@HedgieMarkets The real winners will be Chinese models that which will come in to swoop in as a technology. American’s may not use the Chinese hosted models but it won’t stop people from using local or hosting their own service . Doesn’t Microsoft host deepseek models?
@AntifaBill@mattpocockuk The afk is not the one doing the planning. That comes before. Grill/prd/issues /then afk. With the first three process ai tries to understands what you want and the prd and later process is so that ai can understand it. I've been using this a lot.
@mattpocockuk hey I just watched your presentation on ai software engineering principles and’s what a refreshing new take on that was. After watching it I started to use the skill for grill me and the other processes and tried it out on two code bases. It worked wonderfully
I love the grill me process. It has a way better outcome than just planning alone was finally able to get 5 sub agents spinning up. I use opencode but what you talked about is very much relevant. Thanks once again
Memory for OpenClaw is now Native!
Our first OpenClaw Memory Skill was a massive success: 30k+ downloads in a week and 500k+ organic impressions overnight for launch post.
But we knew memory needed to be native.
On March 21, OpenClaw merged PR #50848, allowing us to go beyond the skill layer and integrate directly into the agent’s context assembly flow.
We try to make OpenClaw a truly 24/7 employee capable of complex workflows. The technical setup isn’t the hardest part but the real challenge is giving it a "brain" that remembers exact project details, past decisions, and team changes over time.
The Native Memory Plugin is now live on NPM & ClawHub. Here is what it brings to your OpenClaw agents:
👉 Native Integration: Automatically manages a Three-Layer Memory architecture (Context Tree, Workspace Memory, Daily Memory).
👉 Git-like Stateful Memory: Organizes memory into a semantic hierarchy of human-readable, diffable Markdown files. You always get updated knowledge and can actually see and fix what your agent learns.
👉 Top Market Accuracy: Achieves an industry-leading 92.2% retrieval accuracy (LoCoMo & LongMemEval benchmarks), maintaining 90% accuracy even with cheap, lightweight models.
👉 Local-first & Portable: Local-by-default, fully portable for multi-agent teams.
👉 Super Easy Setup
@northmotorsinc@TheBradOwen@Pinboard Trump is responsible for what goes on in the bill. He is the one promoting it. He stands behind it and that’s what matters
@Avals_lik@maximebodenmann Ai is only useful as the person using it. If there is no programming fundamentals practiced or planning being made then that will be reflected in how ai will work. I treat ai like an intern that knows a breadth of languages technically but doesn’t have foresight
@MVP_Builder These set of principles are absolutely gold. Not just for cursor but for any ai powered ide. I need to really follow this for my projects. Well written. Would love to see this in a blog or stream 👍