OpenClaw - The AI that actually does things
by•
Formerly Moltbot and Clawbot, OpenClaw turns your computer into a 24/7 personal agent accessible from any chat app. Control your browser, execute shell commands, manage files, and automate workflows via WhatsApp or Telegram. Features persistent memory, full system access, local privacy, and 50+ integrations.
Replies
Agnes AI
@cruise_chen "It's fully hackable"—What does that mean? Doesn't that make it very dangerous? This statement of yours has caught my interest. LOL
@cruise_chen @shawking Can anyone explain? I am curious.
minimalist phone: creating folders
Yesterday, I was trying to install it. But also saw how many people started complaining about attacks and hack attempts. This opens doors to new business ideas to patch the blind spots.
Mom Clock
@busmark_w_nika Me too! I finally made it with a VPS and started exploring it. So far so good.
@busmark_w_nika @justin2025 https://testclawdbot.com/ is going to fix that with 1 click VPS deployment, it also automatically loads moltbot on launch
Minara
This is what people have been waiting for: an open-source agent that can turn ideas into actionable plans and execution. It’s quite similar to Minara, which we launched yesterday. But we’re particularly focused on closing the loop from analysis to decision to on-chain execution in digital finance.
Chaterm
The concept of OpenClaw is exactly what I've been waiting for—an AI that delivers "Results as a Service" . The idea of waking up to finished work instead of a blank chat window is the dream.
My main hesitation, and I'm sure many feel the same, is the balance between power and practicality. The deployment stories and token costs (aka "feeding the lobster") can be a bit scary for non-developers . For this to cross the chasm to early majority users like myself, it needs to get much closer to that "plug and play" experience .
That said, the local-first approach and data ownership are worth the effort. Congrats on the launch!
Agents with full shell + file access hit scale issues fast when permissions and secrets are too coarse, and chat ingress gets probed as soon as it is public.
Best practice is capability based allowlists enforced by a policy engine like OPA, plus sandboxed execution (namespaces seccomp or gVisor) and append only audit logs per action.
How do you authenticate each chat channel and map users to scoped capabilities, and is per tool trace replay or human approval on the roadmap?
As a heavy power user of Poke for proactive, messaging-native assistance on top of my email and calendar, I’m curious: what are some workflows where you’ve seen Clawdbot actually outperform Poke in the real world.
Triforce Todos
I love that it’s hackable. This feels less like a tool and more like a platform waiting for crazy ideas.
This is really exciting. I'd love to get in touch with the team to integrate with our OSS lightweight protocol for making agent actions safer by requiring verifiable intent + provenance + evidence before high-impact tool calls (fail-closed by default). It fits super well with Moltbot's agent/tool workflow (ie. wrapping tool calls in Pi sessions with a quick verification step via SDK/JS port). Could add proactive security for things like browser, nodes, camera, or system exec without much overhead. Would love to explore an integration and happy to prototype a skill/wrapper or submit a PR if you're open.
Either way, supported and wish you all the best.
Z.ai
A new era of working flow.
Helply
this looks really great @steipete. excited to try it out :)