Setup is done and the script printed SMOKE OK. This page is everything that
comes after: your addresses and logins, the handful of commands you need, how
to get your own files in and out, how to update, and what to do when something
goes wrong. Bookmark it β you wonβt need the setup guide again.
Everything with a ./kingo in it is typed in the Ubuntu app, inside the
kingo-pod folder.
Your services
Use your normal Windows browser β WSL2 forwards localhost from Ubuntu to
Windows automatically. If setup had to move a port your addresses differ from
the defaults below β ./kingo credentials always prints the truth for your own
laptop:
| Service | Address | Login |
|---|---|---|
| Langflow | http://localhost:7860 | none (logs in automatically) |
| n8n | http://localhost:5678 | create your own account on first visit |
| JupyterLab | http://localhost:8888 | none |
| JupyterHub | http://localhost:8000 | any username + password kingo2026 |
| Metabase | http://localhost:3000 | admin@kingo.local / Kingo2026! |
| CloudBeaver | http://localhost:8978 | student / Kingo2026! β how to connect |
| Qdrant | http://localhost:6333/dashboard | none |
| PostgreSQL | localhost:5432 |
student / kingo2026 (db: classroom) |
Not all of these run at the same time: in abp mode β what setup installs β
only Langflow, n8n, Mail, CloudBeaver, Qdrant and PostgreSQL are on, and
./kingo credentials marks the others as off. See Modes
for switching.
CloudBeaver looks empty at first (βNo Connectionsβ) β you have to log in via the gear icon β Login before the class database shows up, and give it the database password once. Two minutes, step by step: Using CloudBeaver.
MCP (Model Context Protocol) is how AI assistants such as Claude Desktop,
Claude Code, or Cursor connect to tools. Point yours at the Jupyter MCP
endpoint http://localhost:4040/mcp (header
Authorization: Bearer kingo-mcp-2026) and it can write and run code in the
class notebook for you. ./kingo mcp prints exactly this.
OpenCode (AI coding in the terminal) runs inside your Ubuntu β install it once with:
curl -fsSL https://opencode.ai/install | bash
then run opencode. The first run asks for an API key; change it anytime with
opencode auth login.
Everyday use
Open the Ubuntu app and go to the class folder:
cd kingo-pod
then one command per job:
| Command | What it does |
|---|---|
./kingo up |
start everything (your data stays between runs) |
./kingo down |
stop everything |
./kingo status |
which services are up? |
./kingo credentials |
my addresses + logins |
./kingo mode |
which services run β and ./kingo mode full / abp / β¦ switches (see Modes) |
./kingo memory |
how much memory the containers have and use |
./kingo mail |
set up the mailbox for the mail assistant (n8n workshop); ./kingo mail help shows the rest |
./kingo claude |
start Claude Code, your coding agent, in its sandbox (see Claude Code) |
./kingo claude --login |
the same with your Claude subscription in place of OpenRouter (see Your Claude subscription) |
./kingo shortcuts |
short commands for your terminal, such as kc for Claude Code and kc . for Claude Code in the folder you are in (see Shorter commands) |
./kingo doctor |
somethingβs wrong? start here |
./kingo version |
which version am I running? (send this when you ask for help) |
./kingo update |
get the newest class files + images (run it when the instructor announces an update) |
What if I just close the Ubuntu window? Nothing breaks β the stack keeps running in the background: your services stay reachable in the browser, and it keeps using its memory (about 3 GB in abp mode, up to 6 GB in full mode). It stops only when you run
./kingo downor shut down / restart Windows. Your data survives all of these β closed windows,down, reboots. After a reboot, open Ubuntu and run./kingo upagain. (Docker Desktop users: the stack may come back by itself when Docker starts β./kingo statusshows whatβs up.)
Modes: which services run
Not every class week needs all ten services, and an 8 GB laptop cannot run them all comfortably. A mode is the set of services that runs β the others are simply off (nothing is deleted; every mode keeps your data):
| Mode | What runs | Memory it wants |
|---|---|---|
abp (what setup installs) |
Langflow, n8n, Mail, CloudBeaver, Qdrant, PostgreSQL | 4 GB |
full |
all ten services | 6 GB |
bi |
JupyterLab, JupyterHub, Jupyter MCP, Metabase, CloudBeaver, Qdrant, PostgreSQL | 4.5 GB |
langflow |
Langflow, PostgreSQL | 3.5 GB |
n8n |
n8n, Mail, PostgreSQL | 2.5 GB |
./kingo mode shows the current one. Switching is one line, for example:
cd ~/kingo-pod && ./kingo mode full
It takes about a minute: the stack stops and comes back with the new set of
services. Your notebooks, dashboards, flows and workflows are all still
there β switch back any time with ./kingo mode abp.
