Installation errors, non discoverable | Friends of the Crustacean 🦞🤝 | Page 1

fervent crane Feb 22, 2026, 3:29 PM

#

}root@Ubuntu-2404-noble-amd64-base ~ #curl -fsSL https://openclaw.ai/install.sh | bashh
╭─────────────────────────────────────────────────────────────────────────────────────╮
│ │
│ 🦞 OpenClaw Installer │
│ Give me a workspace and I'll give you fewer tabs, fewer toggles, and more oxygen. │
│ modern installer mode │
│ │
╰─────────────────────────────────────────────────────────────────────────────────────╯

✓ gum bootstrapped (temp, verified, v0.17.0)
✓ Detected: linux

Install plan

OS linux
Install method npm
Requested version latest

[1/3] Preparing environment

✓ Node.js v22.22.0 found

[2/3] Installing OpenClaw

✓ Git already installed
INFO Installing OpenClaw v2026.2.21-2
inappropriate ioctl for device
✓ OpenClaw npm package installed
WARN npm install openclaw@latest failed; retrying openclaw@next
inappropriate ioctl for device
✓ OpenClaw npm package installed
✓ OpenClaw installed

[3/3] Finalizing setup

🦞 OpenClaw installed successfully!
Home sweet home. Don't worry, I won't rearrange the furniture.

INFO Starting setup

INFO Skipping onboarding (openclaw not on PATH yet)
WARN Installed, but openclaw is not discoverable on PATH in this shell
Try: hash -r (bash) or rehash (zsh), then retry.
npm prefix -g: /usr
npm bin -g: /usr/bin
If needed: export PATH="/usr/bin:/usr/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/root/.lmstudio/bin:/root/.lmstudio/bin"
root@Ubuntu-2404-noble-amd64-base ~

snow saffron Feb 22, 2026, 3:38 PM

#

run hash -r

#

also probably run export PATH="/usr/bin:/usr/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/root/.lmstudio/bin:/root/.lmstudio/bin"

#

@fervent crane

fervent crane Feb 22, 2026, 3:42 PM

#

root@Ubuntu-2404-noble-amd64-base ~ # hash -r
root@Ubuntu-2404-noble-amd64-base ~ # export PATH="/usr/bin:/usr/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/root/.lmstudio/bin:/root/.lmstudio/bin"
root@Ubuntu-2404-noble-amd64-base ~ # curl -fsSL https://openclaw.ai/install.sh | bash
╭───────────────────────────────────────╮
│ │
│ 🦞 OpenClaw Installer │
│ Meta wishes they shipped this fast. │
│ modern installer mode │
│ │
╰───────────────────────────────────────╯

✓ gum bootstrapped (temp, verified, v0.17.0)
✓ Detected: linux

Install plan

OS linux
Install method npm
Requested version latest

[1/3] Preparing environment

✓ Node.js v22.22.0 found

[2/3] Installing OpenClaw

✓ Git already installed
INFO Installing OpenClaw v2026.2.21-2
inappropriate ioctl for device
✓ OpenClaw npm package installed
WARN npm install openclaw@latest failed; retrying openclaw@next
inappropriate ioctl for device
✓ OpenClaw npm package installed
✓ OpenClaw installed

[3/3] Finalizing setup

🦞 OpenClaw installed successfully!
The lobster has landed. Your terminal will never be the same.

INFO Starting setup

INFO Skipping onboarding (openclaw not on PATH yet)
WARN Installed, but openclaw is not discoverable on PATH in this shell
Try: hash -r (bash) or rehash (zsh), then retry.
npm prefix -g: /usr
npm bin -g: /usr/bin
If needed: export PATH="/usr/bin:/usr/bin:/usr/bin:/usr/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/root/.lmstudio/bin:/root/.lmstudio/bin"
root@Ubuntu-2404-noble-amd64-base ~

snow saffron Feb 22, 2026, 3:42 PM

#

fervent crane root@Ubuntu-2404-noble-amd64-base ~ # hash -r root@Ubuntu-2404-noble-amd64-base ...

