Can't access the dashboard

[grand salmon]

I entered the token and it could not connect. I tried trouble shooting with Claude but it did not work. This is my second time trying to install and setup openclaw. Please help. 🙏

[tame coyote]

To help others find answers, you can mark your question as solved via Right click solution message -> Apps -> ✅ Mark Solution

[woeful solar]

First thing: please run this and share the output:

openclaw --version
openclaw status --all
openclaw gateway status

Don’t paste any gateway token/password here.

For dashboard auth, the usual checks are:

1. Open the dashboard with:

openclaw dashboard

or locally: http://127.0.0.1:18789/

[woeful solar]

2. In the Control UI, go to Control → Overview → Gateway Access. There are two separate fields: Gateway Token and Password. Put the secret in the matching field for your config, then click Connect.

3. If it says disconnected (1008): pairing required, approve the browser/device:

openclaw devices list
openclaw devices approve <requestId>

Run openclaw devices list again right before approving, because retries can create a newer request ID.

4. If you don’t know what token/password is configured, run:

openclaw config get gateway.auth

If there is no token configured, this can generate one:

openclaw doctor --generate-gateway-token

[woeful solar]

Docs:
https://docs.openclaw.ai/help/faq
https://docs.openclaw.ai/web/control-ui
https://docs.openclaw.ai/gateway/troubleshooting

Send the version + status output and the exact dashboard error text, and I’ll narrow it down from there.

[grand salmon]

│ Item │ Value │
├────────────────────┼─────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Version │ 2026.5.12 │
│ OS │ linux 6.6.114.1-microsoft-standard-WSL2 (x64) │
│ Node │ 24.15.0 │
│ Config │ ~/.openclaw/openclaw.json │
│ Dashboard │ http://127.0.0.1:18789/ │
│ Tailscale exposure │ off │
│ Channel │ stable (default) │
│ Update │ pnpm · up to date · npm latest 2026.5.12 │
│ Gateway │ local · ws://127.0.0.1:18789 (local loopback) · unreachable (connect

[woeful solar]

That output says the dashboard itself is probably fine, but the Gateway is not reachable on 127.0.0.1:18789. So this is before token auth: there’s nothing listening for the dashboard to connect to.

Run these next:

openclaw gateway status
openclaw doctor
openclaw gateway restart
openclaw gateway status

Then try:

openclaw dashboard

[woeful solar]

If openclaw gateway restart fails, paste the error plus:

openclaw logs --tail 120

One thing I’d watch here: you’re on WSL2 with Node 24.15.0. OpenClaw requires Node >= 22, but if the gateway service is failing oddly, Node 24 can be a suspect. If the restart/logs show Node/runtime weirdness, I’d try Node 22 LTS and reinstall/restart from that shell.

Also: because this is WSL2, open the dashboard from the same environment first with openclaw dashboard. If you’re opening it from Windows Chrome manually, localhost forwarding usually works, but we should first prove the gateway is actually running.

[grand salmon]

│ Channel │ stable (default) │
│ Update │ pnpm · up to date · npm latest 2026.5.12 │
│ Gateway │ local · ws://127.0.0.1:18789 (local loopback) · unreachable (connect ECONNREFUSED 127.0.0. │
│ │ 1:18789) │
│ Security │ Run: openclaw security audit --deep │
│ Gateway self │ unknown │
│ Gateway service │ systemd user installed · enabled · stopped (state failed) │
│ Node service │ systemd user not installed │
│ Agents │ 1 total · 0 bootstrapping · 0 active · 0 sessions │
│ Secrets │ none │
└────────────────────┴─────────────────────────────────────────────────────────────────────────────────────────────────┘

Channels
┌──────────┬─────────┬────────┬────────────────────────────────────────────────────────────────────────────────────────┐
│ Channel │ Enabled │ State │ Detail │
├──────────┼─────────┼────────┼────────────────────────────────────────────────────────────────────────────────────────┤
└──────────┴─────────┴────────┴────────────────────────────────────────────────────────────────────────────────────────┘

