Blown away by what Anthropic keeps shipping. This new cloud design feature is going to help a lot of us create demos, walkthroughs, and tutorials of our products. I think it's better than Remotion at this point. https://www.anthropic.com/news/claude-design-anthropic-labs Try - https://claude.ai/design made this quick video for - https://www.themagichand.io/

Just spotted on openrouter. Endpoints will go live today Get ready for testing this should be a massive upgrade over 5.4

Hi Everyone, My company of 7 is all on g-suite. My orchestrator, Ratchet Raccoon, has his own google account as well. One of my agents creates QR codes of plansets, show drawings, etc. so that we can post them on walls at our job sites. In the future, we'll have different spec sheets and install manuals on the drive as well. Currently, OpenClaw is on a hetzner instance. What would you do, but the bullet and start a file server? Or use Ratchet's google drive? I'm having a real hard time keeping Ratchet's access to the google drive. His Oauth is constantly expiring and I don't know the right way to configure.

one thing nobody talks about enough or at least i have not seen it much... is how to actually save tokens when you are running openclaw every day i have been doing this for a while now and the setup that works best for me is keeping claude code completely separate from my main openclaw session here is exactly how i have it set up right now, you should copy if you want to save money imo i have two claude code terminals open at the same time terminal one is pointed at my openclaw workspace folder. that is where all my agent files live. SOUL.md, USER.md, MEMORY.md, all my cron job prompts, skill files, everything. when i need to edit an agent prompt, update a memory file, fix a skill, or change how a cron job works, i do it in claude code, not in my main chat with atlas terminal two is pointed at my mission control folder. that is my next.js dashboard that tracks all my revenue, content drafts, clips, everything. when i need to add a new feature, fix a bug, or update the ui, claude code handles it directly in that folder the reason this saves so many tokens is simple and easy to understand your main openclaw session has a context window. every message you send, every response you get, every tool call that runs, all of it adds up. when you ask atlas to write code or fix a bug inside the main chat, that whole conversation lives in the context window. it compresses eventually but it burns tokens before it does, and it clutters your agent memory with code noise that has nothing to do with running your business claude code works completely differently using your claude subscription. it reads only the files it needs for the specific task you give it. it does the work. it closes. no session history. no context overhead. no lcm compression eating your budget. just the task, done think of it this way. your main openclaw session is your chief of staff. you talk to it about strategy, content, community, what to work on next. that conversation should stay clean and focused

Hi everyone, I'm shipping systems that make it easier for my teammates and I to do project management. Do you recommend one orchestrator for all teammates? Or, each teammate has an orchestrator that can pull from a shared pool of specialized agents? What are the best interfaces to allow 2-8 people to interface with the AI agents? I've done slack, which appears slow to respond and the Mobile UX is not good. My orchestrator has a gmail, but I can't find a way to push emails. I set up cron jobs for every 5 minutes, which is kinda stupid frequent and still isn't fast enough response time for my teammates. Plus, once an email is marked read my AI appears to have reduced accuracy. Telegram bots I guess? Wondering what the community has stored in their collective experience regarding these issues. Thanks for your time!