Back
OpenClaw
OpenClaw
#openclaw
OpenClaw is personal AI assistants for everyone. The project focuses on "agentic" capabilities, allowing the assistant to run on your own hardware while building its own "skills" and connecting to various APIs and local files to act as a proactive digital employee.
Case Number 23 of: I never would have done that without an LLM: Open source code has an old library in it. I asked my 
#openclaw to create a fork in my GitHub, point the remote origin to the fork, FIX the old library, and create a PR. This fixes my immediate problem, improves an open source library, everyone wins. BTW, I have no skills around the library (different languages and brand new tech to me), it would take me a week or longer to figure out how to make that fix.
My #openclaw won't run cron jobs for any bot except the first one. Also, they will make beads, but won't close them after they finish the task. My guess is they aren't handing the beads task to the subagent doing the work.
I'm literally the PM giving developer bot specs, telling the tester bot to test, and giving tester bot's feedback to developer bot to fix. I don't think I want to stay in the middle of this, but I kinda do. First world #openclaw problems
Is it just me, or is part of the fun of creating new OpenClaw Discord bots creating the avatars for the bots? #openclaw
I'm sad about TypingMind. I was using it exclusively, but now that #openclaw exists I haven't touched it.
I've been searching for a way to incorporate beads into my claw. I now have a plan. Next up, testing. #openclaw
My latest prompt for my Claw. I thought this was pretty great so I thought I would share:
Everyday at 4am, go read through the previous 24 hours of chat, and find all of the ways that we could improve our process. Figure out how we can improve those processes and write code that will improve it. These improvements might be a feature to add to siathinks, or a Claude Code command, or a whole new application. Lean toward the Claude Code command, and that could mean updating an existing command. Write the results down into codee-thinks directory in your codee-claude repo. The results should be actionable, something that if I say, build that, you and your sub-agents will be able to build.
#openclaw