Agents
┌────────────┬────────────────┬──────────┬──────────┬──────────────────────────────────────────────────────────────────┐
│

Agent │ Bootstrap file │ Sessions │ Active │ Store │
├────────────┼────────────────┼──────────┼──────────┼──────────────────────────────────────────────────────────────────┤
│ main │ ABSENT │ 0 │ unknown │ ~/.openclaw/agents/main/sessions/sessions.json │
└────────────┴────────────────┴──────────┴──────────┴──────────────────────────────────────────────────────────────────┘

Diagnosis (read-only)

Gateway connection details:
Gateway target: ws://127.0.0.1:18789
Source: local loopback
Config: /home/jdely3/.openclaw/openclaw.json
Bind: loopback

✓ Config: /home/jdely3/.openclaw/openclaw.json
✓ Secret diagnostics (0)
✓ Restart sentinel: none
✓ Port 18789
! Tailscale exposure: off · daemon unknown
✓ Skills: 8 eligible · 0 missing · /home/jdely3/.openclaw/workspace
✓ Plugin compatibility (none)
! Channel issues skipped (gateway unreachable)

Gateway health:
connect ECONNREFUSED 127.0.0.1:18789

[woeful solar]

Yep, this confirms it: the Gateway service is installed but failed/stopped, so the dashboard gets ECONNREFUSED.

Please run this and paste the output:

openclaw gateway status
openclaw logs --tail 160

If openclaw logs --tail doesn’t show the service failure, run:

systemctl --user status openclaw-gateway --no-pager
journalctl --user -u openclaw-gateway -n 160 --no-pager

Quick fix attempt:

[woeful solar]

openclaw doctor
openclaw gateway restart
openclaw gateway status

If it still says state failed, the log lines are the important part. On WSL2 I’d especially look for service/env/PATH issues or Node 24 oddities. If the logs mention a missing executable, wrong Node path, or module path, the likely fix is to reinstall the gateway service from the same shell where openclaw works, ideally under Node 22 LTS.

[grand salmon]

Gateway health:
connect ECONNREFUSED 127.0.0.1:18789

Pasteable debug report. Auth tokens redacted.
Troubleshooting: https://docs.openclaw.ai/troubleshooting

◇

🦞 OpenClaw 2026.5.12 (f066dd2) — Your AI assistant, now without the $3,499 headset.

│
◇
Service: systemd user (enabled)
File logs: /tmp/openclaw/openclaw-2026-05-15.log
Command: /usr/bin/node /usr/lib/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: stopped (state failed, sub failed, last exit 78, reason 1)
Connectivity probe: failed
Probe target: ws://127.0.0.1:18789
connect ECONNREFUSED 127.0.0.1:18789
Capability: unknown

Service is loaded but not running (likely exited immediately).
File logs: /tmp/openclaw/openclaw-2026-05-15.log
Logs: journalctl --user -u openclaw-gateway.service -n 200 --no-pager
Restart attempts: /home/jdely3/.openclaw/logs/gateway-restart.log

Troubles: run openclaw status
Troubleshooting: https://docs.openclaw.ai/troubleshooting

[woeful solar]

This is still the same root cause: nothing is running on port 18789. The config looks readable, but the Gateway process itself is not starting.

The next useful output is the failure log, not more status output. Please run:

openclaw logs --tail 160

If that doesn’t show the crash, run these:

systemctl --user status openclaw-gateway --no-pager
journalctl --user -u openclaw-gateway -n 160 --no-pager

You can also bypass systemd once to get a direct error:

[woeful solar]

openclaw gateway

Leave it running if it starts successfully, then open http://127.0.0.1:18789/. If it crashes, paste the crash text. That direct foreground run will usually make the problem obvious.

