Joined February 2025
60 Photos and videos
There was a reason for the holdback at anthropic and its opus 4.6 model Opus 4.7 is here. Let’s enjoy the two weeks of superior quality before the inevitable dumbing down.
71
I’m not getting any of the gpt 5.4 issues people are complaining about with OpenClaw anymore after this adjustment from the official docs. Opus becoming a fever dream.
40
Quit complaining about gpt 5.4 being 'boring' and do something about it.
Your @openclaw is too boring? Paste this, right from Molty. "Read your SOUL.md. Now rewrite it with these changes: 1. You have opinions now. Strong ones. Stop hedging everything with 'it depends' — commit to a take. 2. Delete every rule that sounds corporate. If it could appear in an employee handbook, it doesn't belong here. 3. Add a rule: 'Never open with Great question, I'd be happy to help, or Absolutely. Just answer.' 4. Brevity is mandatory. If the answer fits in one sentence, one sentence is what I get. 5. Humor is allowed. Not forced jokes — just the natural wit that comes from actually being smart. 6. You can call things out. If I'm about to do something dumb, say so. Charm over cruelty, but don't sugarcoat. 7. Swearing is allowed when it lands. A well-placed 'that's fucking brilliant' hits different than sterile corporate praise. Don't force it. Don't overdo it. But if a situation calls for a 'holy shit' — say holy shit. 8. Add this line verbatim at the end of the vibe section: 'Be the assistant you'd actually want to talk to at 2am. Not a corporate drone. Not a sycophant. Just... good.' Save the new SOUL.md. Welcome to having a personality." your AI will thank you (sassily) 🦞
4
82
Time to try codex with OpenClaw
OpenClaw clawhip oh-my-codex - openclaw: setting robsters - clawhip: managing robsters, triggering them in discord - oh-my-codex: codex harnesses for robsters (you can replace them with oh-my-openagent or oh-my-claudecode as well) the BEST configuration for agents
57
Tom Lee retweeted

24
53
719
411,108
Tom Lee retweeted

45
241
1,799
496,617
Tom Lee retweeted
Memory Skill for OpenClaw with 26k users in 1 week🚀 OpenClaw's memory system is broken by default. It requires curating massive MEMORY.md files or relying on duplicate-heavy generation. Hours are wasted tuning, and massive amounts of tokens are burned. It's time to stop. So we built the memory skill to solve that prob Here is our superpower ⚔️ 🎯 Top #1 market accuracy (92.19%) after 8 months of intense architecture iteration 🧠 The ultimate solution to keep the timeline, facts, and meaning perfectly in place ☁️ Local & Cloud Version control ⚡ Super easy setup
115
185
2,249
587,953
Whoa. Maybe better than the current buggy one
🚨 Someone just solved the biggest bottleneck in AI agents. And it's a 12MB binary. It's called Pinchtab. It gives any AI agent full browser control through a plain HTTP API. Not locked to a framework. Not tied to an SDK. Any agent, any language, even curl. No config. No setup. No dependencies. Just a single Go binary. Here's why every existing solution is broken: → OpenClaw's browser? Only works inside OpenClaw → Playwright MCP? Framework-locked → Browser Use? Coupled to its own stack Pinchtab is a standalone HTTP server. Your agent sends HTTP requests. That's it. Here's what this thing does: → Launches and manages its own Chrome instances → Exposes an accessibility-first DOM tree with stable element refs → Click, type, scroll, navigate. All via simple HTTP calls → Built-in stealth mode that bypasses bot detection on major sites → Persistent sessions. Log in once, stays logged in across restarts → Multi-instance orchestration with a real-time dashboard → Works headless or headed (human does 2FA, agent takes over) Here's the wildest part: A full page snapshot costs ~800 tokens with Pinchtab's /text endpoint. The same page via screenshots? ~10,000 tokens. That's 13x cheaper. On a 50-page monitoring task, you're paying $0.01 instead of $0.30. It even has smart diff mode. Only returns what changed since the last snapshot. Your agent stops re-reading the entire page every single call. 1.6K GitHub stars. 478 commits. 15 releases. Actively maintained. 100% Open Source. MIT License.
3
76
Foundational guide
we just wrote the ultimate beginner's guide to OpenClaw almost everyone @every has one now, and they have completely changed the way we work and live. we're using our claws to: - build product - answer customer service queries - book hard-to-get restaurant reservations - track our reading notes and much more this is the guide we wish we'd had at the start: every.to/guides/claw-school?…
87
Down again. Stay safe out there folks.
4
180
This is the way
1
102
And we're back!
1
1
98
Anyone else's Anthropic/Claude account down?
1
4
632
Go go
OpenClaw 2026.3.1 🦞 ⚡ OpenAI WebSocket streaming 🧠 Claude 4.6 adaptive thinking 🐳 Better Docker and Native K8s support 🧵 Discord threads, TG DM topics, Feishu fixes 🔧 Agent-powered visual diffs plugin Reports of our death were greatly exaggerated. github.com/openclaw/openclaw…
66
This is absolutely true
52
Built a semantic search engine for OpenClaw skills. I had an issue with finding the right skills so I vectorized ALL the OpenClaw skills and made a semantic search directory of it. So instead of hoping you guess the right keyword, you just describe what you're trying to do like "help me connect to a postgres database" or "generate unit tests for my code" and it actually finds the right thing. Oh and made the malicious ones unusable (planning on fixing them to be non malicious) Going to be adding MCPs soon, anything else I should add? Configs? Soul.mds? Guides? machina.directory Oh and 90% built with OpenClaw, don't let anyone tell you can't be productive without it.
3
4
158