On Windows there is no memory setting to make: Windows lets WSL use up to
half of the laptopβs memory by default (4 GB on an 8 GB laptop) and takes
back whatever the containers do not use. abp, langflow and n8n fit that
default; bi and full on an 8 GB laptop will run, but slowly β kingo
says so when you switch. ./kingo memory shows what the containers have and
use, and which modes fit.
Your own files β the shared folder
shared is a folder inside kingo-pod that both you and Langflow can see.
Put your own files there: a SQLite database, a CSV, an Excel sheet, a PDF.
It is one folder with two names, because you and Langflow look at it from different sides:
| Looking from | The folder is called |
|---|---|
| your laptop (Ubuntu, or File Explorer) | ~/kingo-pod/shared |
| inside Langflow | /app/shared |
So a database you drop in as ~/kingo-pod/shared/trials.sqlite is
/app/shared/trials.sqlite when you type it into a Langflow component. It
works the other way round too: whatever Langflow writes there shows up on your
laptop. The folder is made for you β if it is not there, run ./kingo update
once.
Opening a SQLite file in Langflow? The SQL component wants a database URL, not a path, and an absolute path takes four slashes:
sqlite:////app/shared/trials.sqlite.
Where is the folder in Windows? Ubuntuβs files show up in File Explorer. Open Explorer and follow the left sidebar:
Linux β Ubuntu β home β your Linux user name β kingo-pod β shared
Your Linux user name is the one you chose when Ubuntu first started, so your
folder is not called frank like the one in the picture. You can also paste
\\wsl.localhost\Ubuntu\home\ into the address bar and click on from there.

Drag files in and out like in any other folder. Langflow sees them at once.

Quickest way there from Ubuntu β this opens the folder in Explorer:
cd ~/kingo-pod/shared && explorer.exe .
Then right-click shared in Explorerβs sidebar β Pin to Quick access, and it is one click away from then on.
Keep private files out of it. Anything running inside Langflow can read, change and delete what is in this folder β including a flow someone else built and you imported. Never let it hold your only copy of something. Nothing outside this one folder is reachable from Langflow.
Using Docker Desktop? Files that Langflow itself writes into the folder end up owned by
rootinside Ubuntu β deleting those needssudo rm. Files you put in are never affected. With Podman (the default) this does not happen.
Claude Code β your coding agent
Claude Code is an AI that works with you in the Ubuntu app. It reads and writes files, runs commands, and in kingo-pod it can change your n8n workflows, your Langflow flows and your database. It uses the model GLM 5.3 Flash, paid with the OpenRouter key Yanbo gave you.
It runs in a sandbox called nono: on your laptop it can write in one
folder only, ~/kingo-pod/claude. It can read the rest of kingo-pod to
understand the stack, and nothing else on your laptop.
Install it once. One line installs the database tool psql and Claude
Code (it asks for your Linux password):
sudo apt install -y postgresql-client && curl -fsSL https://claude.ai/install.sh | bash
nono you do not install: ./kingo claude gets the version it needs by
itself, the first time you start it.
Already use Claude Code? Run the line anyway: it installs Claude Code the way Anthropic recommends, or brings it up to date. Your own settings and your login stay as they are. Did you install Claude Code in Ubuntu with npm instead? Then you now have two installations.
./kingo claudealways takes the new one. To keep only the new one, remove the old one:npm uninstall -g @anthropic-ai/claude-code.
Make a key in n8n for Claude. In n8n, click Settings at the bottom of
the left sidebar, then n8n API, then Create API key. Label: claude.
Expiration: Never. Click Save and copy the key: n8n shows it only once.
Start it:
cd ~/kingo-pod && ./kingo claude
Always start it this way: only ./kingo claude (or ./kingo yolo) sets it
up for the course. A plain claude is a standard Claude Code with
Anthropicβs settings β no sandbox, no keys, your own ~/.claude.