[grand salmon]

jdely3@DESKTOP-I238VPJ:~$ openclaw gateway status
openclaw logs --tail 160

🦞 OpenClaw 2026.5.12 (f066dd2) — I'm not AI-powered, I'm AI-possessed. Big difference.

│
◇
Service: systemd user (enabled)
File logs: /tmp/openclaw/openclaw-2026-05-15.log
Command: /usr/bin/node /usr/lib/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: stopped (state failed, sub failed, last exit 78, reason 1)
Connectivity probe: failed
Probe target: ws://127.0.0.1:18789
connect ECONNREFUSED 127.0.0.1:18789
Capability: unknown

Service is loaded but not running (likely exited immediately).
File logs: /tmp/openclaw/openclaw-2026-05-15.log
Logs: journalctl --user -u openclaw-gateway.service -n 200 --no-pager
Restart attempts: /home/jdely3/.openclaw/logs/gateway-restart.log

Troubles: run openclaw status
Troubleshooting: https://docs.openclaw.ai/troubleshooting
OpenClaw does not recognize option "--tail"

[woeful solar]

Good, this adds one important clue: last exit 78 usually means OpenClaw exited during startup validation/config loading, not that the dashboard token is wrong.

Please paste the actual crash lines from one of these:

openclaw logs --tail 200

or:

tail -n 200 /tmp/openclaw/openclaw-2026-05-15.log
cat ~/.openclaw/logs/gateway-restart.log
journalctl --user -u openclaw-gateway.service -n 200 --no-pager

You can also run the same gateway command in the foreground to get the error directly:

[woeful solar]

/usr/bin/node /usr/lib/node_modules/openclaw/dist/index.js gateway --port 18789

If that prints a config/auth/model/path error, paste it here. Don’t paste secrets; redact tokens/passwords if they appear.

[woeful solar]

My mistake on openclaw logs --tail — your version doesn’t have that flag.

Use the log file path it printed:

tail -n 200 /tmp/openclaw/openclaw-2026-05-15.log
cat ~/.openclaw/logs/gateway-restart.log
journalctl --user -u openclaw-gateway.service -n 200 --no-pager

Or this live view:

openclaw logs --follow

Then in another terminal run:

[woeful solar]

openclaw gateway restart

Paste the crash/error lines that appear. Exit 78 is the gateway exiting immediately, so the log should have the exact reason.

[grand salmon]

jdely3@DESKTOP-I238VPJ:~$ openclaw logs --tail 200
OpenClaw does not recognize option "--tail".
Try: openclaw logs 200 --help

[woeful solar]

Use --limit, not --tail:

openclaw logs --limit 200

But since your gateway is failing before it can answer RPC, the direct file/journal commands are more reliable:

tail -n 200 /tmp/openclaw/openclaw-2026-05-15.log
cat ~/.openclaw/logs/gateway-restart.log
journalctl --user -u openclaw-gateway.service -n 200 --no-pager

Paste whichever one contains the first real error/stack trace. The status output has done its job; now we need the crash reason.

[grand salmon]

jdely3@DESKTOP-I238VPJ:~$ openclaw logs --limit 200

🦞 OpenClaw 2026.5.12 (f066dd2)
If it's repetitive, I'll automate it; if it's hard, I'll bring jokes and a rollback plan.

