Agent Canvas is the latest way to get

started with Open Hands. Learn how to

use Docker to install on Windows and get

automations on GitHub and Slack.

Windows installation with a Docker

sandbox. You'll need Docker installed.

The Docker command for Windows is

different than the one [music] for Mac.

You'll need to check the Agent Canvas

GitHub Readme for the latest Docker

image. This is just a sample of what you

will run in your terminal.

Run the command to pull the image.

Then set your project path variable and

state path variable. Your project path

is the directory containing the files

you want your agent to have access to.

After that, run the Docker command.

>> [music]

>> Once you see that all services have

started, you're ready to go. Windows

install from source code. You'll need

Node, NPM, and UV installed. [music]

Please note that if you run the agent

server directly on your machine without

a sandbox, the agent will have full

access to your file system. These are

the commands that you'll execute in your

terminal. [music]

First, you'll need to clone the GitHub

repo.

Make sure to clone it in the directory

of your choice.

Once cloned, change into that directory.

Then you'll run NPM install.

Once installation is completed, run NPM

run dev.

When you see the localhost at the end,

you know that you're ready to get

started. Getting started, setting up

Agent Canvas and starting your first

chat. Navigate to localhost:8000.

[music]

You'll then go ahead and go through the

prompt choosing your agent. I'm going to

choose Open Hands.

You'll check your back end. This time it

will be local. Just click next.

Then you'll pick your LLM provider. In

this case, we'll use Anthropic, with the

Claude Opus 4.7. I'm going to input my

API key and click next.

From here, you can see our proven

workflows that you can try out with

Linear, Slack, Notion,

or you can enter your own prompt. We're

going to create a basic webpage

explaining what Open Hands can do. We're

going to click send, and that will open

up a new conversation.

The agent is going to start working on

the prompt given, in this case creating

a webpage. It will reply back in the

chat, and you can preview the webpage on

the right-hand side.

Getting started, [music]

adding Open Hands Cloud backend. Let's

go ahead and hover down to the local

area and click add backend.

We're then going to log in to Open Hands

Cloud. You'll see a new tab pop open

with some letters. That's the name of

this connection. You don't need to save

that. We're going to click authorize,

and then we'll return back to our agent

canvas. Then you'll be able to see that

we are now connected to Open Hands

Cloud. Create an LLM profile.

First, you'll want to navigate to your

settings and click [music] LLM.

From there, you'll click add LLM

profile. You can give that profile a

nickname. [music]

In this case, we are going to call it

MiniMax.

From there, you'll pick an LLM provider.

I'm going to pick Open Hands. I'm going

to pick the model MiniMax M.3, and I'm

going to put my API key in and click

save.

Once you've saved, now you have a couple

of different LLM profiles, and when you

create a new chat, you can pick which

profile you want to start with.

Creating an automation from scratch.

You can create an automation just by

starting a new chat. [music] In this

case, I'm going to create a new

automation where every day at 10:00 a.m.

Eastern, I'm going to have all my GitHub

notifications summarized and presented

to me in a chat.

From there, you can use any LLM model

that you want. I'm using GPT. If it's a

simple request, you can also use

something like MiniMax.

And then [music] the agent will go ahead

and get started on that task. Once it's

done, I'm going to return to the

automate tab, and I'm going to go ahead

and trigger it to run now, only for

demonstration purposes.

Then a chat will get kicked off. We're

going to open it to follow along, and

once it's done, it'll return that

summary of my GitHub notifications. In

the future, you could even set it up

with Slack so that it would send you a

message. Adding an agent canvas [music]

to your Slack server. You'll want to

navigate to api.slack.com/apps. You'll

want to click create an app,

and then [music] from scratch. You'll

then need to give this app a name.

Whatever you want is fine. And then

you'll need to pick a workspace. You'll

need to be admin of that workspace in

order to create and add an application.

Then click create app.

It'll have you return back to this page.

You'll want to scroll down and go to

OAuth and permissions.

Then you'll need to scroll down,

and you're going to want to add an OAuth

scope.

You'll see here that these are the

scopes that you need to add for this to

work.

Once you have all of them, scroll up to

install to dummy hands or whatever your

workspace [music] is called and click

allow. Afterwards, you'll scroll down

>> [music]

>> and there will be a bot user OAuth

token. Please [music] save that for

later.

Return to your workspace and click the

person icon.

From there, you'll want to go to the

integrations tab

and you're going to click add an app.

Once the new page opens up, you're going

to click add for the app, which we named

agent hands. You'll want to return back

to agent canvas and click automate in

the left hand. You'll then click Slack

channel monitor. You're going to put in

your team workspace ID, which you can

find in your URL,

and you'll also need to add that OAuth

bot token we saved earlier.

Once you click install, it'll open up a

new chat with a prompt. If you'd like,

you can go ahead and change the default

name

and then submit it to start the chat.

The agent is going to come back and ask

you a few questions like what channel,

in this case we want general, and also

what name to monitor for, and we are

going to use Joe-bot.

is done, you'll see something similar to

this be returned in your chat.

You can then navigate back to automate

and click [music] on that Slack channel

monitor to see that it is active.

Now, we'll return back to our workspace

>> [music]

>> and go ahead and send a message for our

bot.

Once the bot has seen this, it'll react

with some eyes and start a thread.

You can either go to the localhost URL

or wait for the agent to reply back with

your answer in Slack. Adding GitHub to

your agent canvas. First, navigate to

the automate tab on the left-hand side,

and then go ahead and pick a GitHub

workflow that you want to implement.

[music]

I'm going to pick the GitHub code

review, and I'm going to input my

personal access token,

and click install.

A new chat is going to open with the

skill, and I'm going to enter,

and then I will need to answer a few

questions, like [music] how often do I

want this automation to poll? I'm going

to pick every 5 minutes. I'm also going

[music] to have the agent comment on PRs

that are ready for review, but not

drafted,

and also put the agent's review as a

comment to that PR. And then I'm going

to pick [music] a repository for this

automation to monitor.

Now that the automation is done, just

for demonstration, I'm going to go ahead

and go back to the automate tab, and I'm

going to go ahead and click run now so

that I can get a review for my PR.

Once the job is done, I can go to

GitHub, and I can check out the comment

that was left.

Join our Slack if you have any questions

or comments. Thanks so much for

watching.