a couple months ago, i posted that i would be hosting openclaw demo nights across the world.
i didn’t know what to expect.
since then, we’ve hosted 8 openclaw events across 6 countries.
hundreds of builders, researchers, founders, and ai enthusiasts have joined us along the way.
and now we’re heading to shenzhen.
people call shenzhen the san francisco of china.
it’s one of the most exciting places in the world to build technology, and i’m genuinely excited to meet the builders there.
what has surprised me most throughout this journey is how many people have stepped up to help.
the only reason i’m able to organize these events is because of the incredible support of local community leaders who believe in what we’re doing.
huge thanks to our contributors and fellow co-hosts for openclaw demo night, shenzhen:
• @0xqiuqiuu
• @OpenClaw_ASIA
• @0xSZUBA (blockchain association started by students of the shenzhen university)
• @sgshumin and the team at @021labxyz
you can build products online.
but you build movements in person.
see you in shenzhen.
OpenClaw, Shenzhen🦞
After receiving such an overwhelming response to our events in Shanghai and Beijing in China, we are now doing an event in SHENZHEN!
In Collaboratoration with @0xqiuqiuu and Asia’s biggest OpenClaw community @OpenClaw_ASIA
Join us:https://t.co/TTxTq7WwHA
We got into Y Combinator (P26)
After scaling SimpleClaw to $40k MRR in <3 weeks, we learnt what our users were trying to accomplish - build companies with agents.
SimpleClaw is shutting down;
I’m now 19, and made the hard decision to skip college to build Result, my biggest bet so far.
Company announcement tomorrow.
ok, back to work.
We started the Great LLM Meetup yestersay with a stacked docket of talks, panels and fiery discussions 🔥
With guests from Z-ai, Openclaw, Qwen, PixVerse, Kimi, Ant ling Model & StepFun gracing us, we were bound to leave the session feeling like LLM maxis 😎
hot take: "agent memory" as a product category is mostly marketing.
here's what i believe actually matters
most "agent memory" solutions solve session persistence.
that's actually the easy part.
the hard part: cross-tool context. when your agent switches from slack to your CRM to your docs does it know what it just learned?
99% of solutions: no.
the real problem isn't storage. it's retrieval timing.
knowing when to inject context is harder than storing it.
inject too much → context window bloat,
increased latency, confused model
inject too little → agent loses relevant history
getting this balance right is the actual engineering challenge.
we're building ekai to solve this at the proxy layer (before the request hits the model).
true persistent memory across your entire stack.
So true. Humans drift toward comfortable work.
Busy movement feels productive, where much brainpower isn’t required.
But real progress and productivity is solving hard, unsolved problems.
will be building ekai from singapore for the next couple of months. if you're around, happy to catch up!
If you have any suggestions on events, hacker houses, or interesting people to connect with, do share :)
PromptGrammarly — your personal PromptEngineer.
Communicating with AI in this new era should be seamless, easy, and effective
PromptGrammerly understands exactly how each AI performs when it’s prompted the right way
Upgrade your prompts.
Upgrade your results.