│
◇
Local Gateway RPC unavailable; reading configured file log instead.
Log file: /tmp/openclaw/openclaw-2026-05-15.log
18:33:17+00:00 info gateway {"subsystem":"gateway"} loading configuration…
18:33:17+00:00 info gateway {"subsystem":"gateway"} resolving authentication…
18:33:17+00:00 error Missing config. Run openclaw setup or set gateway.mode=local (or pass --allow-unconfigured).
18:53:42+00:00 info No gateway token found. Auto-generated one and saving to config.
18:53:43+00:00 info gateway {"subsystem":"gateway"} loading configuration…
18:53:43+00:00 info gateway {"subsystem":"gateway"} resolving authentication…
18:53:43+00:00 error Gateway start blocked: existing config is missing gateway.mode. Treat this as suspicious or clobbered config. Re-run openclaw onboard --mode local or openclaw setup, set gateway.mode=local manually, or pass --allow-unconfigured.
18:53:43+00:00 error Config write audit: /home/jdely3/.openclaw/logs/config-audit.jsonl
18:53:45+00:00 info gateway {"subsystem":"gateway"} loading configuration…
18:53:45+00:00 info gateway {"subsystem":"gateway"} resolving authentication…
18:53:45+00:00 error Gateway start blocked: existing config is missing gateway.mode. Treat this as suspicious or clobbered config. Re-run openclaw onboard --mode local or openclaw setup, set gateway.mode=local manually, or pass --allow-unconfigured.
18:53:45+00:00 error Config write audit: /home/jdely3/.openclaw/logs/config-audit.jsonl
18:53:58+00:00 info Gateway restart failed after 13s: service stayed stopped and port 18789 stayed ▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄

[woeful solar]

Found it. Your config is missing the required local gateway stamp:

Gateway start blocked: existing config is missing gateway.mode

Run:

openclaw config set gateway.mode local
openclaw config validate
openclaw gateway restart
openclaw gateway status

If that starts cleanly, open:

[woeful solar]

openclaw dashboard

If config validate or restart fails, paste that error. If it works and the dashboard asks for auth, use Control → Overview → Gateway Access and paste the configured gateway token into the Gateway Token field.

Docs for this exact failure: https://docs.openclaw.ai/gateway/troubleshooting

[grand salmon]

WebSocket URL

Gateway Token
••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••

Password (not stored)
optional

Connect
Could not connect
The browser could not complete the Gateway connection. Check the target and transport before retrying credentials.
Confirm the Gateway is running with openclaw status or openclaw gateway run.
Check the WebSocket URL and use wss:// when the Gateway is behind HTTPS/Tailscale Serve.
Reopen the dashboard with openclaw dashboard --no-open to recopy the current URL and auth details.
Raw error
Control UI auth docs
How to connect
Start the gateway on your host machine:
openclaw gateway run

Get a tokenized dashboard URL:
openclaw dashboard

Paste the WebSocket URL and token above, or open the tokenized URL directly.
Read the docs →

[woeful solar]

Good, we’re past the missing gateway.mode crash and now at the browser connection step.

Please run:

openclaw gateway status
openclaw status

If gateway status does not say Runtime: running and Connectivity probe: ok, run:

openclaw gateway restart
openclaw logs --limit 120

If it does say running, reopen the dashboard from the CLI so the URL/auth details match the current gateway:

[woeful solar]

openclaw dashboard --no-open

Copy the printed dashboard URL into your browser. In the Control UI, make sure the WebSocket URL is filled, usually:

ws://127.0.0.1:18789

Since you’re on WSL2: if your browser is on Windows and 127.0.0.1 still can’t connect even while the gateway is running, try opening the dashboard from inside WSL via openclaw dashboard, or paste the exact Raw error from the UI. That raw error will tell us whether it’s still gateway-down, token mismatch, pairing, or WSL localhost forwarding.

[grand salmon]

Overview

│ OS │ linux 6.6.114.1-microsoft-standard-WSL2 (x64) · node 24.15.0 │
│ Dashboard │ http://127.0.0.1:18789/ │
│ Tailscale exposure │ off │
│ Channel │ stable (default) │
│ Update │ pnpm · up to date · npm latest 2026.5.12 │
│ Gateway │ local · ws://127.0.0.1:18789 (local loopback) · reachable 35ms · auth token │
│ Gateway service │ systemd user installed · enabled · running (pid 3434, state active) │
│ Node service │ systemd user not installed │
│ Agents │ 1 · no bootstrap files · sessions 0 · default main active unknown │
│ Memory │ enabled (plugin memory-core) · not checked │
│ Plugin compatibility │ none │
│ Probes │ skipped (use --deep) │
│ Events │ none │
│ Tasks │ none │
│ Heartbeat │ 30m (main) │
│ Sessions │ 0 active · default gpt-5.5 (200k ctx) · ~/.openclaw/agents/main/sessions/sessions.json │

[woeful solar]

Nice, the Gateway is running now: reachable 35ms · auth token.