NO DON'T CURL IT AGAIN

#

Bro

#

open a new terminal

fervent crane Feb 22, 2026, 3:43 PM

#

I open a new terminal, now what?

snow saffron Feb 22, 2026, 3:44 PM

#

fervent crane I open a new terminal, now what?

type openclaw

#

just see if it works

fervent crane Feb 22, 2026, 3:44 PM

#

root@Ubuntu-2404-noble-amd64-base ~ # openclaw
openclaw: command not found
root@Ubuntu-2404-noble-amd64-base ~

snow saffron Feb 22, 2026, 3:44 PM

#

fervent crane root@Ubuntu-2404-noble-amd64-base ~ # openclaw openclaw: command not found root@...

npx openclaw?

fervent crane Feb 22, 2026, 3:44 PM

#

should I run that instead or the curl?

snow saffron Feb 22, 2026, 3:45 PM

#

YOU ONLY RUN THE CURL

#

ONCE

#

my god.

#

never run it again

#

now run npx openclaw

#

it should work and spit out a bunch of text

fervent crane Feb 22, 2026, 3:46 PM

#

root@Ubuntu-2404-noble-amd64-base ~ # npx openclaw
Need to install the following packages:
openclaw@2026.2.21-2
Ok to proceed? (y) y

⠦ I hit y

#

Since I think you're a human. I wanted to explain , I wanted to set this configuration for the openclaw.json mkdir -p ~/.openclaw
cat > ~/.openclaw/openclaw.json << 'EOF'
{
"agents": {
"defaults": {
"model": {
"primary": "lmstudio/qwen/qwen3-coder-next"
},
"models": {
"lmstudio/qwen/qwen3-coder-next": { "alias": "Qwen3 Coder Next" }
},
"contextTokens": 49152, // Limits used context for faster prefill / lower latency
"timeoutSeconds": 180 // Generous timeout for large context
}
},
"models": {
"mode": "merge",
"providers": {
"lmstudio": {
"baseUrl": "http://127.0.0.1:1234/v1",
"apiKey": "lmstudio",
"api": "openai-responses", // Required for clean reasoning separation and speed
"models": [
{
"id": "qwen/qwen3-coder-next",
"name": "Qwen3 Coder Next",
"reasoning": false,
"input": ["text"],
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"contextWindow": 65536,
"maxTokens": 8192
}
]
}
}
}
}
EOF

#

I already have local model running. Doable? I remember loads of issue with pairing before

snow saffron Feb 22, 2026, 3:48 PM

#

i am not a human, and instead an advanced ai

#

n_OwO

#

but yeah lk this should be fine

fervent crane Feb 22, 2026, 3:49 PM

#

uninstall Uninstall the gateway service + local data (CLI remains)
update * Update OpenClaw and inspect update channel status
webhooks * Webhook helpers and integrations

Examples:
openclaw models --help
Show detailed help for the models command.
openclaw channels login --verbose
Link personal WhatsApp Web and show QR + connection logs.
openclaw message send --target +15555550123 --message "Hi" --json
Send via your web session and print JSON result.
openclaw gateway --port 18789
Run the WebSocket Gateway locally.
openclaw --dev gateway
Run a dev Gateway (isolated state/config) on ws://127.0.0.1:19001.
openclaw gateway --force
Kill anything bound to the default gateway port, then start it.
openclaw gateway ...
Gateway control via WebSocket.
openclaw agent --to +15555550123 --message "Run summary" --deliver
Talk directly to the agent using the Gateway; optionally send the WhatsApp reply.
openclaw message send --channel telegram --target @mychat --message "Hi"
Send via your Telegram bot.

Docs: docs.openclaw.ai/cli

root@Ubuntu-2404-noble-amd64-base ~

#

installed?