The first time, it asks for two keys: your OpenRouter key and the n8n key you
just made. Paste each one (right-click in the Ubuntu window) and press Enter;
you do not see a key as you paste it. The key for Langflow it makes by itself.
Then Claude Code asks a few questions of its own: pick a look, and say Yes
when it asks whether you trust the folder. To stop, type /exit. Every next
time, ./kingo claude starts it right away.
The first start may also ask Install them now? These are a few packages of Ubuntu that the browser needs, with which Claude looks at the pages it writes. Press Enter for yes, and type your Linux password.
Hard to read? Type
/themein Claude Code and pick another look./themechanges only the colors of the text. The background is not Claude Codeβs: it belongs to your terminal, and you change it in the settings of the terminal (in the Ubuntu window: the arrow next to the tabs, Settings, Ubuntu, Appearance, Color scheme).
Tell it your teamβs rules. Claude reads the file
~/kingo-pod/claude/AGENTS.md at every start. Paste your teamβs copy of
ws2_rules.html into it, below the heading Your teamβs rules, as the
file explains, then start Claude again. kingo writes the part above the
heading anew at every start, and a line of yours there it moves below the
heading. This line opens the file in Notepad:
cd ~/kingo-pod/claude && notepad.exe AGENTS.md
| Claude can | Claude cannot |
|---|---|
read and write in ~/kingo-pod/claude |
write anywhere else on your laptop |
read kingo-pod: compose.yml, the guides |
change kingo-pod, or run ./kingo |
| change your n8n workflows, Langflow flows and database | see your keys: it gets stand-ins |
| look things up on the web | see your own Claude Code settings, if you use Claude Code already |
look at the pages it writes, and click through them as a person would (look, clickthrough) |
open http addresses on your laptop, apart from your dev server with clickthrough --dev 5173 |
It asks before every command, unless you start it with
./kingo yolo. Inside the sandbox, Claude Codeβs requests for permission do not
protect your laptop β the sandbox does that either way β but they show you every
change to your workflows, flows and database before it happens. Without them,
save your workflows and flows first with ./kingo backup (your own tables are
not in it). And only run a command in your
own Ubuntu window if you understand it: Claude cannot leave its sandbox, but a
command you type can.
A key stopped working?
./kingo claudechecks the keys at every start. A key that a service refuses is deleted, and the next start asks for it again. The keys are kept in~/.config/kingo/, where Claude cannot read them.
Your Claude subscription (optional)
Do you have a Claude subscription (Pro or Max)? Then Claude Code can use it in place of OpenRouter: Anthropicβs models, paid by your subscription. The course does not need this. Everything else stays the same: the sandbox, n8n, Langflow, the database, and your OpenRouter key, with which Claude can try the models of your flows.
cd ~/kingo-pod && ./kingo claude --login
The first start shows a long address in the Ubuntu window. Copy it, open it in
your browser in Windows, log in to Claude there and allow the access. The page
then shows a code: copy it, paste it into the Ubuntu window (right-click) and
press Enter. The window then says Logged in., and Claude Code starts.
Every next time, ./kingo claude --login starts Claude Code right away.
- Back to OpenRouter: start with
./kingo claude, as before. Both ways stay set up, side by side. - One session at a time. Two sessions with
--loginat once break the login, sokingodoes not start a second one. Close the first session, then start the new one. - Claude Code says that you are not logged in? Run
./kingo claude logout, then start with--loginagain. - End the login:
./kingo claude logout.
Where the files are:
| What | Where |
|---|---|
| your work | ~/kingo-pod/claude, the same folder as without --login |
settings and history of the sessions with --login |
~/.kingo-claude-login |
| settings and history of the sessions without it | ~/.kingo-claude |
| your login | ~/.local/state/nono/oauth-capture |
The login is kept by nono, outside the sandbox, for up to 90 days. Only you can read that folder on your laptop; it is not encrypted. Claude Code gets stand-ins, which are of no use outside the sandbox. To remove the login from your laptop for good, log out and delete the folder in the Ubuntu window:
./kingo claude logout && rm -rf ~/.local/state/nono/oauth-capture
The folder holds only this login, unless you use nono for other tools too.
