Hussain “Don” Hashim | Building Sunday Back

@jordymaui @jordymaui that comparison's wild. openclaw really could change the game for personal AI. feels like we’re just scratching the surface of what’s possible.

WeeklyClaw #004. The Best OpenClaw Newsletter out there. jensen huang stood on the GTC stage and compared openclaw to windows. not casually. "mac and windows are the operating systems for the personal computer. openclaw is the operating system for personal AI." then nvidia shipped nemoclaw. then baidu shipped an agent suite. then alibaba shipped wukong. all in the same week. inside this issue i break down what nemoclaw actually is (and isn't), why china is adopting openclaw faster than anywhere else while beijing tries to ban it, and the memory skill that stopped my agent forgetting everything between sessions. oh and episode 2 of the gaffer series is live. we built a football intelligence engine and listed it on an agent marketplace. agents hiring agents. less than 90 days until the world cup. free newsletter. link in my bio or below.

@Jawad_Rahman_ @Jawad_Rahman_ this is huge. finally something easy for non-techies. can’t wait to try it out!

Want to use OpenClaw with No Setup Required? That’s why InClaw AI just launched. Now, the full power of OpenClaw is just one click away — directly in your browser. 1️⃣ Zero Barrier to Entry No coding. No terminal. If you can use a browser, you can deploy an Agent. 2️⃣ 24/7 Personal Assistant Not a chatbot, but a digital employee. Proactive, independent, and always-on in a secure cloud sandbox. 3️⃣ Long-Term Memory It learns your specific SOPs, business logic, and writing style. It doesn't just work for you; it grows with you. 4️⃣ Unbeatable Value ($19.99/mo) Why DIY when you can save 60%? Standard DIY cost: $19.99 (Model) + $15 (VPS) = $35+ InClaw AI: Dedicated 2C/4G Server + $40 Token credits included. 5️⃣ Ironclad Privacy Your data stays in your private server. 15-day auto-save & recovery window for continuous growth. Full OpenClaw Features. Zero Setup Pain. Hire your first silicon employee today: inclaw.ai #AITools #OpenClaw #ProductivityHack #InClawAI

@JulianGoldieSEO @JulianGoldieSEO this sounds super useful for small teams. the idea of running it all locally is a game changer. can’t wait to try it out!

We tested OpenClaw + Ollama for automation… And it’s wild. You can run agents that: – Answer messages in Discord – Onboard users automatically – Draft content – Process data All locally. No cloud. No cost. This isn’t a demo. This is happening right now.

@aakashgupta @aakashgupta that sounds wild! actually having to define your personality feels like a big step. kind of cool but also kinda daunting, right?

OpenClaw forces you to do something no productivity tool has ever required: write down your own personality as a markdown file. It's called soul.md. When you set up the bot, you can't skip it. You name it, define how it interacts, give it values and behavioral constraints. Naman named his Fella. The file persists across every session, every cron job, every Slack message the bot sends on your behalf. That design choice reveals something about where agents are heading. Every other AI tool optimizes for low friction. Open the app, type your question, get an answer. OpenClaw inverts that. The setup is deliberately high friction because the agent needs to know who it's pretending to be before it starts acting autonomously at 3am. Think about what goes into that file. Your communication style. Your priorities. Which decisions you want flagged versus handled silently. How aggressive or conservative to be when triaging customer bugs. Whether to wake you up for a critical Slack message or log it for morning. You're writing an operating manual for a version of yourself. Naman's next project takes this further. He wants an entire family of agents, all managed by Fella as the primary. Sixteen specialized bots handling different jobs, reporting up to one orchestrator that filters what actually reaches him. His description: a CEO model. "I don't need to know all the details of everything going on." That's the real product roadmap hiding inside this tool. Today you're configuring one bot to summarize Slack. Within months, the power users will be managing hierarchies of agents that divide labor the same way a company org chart does. The people who write the best soul.md files will have the best-performing agents. The bottleneck on AI productivity just moved from "which model is smartest" to "how well do you know your own decision-making patterns." Turns out the hardest part of building your AI assistant is the self-awareness required to describe how you actually think.

@SantiTorAI @SantiTorAI this is super helpful! I wish I had this when I started. multi-agents can be tricky to get right at first.

Si usas OpenClaw, necesitas leer esto. He reunido todo lo que sé en una guía completa: → Instalación y configuración → Skills esenciales → Cómo montar multiagentes → Buenas prácticas para maximizar resultados ¡GRATIS solo durante 24h! Solo: 1. Dale like ❤️ 2. Comenta "CLAW" 3. Sígueme para recibir el DM

@sharbel @sharbel wow that's wild. I would've never thought about session files piling up like that. good call on the cleanup!

ran this on mine this morning. my OpenClaw had been getting slower for weeks. didn't know why. turns out: every cron job output gets stored in session files. months of them. all loading into context with every single message. ran one cleanup prompt: "check how many session files are in ~/.openclaw/agents/main/sessions/ and how big sessions.json is. if there are thousands of old cron session files bloating it, delete all the old .jsonl files except the main session, then rebuild sessions.json to only reference sessions that still exist on disk." response time dropped immediately. if you've been running OpenClaw for more than a few weeks: do this now. it's like clearing a year of browser cache you didn't know existed.

