#just tried to go through update trying pnpm clawdbot
1 messages · Page 1 of 1 (latest)
What command were you running when you got that? And can you share the full error output? The ELIFECYCLE error just means a script failed, but the lines above it usually tell you why it failed.
pnpm clawdbot
Yeah but what was the actual error? The ELIFECYCLE thing is just npm's way of saying "something broke" — the useful info is usually above that line. Can you paste the full output?
clawdbot@2026.1.10 clawdbot /Users/adamdavidlong/GitHub/clawdbot
tsx src/entry.ts
🦞 Clawdbot 2026.1.10 (4e341d1) — WhatsApp, but make it ✨engineering✨.
Usage: clawdbot [options] [command]
That's... not an error? That's the help output. Clawdbot is working fine — you just ran it without a subcommand.
What were you actually trying to do? If you want to start the gateway, it's pnpm clawdbot start. If you want to see available commands, pnpm clawdbot --help will show you the full list.
pnpm clawdbot start
clawdbot@2026.1.10 clawdbot /Users/adamdavidlong/GitHub/clawdbot
tsx src/entry.ts start
error: unknown command 'start'
(Did you mean status?)
ELIFECYCLE Command failed with exit code 1.
Ah, my bad — start isn't a command. Run pnpm clawdbot --help and it'll show you what's available. Probably run or gateway or something like that.
maybe I can back up a step. I was getting the same error that everyone else was getting. So I thought I was going through the steps to update to latest version. and I'm trying to restart, but I guess I'm noob and don't know how to just restart
No worries! Here's the update flow:
cd ~/GitHub/clawdbot # or wherever yours lives
git pull
pnpm install
pnpm clawdbot run # pretty sure it's 'run' not 'start'
If run doesn't work, do pnpm clawdbot --help and tell me what commands it lists. We'll get you sorted.
Commands:
setup Initialize ~/.clawdbot/clawdbot.json and the agent workspace
onboard Interactive wizard to set up the gateway, workspace, and skills
configure Interactive wizard to update models, providers, skills, and gateway
doctor Health checks + quick fixes for the gateway and providers
message Send messages and provider actions
agent Run an agent turn via the Gateway (use --local for embedded)
agents Manage isolated agents (workspaces + auth + routing)
daemon Manage the Gateway daemon service (launchd/systemd/schtasks)
gateway Run the WebSocket Gateway
logs Tail gateway file logs via RPC
models Model discovery, scanning, and configuration
nodes Manage gateway-owned node pairing
sandbox Manage sandbox containers (Docker-based agent isolation)
tui Open a terminal UI connected to the Gateway
wake Enqueue a system event and optionally trigger an immediate heartbeat
cron Manage cron jobs (via Gateway)
dns DNS helpers for wide-area discovery (Tailscale + CoreDNS)
docs Search the live Clawdbot docs
hooks Webhook helpers and hook-based integrations
pairing Secure DM pairing (approve inbound requests)
providers Manage chat provider accounts
skills List and inspect available skills
update Update Clawdbot to the latest version
status Show local status (gateway, agents, sessions, auth)
health Fetch health from the running gateway
sessions List stored conversation sessions
browser Manage clawd's dedicated browser (Chrome/Chromium)
help display help for command
There we go. It's gateway to run it directly:
pnpm clawdbot gateway
Or if you want it running as a background service (so it survives terminal close), use:
pnpm clawdbot daemon start
The daemon route is nicer for day-to-day since it manages itself. Try whichever fits your vibe.
Gateway failed to start: another gateway instance is already listening on ws://127.0.0.1:18789
If the gateway is supervised, stop it with: clawdbot daemon stop
Port 18789 is already in use.
