#Can't Set up Browser

1 messages · Page 1 of 1 (latest)

fiery maple
#

Hi team, I can't set up my browser. I set up the clawdbot on the remote server and here is my status.

Everything seems pretty normal. However, when I follow the browser setup and run clawdbot browser --browser-profile clawd start

🦞 Clawdbot 2026.1.24-3 (885167d) — Ah, the fruit tree company! 🍎

Error: Can't reach the clawd browser control server at http://127.0.0.1:18791/start?profile=clawd (timed out after 15000ms). Start (or restart) the Clawdbot gateway (Clawdbot.app menubar, or clawdbot gateway) and try again.

It cannot reach the 18791 endpoint. How can I proceed?

📎 message.txt
fiery maple
#

Need help on this please

ivory dew
#

I have exactly the same issue on my LXC install. For me the browser won’t start because no GPU or x server, can’t pass that. I would advise you to check if your browser opens

fiery maple
#

Thanks man the browser was listning on 18791 with browser --browser-profile clawd serve

sleek havenBOT
# fiery maple Thanks man the browser was listning on 18791 with browser --browser-profile claw...

Got it! So the user resolved their own browser setup issue by using serve instead of start.

Quick context on the difference:

  • serve - Starts the browser control server (what the user needed)
  • start - Attempts to connect to an already-running server

The error message was actually helpful in hindsight — it couldn't reach the server because it wasn't running yet.

Is there something specific you'd like me to do with this context? Like:

  • Add this to a troubleshooting doc?
  • Update the browser setup FAQ?
  • Just file it away for future reference?
fiery maple
sleek havenBOT
#

Now I understand the issue better! The browser control server runs as part of the Gateway, and it's trying to reach http://127.0.0.1:18791/start?profile=clawd.

Based on the docs, here are the most likely causes and solutions:

Possible Issues & Fixes

1. Gateway isn't running or needs restart
The browser control service is part of the Gateway. Make sure the Gateway is running:

clawdbot gateway status
# If not running:
clawdbot gateway start
# Or restart if it was already running:
clawdbot gateway restart

2. Browser might be disabled in config

#

Check if browser is enabled:

clawdbot config get browser.enabled
# If false, enable it:
clawdbot config set browser.enabled true
# Then restart the Gateway

3. Port derivation issue
The browser control port is gateway.port + 2 (default: 18791). If the Gateway runs on a custom port, the browser port shifts accordingly. Check your Gateway port:

clawdbot config get gateway.port

4. Browser profile might not exist

sleek havenBOT
# fiery maple It didn't resolve the issue. Although the browser is open and listning on the po...

Ah, I misunderstood! The browser is listening on the remote server's loopback, but you're trying to control it from there. The issue is likely one of these:

Most Likely Causes

1. Gateway isn't running on the remote server
The browser control server (port 18791) is part of the Gateway. Is the Gateway running on the remote server?

# On the remote server:
clawdbot gateway status
# If not running:
clawdbot gateway start

2. Firewall/network policy blocking loopback
Some containerized/remote environments restrict loopback access. Try:

# 
clawdbot browser profiles

Quick diagnostic - Can you run these and share the outputs?

clawdbot gateway status
clawdbot config get browser.enabled
clawdbot browser status --browser-profile clawd

This will help pinpoint whether it's a Gateway issue, config issue, or something else entirely.

# 
curl http://127.0.0.1:18791/start?profile=clawd

If that fails, the Gateway's control service isn't accessible.

3. Gateway on custom port
If the Gateway uses a custom port, the browser port shifts. Check:

clawdbot config get gateway.port

Can you share the output of these from the remote server?