way to solve
that is to continue to help it memorize
those things. So just tell it, no,
explicitly write this down. Crashes also
happen. And I was out of my house
yesterday and all of a sudden I got into
this weird tool call loop and it was
basically broken. It I could not use it
anymore. Any message I would send, it
would tell me that the tool call was
malformed and I had to wait until I got
home and I restarted the system and then
it finally worked again. And next, it's
not free if you're using Claude.
Obviously, if you're using different
Frontier LLMs and you're giving
Claudebot your API key, it's using
tokens and it costs money. So, for
example, just yesterday I used 70
million tokens. The vast majority of
which it chose to use Claude Opus 4.5.
Some you can see Haiku 4.5 right there.
Then today, just so far and it's only
9:30 in the morning, 25 million tokens
total. Now, for costs, that is a lot
more than I thought it would be. Holy
crap, it is very expensive. In fact, I'm
just seeing it now. I'm kind of
surprised. So, yesterday I paid about
$130.
Today, we're already up to $32. So,
immediately I'm thinking, how do I start
using other models that aren't so
expensive? So, that's where local models
start coming into play. So, you really
need to be careful. Obviously, I need to
be careful about costs. very cool
project. I think this is something
special. I do recommend trying it out.
Just be careful. If you're really
worried, install it on a VPS, but
definitely give it a try and get a feel
of what is likely to be the future of AI
assistance. Now, I mentioned this is
what Siri should have been, and the one
piece missing is some hardware device
that I can actually speak to and have it
talk back to me. Having to type
everything out is great, but I really
want to be able to have a voice
assistant powered by Cloudbot. So, it
would be cool if it worked via my phone.
I'm sure there's going to be a skill
released soon that allows for that, but
for now, it's all through Telegram or
whatever chat app you're using. Now, it
does have TTS support, so you can use
your voice, but it all goes through
whatever chat app you're using. Go try
it out. Let me know what you think. If
you enjoyed this video, please consider
giving a like and subscribe.