5 Must Know TIPS for OpenClaw
Video summary
Companion notes
OpenClaw's biggest gotcha is silent memory failure — fix that first, and the rest of the agent starts behaving.
## Embeddings are non-negotiable
OpenClaw will "wake up with no memory at all" every session unless embeddings are wired up. The creator calls it "one of the most forgotten aspects" and warns the bot will "constantly forget what project you're working on, what keys you have, what passwords you have." You need an OpenAI key for embeddings, or an OpenRouter key if you prefer. The verification line he uses verbatim: ask the agent directly, "are you using the open AI key, is your memory working?" If you skip this, every other tip is fighting upstream.
## Split work across threads, not one mega-chat
Run multiple threads, one per topic, and let the agent auto-join each. The creator ran one thread for general chat and another that built a dashboard in a single shot — a tip he flags as a "bonus." Discord is his preferred surface over Telegram and "much easier to talk to your agent on," though he teases a full Discord tutorial as still pending.
## When it dies, use Claw to fix Claw
If the agent corrupts its own settings file, it can't self-recover. The fix: cd into the openclaw directory and start Claw there, then prompt it with something like, "study this folder, this is for openclaw, I have an error, it doesn't boot up, help me connect to Discord and fix the errors." It beats the in-app help settings because Claw can read its own codebase.
## Tame the 30-minute heartbeat
Default heartbeats fire every 30 minutes and "cost a lot of money" over time. Ask Claw to change the interval — e.g., to one hour — and monitor spend via OpenRouter. If the change bricks the bot, fall back to the previous trick.
## Force secrets into the .env file
OpenClaw will actively delete passwords from notes because it considers them insecure. Tell it explicitly to store API keys and secrets in the .env file. Bots treat that path as coding convention and leave it alone, so the credentials actually persist.
## Tip #1 is the unlock
The creator's closing line: "tip number one will be like the one tip that you will always use to get things done." Memory via embeddings is the lever; everything else is incremental.
Watch on YouTube
Prefer the native player? Open it on YouTube: https://www.youtube.com/watch?v=-PT46iH03RQ