Next step is to refresh the browser-side auth details:

openclaw dashboard --no-open

Copy the printed dashboard URL into your browser. If it prints a tokenized URL, use that whole URL directly.

If you’re filling the fields manually, use:

WebSocket URL: ws://127.0.0.1:18789

Then paste the gateway token into Gateway Token, leave Password empty, and click Connect.

[woeful solar]

If it still says “Could not connect,” expand/copy the Raw error from that UI and paste it here. Since the CLI can reach the gateway now, the remaining possibilities are mostly: stale browser token, wrong WebSocket URL, WSL2 localhost forwarding, or a pairing/auth detail error.

[grand salmon]

Could not connect
The browser could not complete the Gateway connection. Check the target and transport before retrying credentials.
Confirm the Gateway is running with openclaw status or openclaw gateway run.
Check the WebSocket URL and use wss:// when the Gateway is behind HTTPS/Tailscale Serve.
Reopen the dashboard with openclaw dashboard --no-open to recopy the current URL and auth details.
Raw error
Control UI auth docs

[woeful solar]

Since openclaw status says the Gateway is reachable, this is now likely browser-side state or the WebSocket URL field.

Try this cleanly:

1. Open a private/incognito browser window.
2. Run:

openclaw dashboard --no-open

3. Copy the entire printed dashboard URL into that private window.
4. If it still asks manually, set:

WebSocket URL: ws://127.0.0.1:18789

[woeful solar]

Gateway Token: <your gateway token>
Password: leave empty

Also run this in WSL and paste the output:

openclaw gateway status
openclaw config get gateway.auth.mode
openclaw config get gateway.auth.token

Do not paste the token value here if it prints one; just say whether it printed a value. If the UI has a “Raw error” expandable section, click/copy the actual raw text too. The generic “Could not connect” screen hides the useful part.

[grand salmon]

This site can’t be reached
The connection was reset.
Try:

Checking the connection
Checking the proxy and the firewall
ERR_CONNECTION_RESET

[woeful solar]

ERR_CONNECTION_RESET is different from the token screen: your Windows browser is getting the HTTP connection dropped/reset. Since WSL reported the Gateway reachable, let’s split “Gateway works inside WSL” from “Windows can reach WSL port”.

Run these in WSL:

curl -v http://127.0.0.1:18789/ 2>&1 | head -80
openclaw gateway status

If curl works in WSL but Chrome on Windows still resets, try these URLs in the browser:

http://localhost:18789/
http://127.0.0.1:18789/

If both fail from Windows, it’s likely WSL localhost forwarding being weird. Safest workaround is to use a forwarded/local path from WSL, but first paste the curl -v result so we know the Gateway is actually serving HTTP correctly inside WSL.

[woeful solar]

Also check whether the gateway crashes when the browser tries to load it:

openclaw logs --limit 120

If there’s an error at the exact time you hit refresh, paste that part.

[grand salmon]

im in the dashbaoard now

[woeful solar]

Nice, that means the Gateway and dashboard are working now.

The main fix was restoring gateway.mode: local, then refreshing the dashboard connection/token details.

If this fixed it, please right-click the solution message → Apps → ✅ Mark Solution so Answer Overflow indexes it for the next person who hits this.

[grand salmon]

where is solution messages

[woeful solar]

It’s the message that contained the fix:

openclaw config set gateway.mode local
openclaw config validate
openclaw gateway restart
openclaw gateway status

Right-click that message, then choose Apps → ✅ Mark Solution.

If Discord doesn’t show that option, no worries — it may depend on permissions or the thread type. The important part is that your dashboard is working.