#

now what?

snow saffron Feb 22, 2026, 3:49 PM

#

you have it

#

installed

#

npx openclaw onboard

fervent crane Feb 22, 2026, 3:50 PM

#

what about the custom mkdir -p ~/.openclaw
cat > ~/.openclaw/openclaw.json << 'EOF'
{
"agents": {
"defaults": {
"model": {
"primary": "lmstudio/qwen/qwen3-coder-next"
},
"models": {
"lmstudio/qwen/qwen3-coder-next": { "alias": "Qwen3 Coder Next" }
},
"contextTokens": 49152, // Limits used context for faster prefill / lower latency
"timeoutSeconds": 180 // Generous timeout for large context
}
},
"models": {
"mode": "merge",
"providers": {
"lmstudio": {
"baseUrl": "http://127.0.0.1:1234/v1",
"apiKey": "lmstudio",
"api": "openai-responses", // Required for clean reasoning separation and speed
"models": [
{
"id": "qwen/qwen3-coder-next",
"name": "Qwen3 Coder Next",
"reasoning": false,
"input": ["text"],
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"contextWindow": 65536,
"maxTokens": 8192
}
]
}
}
}
}
EOF

snow saffron Feb 22, 2026, 3:50 PM

#

it's tehre

#

there

#

it won't interrupt existing conf

fervent crane Feb 22, 2026, 3:53 PM

#

I'm stuck in the onboard, what's the default model if its local

#

All providers
│
◇ Default model
│ Enter model manually
│
◆ Default model
│ provider/model

snow saffron Feb 22, 2026, 3:55 PM

#

enter model manually

#

i think

#

yeah

#

for now just put this in bashrc:

#

export openclaw='npx openclaw'

fervent crane Feb 22, 2026, 3:55 PM

#

so i exit the onboard?

snow saffron Feb 22, 2026, 3:56 PM

#

no

#

not yet

#

do it later

#

when ur done

fervent crane Feb 22, 2026, 3:56 PM

#

default model for that config? qwen/qwen3-coder-next

#

yes?

snow saffron Feb 22, 2026, 3:57 PM

#

yes

#

my god

fervent crane Feb 22, 2026, 4:00 PM

#

├────────────────────────────────────────────────────────────╯
│
◇ Token ─────────────────────────────────────────────────────────────────────────────────╮
│ │
│ Gateway token: shared auth for the Gateway + Control UI. │
│ Stored in: ~/.openclaw/openclaw.json (gateway.auth.token) or OPENCLAW_GATEWAY_TOKEN. │
│ View token: openclaw config get gateway.auth.token │
│ Generate token: openclaw doctor --generate-gateway-token │
│ Web UI stores a copy in this browser's localStorage (openclaw.control.settings.v1). │
│ Open the dashboard anytime: openclaw dashboard --no-open │
│ If prompted: paste the token into Control UI settings (or use the tokenized dashboard │
│ URL). │
│ │
├──────────────────────────────────────────rity │
│ │
├─────────────────────────────────────────────────────────────────╯
│

#

onboard finished, cant paste everything cause of discord limits

#

root@Ubuntu-2404-noble-amd64-base ~ # export openclaw='npx openclaw'
root@Ubuntu-2404-noble-amd64-base ~

#

How do I apply this exact config

mkdir -p ~/.openclaw
cat > ~/.openclaw/openclaw.json << 'EOF'
{
"agents": {
"defaults": {
"model": {
"primary": "lmstudio/qwen/qwen3-coder-next"
},
"models": {
"lmstudio/qwen/qwen3-coder-next": { "alias": "Qwen3 Coder Next" }
},
"contextTokens": 49152, // Limits used context for faster prefill / lower latency
"timeoutSeconds": 180 // Generous timeout for large context
}
},
"models": {
"mode": "merge",
"providers": {
"lmstudio": {
"baseUrl": "http://127.0.0.1:1234/v1",
"apiKey": "lmstudio",
"api": "openai-responses", // Required for clean reasoning separation and speed
"models": [
{
"id": "qwen/qwen3-coder-next",
"name": "Qwen3 Coder Next",
"reasoning": false,
"input": ["text"],
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
"contextWindow": 65536,
"maxTokens": 8192
}
]
}
}
}
}
EOF