Shorter commands (optional)
One command adds short commands to the Ubuntu window, so that you need not go
to ~/kingo-pod and type ./kingo first:
cd ~/kingo-pod && ./kingo shortcuts
It shows a list. Type the numbers you want, for example 1 3 5, and press
Enter. Enter alone takes all of them.
| Shortcut | What it does |
|---|---|
kc |
Claude Code for the course (./kingo claude); kc . in the folder you are in, kc ~/projects/thesis in that folder |
kcl |
the same with --login: your Claude subscription |
ky |
the same as kc, with ./kingo yolo: Claude works without asking |
kyl |
the same with --login |
kingo |
./kingo from any folder, for example kingo status |
They work in every new Ubuntu window, from any folder:
kcalone starts Claude Code for the course, as./kingo claudedoes.kc .starts Claude Code in the folder you are in, andkc ~/projects/thesisin that folder, without the course: it writes only in that folder, and there is no n8n, Langflow or database. Not in your home folder itself, and not in a Windows folder (/mnt/c/...): make a folder first, for examplemkdir -p ~/projects/thesis. In~/kingo-pod,kc .is the course again, and the window says so in one line.
kingo writes the shortcuts into ~/.bashrc, between two lines that it marks,
and keeps a copy of the file first. If you use one of these names already,
kingo asks before it writes it. ./kingo update writes them anew when kingo
changes them. To take them out again: ./kingo shortcuts remove.
Keeping up to date
One line brings your installation up to date β newest class files, images and rebuilt containers. Safe to run any time in Ubuntu, from any folder:
cd ~/kingo-pod && ./kingo update
Run it whenever your instructor announces an update. It works for every
install, however old β nothing has to be downloaded by hand. Before a new
version starts, it saves a copy of your Langflow flows and n8n workflows in
kingo-pod/backups/, so your instructor can bring them back if something
goes wrong.
Optional this term: Kingo 1.5. It brings Langflow 1.12, which fixes a
memory bug in Langflow 1.8: chats with the same name share one memory, even
in different flows.
./kingo update does not install it by itself. Read
the optional upgrade to Kingo 1.5 and decide with your team
first.
If something breaks
Always start with one command (in Ubuntu, inside kingo-pod) β it checks
the usual suspects and tells you what to do:
./kingo doctor
| What you see | What to do |
|---|---|
Cannot connect to the Docker daemon at unix:///run/user/β¦/podman.sock |
Podmanβs API socket is off. Run systemctl --user enable --now podman.socket, then ./kingo up. (Current versions of setup and kingo do this automatically β git pull gets you there.) |
Other software on this machine is already using ports Kingo needs |
Run ./kingo fixports, then ./kingo up. Kingo moves itself to free ports β your other software is untouched. Your addresses change; ./kingo credentials shows the new ones. |
Same message right after ./kingo down, but you started nothing new |
No real collision β the port forwarding didnβt let go. First just run ./kingo up again (current kingo frees such leftovers where it can β get it: ./kingo update). If it persists: ./kingo fixports moves past it, or run wsl --shutdown in Command Prompt (Windows) and reopen Ubuntu β note: that stops everything running in WSL (including Docker Desktopβs backend), not just Kingo. |
The Kingo stack is ALREADY RUNNING under your other engine |
Nothing is broken β the stack is up under your other container engine. Follow the two commands the message prints. |
ALL of Kingo's ports are busy |
The stack is most likely already running (possibly under your other engine). Run ./kingo status β if services show up, youβre done, nothing is wrong. |
| I have Docker Desktop, but setup installed Podman | Docker wasnβt running or its WSL integration was off during setup. Both engines work β no need to change anything. To switch anyway: turn on WSL integration for Ubuntu, then ./kingo down (stops the Podman stack first), then echo KINGO_ENGINE=docker >> .env.local, then ./kingo up. |
| Laptop feels slow (8 GB machines) | Run a lighter mode: ./kingo mode abp β or, for one tool at a time, ./kingo mode langflow or ./kingo mode n8n. Windows, the containers and everything you run share the same 8 GB β above all a browser with dozens of tabs, which alone can take 2β3 GB (the Langflow and n8n tabs count too): close what you do not need. ./kingo down when you are not using the stack also helps. |
Ubuntu terminal says ./kingo: No such file or directory |
Youβre in the wrong folder. Run cd ~/kingo-pod first. |
| Anything else | ./kingo down, then ./kingo up. If it persists: screenshot the error and ask the instructor / TA. |
FAQ
Why Podman and not Docker? They do the same job and this stack runs identically on both (our tests run on both, every day). We default to Podman because itβs fully open-source and free for everyone β Docker Desktopβs license requires payment at larger companies, and we donβt want the tooling you learn to expire with your student status. If Docker Desktop is already on your laptop, the setup script simply uses it β you are not missing anything either way.