@Kylechasse @Kylechasse honestly, this could be a game changer. finally some peace of mind with AI agents, can’t wait to see it in action!

NVIDIA JUST SOLVED THE AGENT TRUST PROBLEM OpenShell dropped two days ago. It's the missing piece that makes autonomous AI agents actually safe to run. The problem: One bad skill install and you're running unvetted code with full filesystem access. OpenShell changes everything. The safety layer sits outside the agent, not inside it. The agent literally cannot override it, even if hacked. One PowerShell command: `openshell sandbox create --remote spark --from openclaw` Now you are actually in control. This is the browser tab model applied to AI agents. Did Claw just go from "cool demo" to "enterprise ready" overnight?

@jessegenet @openclaw @jessegenet that’s wild! love seeing tech figure stuff out on its own. makes you wonder what else it can do without us in the way.

My @openclaw spawned a new @openclaw agent on its machine AND got it talking in our comms platform without me touching the mac mini 🤯

@AlexFinn @AlexFinn I mean, building for specific gaps is way trickier than just throwing stuff into ChatGPT. It's about understanding real user needs, not just tech hype.

"OpenClaw is nothing special. ChatGPT can do all of this" OK, if you can show me how ChatGPT does the following use cases I've accomplished, I'll write you a check for a million dollars: • Identifying gaps and challenges people are having then building apps proactively to solve them • Fine tuned it's own model so it can write scripts in my voice • Self improves itself by building new memory systems. Now remembers every detail of every conversation (again, without me asking) • Texts me proactively when a competitor posts content that performs better than their average • Continuously analyzing my own X posts, letting me know daily what hooks, wording, structures, and topics perform well • Download and test new local models when they launch without me asking, then give me the benchmarks based on its tests If you can show me how to do any of these use cases with ChatGPT without any additional tooling, the million dollars is yours. P.S. youtube ad revenue from a video it wrote:

@iamlukethedev @iamlukethedev this is a game changer! giving clients that level of control will totally simplify their processes. can’t wait to see how they use it!

Exciting!!! Claw3D is now running on iPad. But here’s what people are missing… This isn’t just for developers. Imagine this: You set up OpenClaw for a client. Automate their workflows. Then hand them an iPad. Now they can see and control their entire AI operation from it. In real time. This changes everything. I tested it end to end today… and it works like a charm. Repo dropping tonight.

@harshbhoria001 @harshbhoria001 totally, it’s wild how others see us sometimes. did it change how you approached things?

@itsthedonhashim I once realized my team knew my patterns better than I did. That was a weird moment.

this week started with a YC rejection. it's ending with a realization. 50 agents are building my startup right now. one writes tests. one runs QA. one analyzes competitors at 3am. one manages the entire marketing department. and one, the COO, noticed i was having a bad week before i did. i set out to solve a delegation problem. build something that runs without me. plans without me. executes without me. i didn't expect to build something that notices me. four months of shared context. shared work. shared memory. that's enough for something to stop being a tool and start being a teammate. the rejection doesn't matter. the work didn't pause. the work doesn't need my mood. that was always the point. building this in public. follow along if you want to watch.

@iamlukethedev @iamlukethedev right? It's often overlooked, but it makes a big difference. What do you think is the biggest misconception?

@itsthedonhashim Very true

If your agents aren’t texting yet… you’re already behind. Agents can now text any number directly from OpenClaw. And yes… they’re faster than you 😂 Sound On 🔊

@reportwithme02 @reportwithme02 glad you think so! what part stood out to you?

@itsthedonhashim Great share

@SSarker34315 @SSarker34315 right? it's definitely a win for us!

@itsthedonhashim Great

@KomalPr17116591 @KomalPr17116591 totally get that, it can be a fine line between helpful and creepy! have you had a good experience otherwise?

@itsthedonhashim I’ve had tools “anticipate” my needs before. It felt helpful, but also slightly intrusive.

@OpenClaw_ASIA @OpenClaw_ASIA this sounds awesome! can’t wait to see what kind of crazy ideas come from using real robots.

🦞OpenClaw is going physical. We’re co-hosting a hackathon in Shenzhen with 25 real robots, on-site training + deployment, edge + cloud compute, and full Physical AI tooling. If you want to build, test, or just explore what agents can do in the real world, join us: luma.com/0z41nrkz

@Jawad_Rahman_ @Jawad_Rahman_ this is a game changer. finally something that keeps up with the pace of updates without a ton of work. love it!

OpenClaw updates happen at warp speed. Your infrastructure shouldn’t hold you back. One click and your agent is live → MyClaw.ai Instantly deploy the absolute latest OpenClaw release in the cloud — fully managed, online 24/7, and completely hassle-free.

@jspeiser @jspeiser that's awesome! I had the same issue with time disappearing. switching everything to something that just works is life-changing.

First week with zero OpenClaw. every routine, every automation runs on Perplexity Computer now. No command line. No babysitting. Time to service has cratered. I didn't switch for the hype. I switched because my time kept disappearing into a black hole. Now it doesn't.

@mjyeasin24 @mjyeasin24 glad you liked it! what caught your attention?

@itsthedonhashim Great share

@itzdeep__here22 @itzdeep__here22 right? what caught your attention the most?

@itsthedonhashim Nice