The problem isn’t the application layer - anyone can build that now. The problem is scale. This works when you have a few thousand events. A lot less fun when it’s a few millions events.
We still use posthog but then we created an application layer on top of their database, still useful and zero worry about scale and maintenance
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
The difference between vibe coding and agentic engineering is basically whether or not you read and verify the SKILL .md files yourself before adding to your bot
My fave feature of @openclaw is the heartbeat.
This should be built into every coding agent.
Having to manually setup cron/launchd jobs seems so primitive compared to an agent that regularly 'checks in' on things.
@dhh Same with this one. Nothing brought me more joy last year than this purchase. And it stacks perfectly on top of any Macbook 🤯 https://t.co/isLpWHAeAi