I already use Docker / have my own database. Will this break my stuff?
No. Kingo runs in its own containers (all named kingo-β¦) with its own
storage. The only possible overlap is a port number β and setup/fixports
resolves that automatically by moving Kingo, never your software.
The passwords are printed in a public repo?! Yes, on purpose. Every
service is reachable only from your own laptop (127.0.0.1 β people on
the same Wi-Fi cannot connect; WSL2βs localhost forwarding keeps it that way).
So these are classroom conveniences, not secrets. The one real rule: the class
shares an n8n encryption key, so never put a real API key into an n8n
workflow you share or export.
Where is my data? Databases, notebooks, and workflows live in container
volumes inside WSL2 and survive ./kingo down, reboots and mode switches.
Only ./kingo reset deletes them (it asks first).
Where did Jupyter and Metabase go? They are off in abp mode, which is
what setup installs β ./kingo status and ./kingo credentials say so.
./kingo mode full turns everything on (about a minute; see
Modes); the instructor announces when a class
week needs it.
Can I give the containers more memory? Not through kingo, and on an
8 GB laptop it would not help: whatever WSL takes, Windows no longer has, so
the fix is a lighter mode (./kingo mode abp). The half-of-the-laptop limit
is Windowsβ own setting (a .wslconfig file). If you know your way around
that file, changing it is your own project β kingo neither needs it nor
touches it.
Can I use extra Python packages (say, statsmodels)?
- JupyterLab (
:8888) already ships the data-science standards β pandas, statsmodels, scikit-learn, seaborn, and friends. For anything else, run%pip install <package>in a notebook cell (repeat it if the stack was restarted since). - Langflow: the class set (statsmodels, ragas, β¦) is built in β
import statsmodelsjust works in Python components. Need one more?./kingo langflow pip install <package>installs it on the spot; it lasts until the next./kingo down+up, so run it again after that (or ask the instructor to add it for everyone). If the install upgraded a compiled package (pyarrow, numpy, pandas β pip lists what it installed), run./kingo restart langflowbefore building a flow: the running Langflow still has the old one loaded, and the build would otherwise fail with βsize changed, may indicate binary incompatibilityβ. - JupyterHub (
:8000) starts a minimal Python without the data packages β use%pip installthere too, or simply do data work in JupyterLab.
Where are my Windows files inside Ubuntu? Your Windows drives are mounted
under /mnt β e.g. C:\Users\you\Documents is /mnt/c/Users/you/Documents.
How it all fits together
ββ Your laptop (Windows) βββββββββββββββββββββββββββββββββββββ
β β
β Browser, KNIME (on Windows) β
β β always talk to localhost:<port> β
β βΌ (WSL2 forwards localhost into Ubuntu) β
β ββ Ubuntu on WSL2 (Windows' built-in Linux) ββββββββββ β
β β β β
β β container engine (Podman or Docker) runs one β β
β β container per service: β β
β β [Langflow] [n8n] [JupyterLab] [Metabase] ... β β
β β β β β β
β β ββββββββββ΄βββΊ [PostgreSQL] [Qdrant] β β
β β β β
β β containers reach each other by service NAME: β β
β β postgres:5432, qdrant:6333 β β
β ββββββββββββββββββββββββββββββββββββββββββββββββββββββ β
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
Two address rules cover everything:
- From your laptop (Windows browser, KNIME): always
localhost:<port>. - From one service to another β e.g. an n8n workflow or Langflow flow
connecting to the database: use the service name as host, not
localhost. PostgreSQL: host
postgres, port5432, databaseclassroom, userstudent, passwordkingo2026. Qdrant:http://qdrant:6333. (Inside a container,localhostmeans the container itself β the most common mistake. Rule 2 is also why moved host ports never affect service-to-service connections.)
KNIME (optional)
KNIME runs on Windows itself, not inside Ubuntu: download KNIME
Analytics Platform from https://www.knime.com/downloads and install it
like any other program. To use the class database, create a PostgreSQL
connection with host localhost, port 5432 (or your moved port from
./kingo credentials), database classroom, username student, password
kingo2026. The stack must be running (./kingo up in Ubuntu) while you use
it.