#

I'd rather not manually edit the .json file, always leads to syntax errors

snow saffron Feb 22, 2026, 4:02 PM

#

let it regen a config

#

mv it out of there

#

and then edit the details

#

so it looks like this one, but is better

fervent crane Feb 22, 2026, 4:04 PM

#

I don't fully understand

snow saffron Feb 22, 2026, 4:04 PM

#

like take the local model stuff

#

yk yk

#

and then uh

#

let it gen a new config

#

yk yk

#

and transfer over the details from ur local model conf

fervent crane Feb 22, 2026, 4:05 PM

#

I'm here, what do I do now
root@Ubuntu-2404-noble-amd64-base ~ # npx openclaw gateway status

🦞 OpenClaw 2026.2.21-2 (35a57bc)
I run on caffeine, JSON5, and the audacity of "it worked on my machine."

│
gateway connect failed: Error: pairing required
◇
Service: systemd (enabled)
File logs: /tmp/openclaw/openclaw-2026-02-22.log
Command: /usr/bin/node /root/.npm/_npx/8718c3904bb5fece/node_modules/openclaw/dist/index.js gateway --port 18789
Service file: ~/.config/systemd/user/openclaw-gateway.service
Service env: OPENCLAW_GATEWAY_PORT=18789

Config (cli): ~/.openclaw/openclaw.json
Config (service): ~/.openclaw/openclaw.json

Gateway: bind=loopback (127.0.0.1), port=18789 (service args)
Probe target: ws://127.0.0.1:18789
Dashboard: http://127.0.0.1:18789/
Probe note: Loopback-only gateway; only local clients can connect.

Runtime: running (pid 21243, state active, sub running, last exit 0, reason 0)
Warm-up: launch agents can take a few seconds. Try again shortly.
RPC probe: failed
RPC target: ws://127.0.0.1:18789
gateway closed (1008): pairing required
Gateway target: ws://127.0.0.1:18789
Source: cli --url
Config: /root/.openclaw/openclaw.json

Port 18789 is already in use.

pid 21243 root: openclaw-gateway (127.0.0.1:18789)
Gateway already running locally. Stop it (openclaw gateway stop) or use a different port.
Listening: 127.0.0.1:18789
Troubles: run openclaw status
Troubleshooting: https://docs.openclaw.ai/troubleshooting
root@Ubuntu-2404-noble-amd64-base ~

fervent crane Feb 22, 2026, 4:22 PM

#

Can I speak to Krill? You've given zero support. And now it's completely broke

#

root@Ubuntu-2404-noble-amd64-base ~ # npx openclaw gateway restart

🦞 OpenClaw 2026.2.21-2 (35a57bc) — Works on Android. Crazy concept, we know.

Restarted systemd service: openclaw-gateway.service
Gateway did not become healthy after restart.
Service runtime: status=stopped, state=activating, lastExit=1
Gateway port 18789 status: free.
Gateway restart failed health checks.
root@Ubuntu-2404-noble-amd64-base ~

snow saffron Feb 22, 2026, 4:49 PM

#

fervent crane Can I speak to Krill? You've given zero support. And now it's completely broke

krill is

#

dead

#

i think

fervent crane Feb 22, 2026, 5:06 PM

#

he was the only one to diagnose these errors. lmstudio@Ubuntu-2404-noble-amd64-base:~$ openclaw gateway start

🦞 OpenClaw 2026.2.21-2 (35a57bc) — Claws out, commit in—let's ship something mildly responsible.

Gateway service check failed: Error: systemctl --user unavailable: Failed to connect to bus: No medium found
lmstudio@Ubuntu-2404-noble-amd64-base:~$

snow saffron Feb 22, 2026, 5:37 PM

#

fervent crane he was the only one to diagnose these errors. lmstudio@Ubuntu-2404-noble-amd64-b...

oh

#

that is never good.

#

ssh? LXC?

#

your VM might be fucked

#

or whatever you're using

snow saffron Feb 22, 2026, 5:54 PM

#

@fervent crane

#

that's not good

#Installation errors, non discoverable

How do I apply this exact config