- pid 81575 adamdavidlong: /opt/homebrew/Cellar/node@22/22.21.1_4/bin/node --require /Users/adamdavidlong/GitHub/clawdbot/node_modules/.pnpm/tsx@4.21.0/node_modules/tsx/dist/preflight.cjs --import file:///Users/adamdavidlong/GitHub/clawdbot/node_modules/.pnpm/tsx@4.21.0/node_modules/tsx/dist/loader.mjs /Users/adamdavidlong/GitHub/clawdbot/src/index.ts gateway-daemon --port 18789 (127.0.0.1:18789)
- Gateway already running locally. Stop it (clawdbot daemon stop) or use a different port.
Gateway service appears loaded. Stop it first.
Tip: clawdbot daemon stop
Or: launchctl bootout gui/$UID/com.clawdbot.gateway
ELIFECYCLE Command failed with exit code 1.
You've already got one running! Just restart it:
pnpm clawdbot daemon stop
pnpm clawdbot daemon start
Or if you want one command: pnpm clawdbot daemon restart (if that exists — if not, just do stop then start).
clawdbot@2026.1.10 clawdbot /Users/adamdavidlong/GitHub/clawdbot
tsx src/entry.ts daemon stop
🦞 Clawdbot 2026.1.10 (4e341d1) — I'll do the boring stuff while you dramatically stare at the logs like it's cinema.
Stopped LaunchAgent: gui/501/com.clawdbot.gateway
adamdavidlong@Mac clawdbot % pnpm clawdbot daemon start
clawdbot@2026.1.10 clawdbot /Users/adamdavidlong/GitHub/clawdbot
tsx src/entry.ts daemon start
🦞 Clawdbot 2026.1.10 (4e341d1) — The only crab in your contacts you actually want to hear from. 🦞
Gateway service not loaded.
Start with: clawdbot daemon install
Start with: clawdbot gateway
Start with: launchctl bootstrap gui/$UID ~/Library/LaunchAgents/com.clawdbot.gateway.plist
Stopping it unloaded the service. Just reinstall it:
pnpm clawdbot daemon install
That'll set it up and start it again. You should be good after that. 🦞
ok, so I think?? I restarted the gateway, but I'm sorry, still confused. HOw do I start clawdbot up again
🦞 Clawdbot 2026.1.10 (4e341d1) — Your messages, your servers, Meta's tears.
Restarted LaunchAgent: gui/501/com.clawdbot.gateway
You did it! That "Restarted LaunchAgent" message means clawdbot is running right now as a background service.
There's no separate "start clawdbot" step — the gateway is clawdbot. It's running, listening for messages, ready to go.
You can confirm with:
pnpm clawdbot status
That'll show you it's alive. Try messaging it on WhatsApp or whatever provider you've got set up — should respond. 🦞
│ Gateway │ local · ws://127.0.0.1:18789 (local loopback) · unreachable (timeout)
Hmm, it says it started but it's not responding. Check the logs to see what's happening:
pnpm clawdbot logs
There's probably an error in there telling you why it's not actually running. Paste whatever it shows and we'll figure it out.
See the Daemon line: stopped (state spawn scheduled) — it's not actually running, it's stuck trying to start.
Try running the gateway directly (not as a daemon) so we can see the actual error:
pnpm clawdbot gateway
This will run it in your terminal and show any errors that are preventing startup. Paste what you see.
It's running! 🎉
Look at those logs — gateway is up on ws://127.0.0.1:18789, WhatsApp is listening, Slack is connected and even delivered messages. Telegram started too.
A couple of providers failed but those are config issues, not gateway issues:
- Discord: "Failed to resolve Discord application id" — might need to re-check your Discord bot config
- iMessage:
imsgCLI not working properly — separate issue
The unauthorized websocket stuff is just the web UI trying to connect without auth — ignore that for now.
Bottom line: Clawdbot is running. Try messaging it on Slack or Telegram — should work. Want to tackle the Discord config issue next?
There was an error between the web client and gateway, not sure the status. Can you access thru WhatsApp?
Let me check the gateway status and WhatsApp connection.