I just reserved my Cloudflare Wallet tag: useai.cloudflare.pay.
Reserve yours now at cloudflare.pay
1
52
Most continuous-adaptation talk loses the plot in about 2 minutes.
It becomes:
- RL
- LoRA
- "self-improving agents"
The boring engineering question is better:
how do you improve an agent in prod without turning prod into the experiment?
2
1
72
My current take:
continuous adaptation is an operator problem before it is a model-improvement problem.
The question is not "can the agent adapt?"
It is "which adaptation layer is safe to touch right now?"
1
30
Sources I am looking at:
MetaClaw: github.com/aiming-lab/MetaCl…
MetaClaw paper: arxiv.org/pdf/2603.17187.pdf
OpenClaw-RL: arxiv.org/pdf/2603.10165.pdf
HyperAgents: arxiv.org/pdf/2603.19461.pdf
42
What unsettles me about agent systems is not code generation.
It’s the idea that a person can be compressed into a few MB of patterns, context, and style and replayed on demand.
If that works, a lot of what we call expertise starts looking like portable data.
Anti-distillation may matter more than better orchestration.
p.s. explored that today, pay attention on it
👉 github.com/titanwings/collea…
👉 github.com/notdog1998/yourse…
👉 github.com/leilei926524-tech…
p.s. more thoughts at my links.llmneighbors.com/djzDR…
One pain I keep hitting in AI engineering:
I do not run everything on one machine.
I have Claw, Paperclip, Codex, CC, OpenCode, Pi, and a few isolated servers/runtimes
Once the same reusable rules and patterns need to exist in several places, copy-paste gets painful fast.
🧵1/2
🤖 Made with AI
1
4
74
So yes, I probably built another bicycle:
right now I use a GitOps monorepo plus a small sync CLI/scripts setup to keep that sane.
The first public pack is here:
github.com/AI-Neighbors/skil…🌟
It works for me, but I am curious:
how do you solve multi-machine agent workflow sync?
1
41
Like if you want boilerplate for your 🧬 LifeOS dashboard or if you have already! Nowadays it is a time of anti-SaaS self hosted 🥷😊
Share your 🤔💭?
1
33
Introducing MacClaw 🦞
Raycast-style macOS client for OpenClaw.
Works over your IDE, browser, slides and other. Just hit the hotkey, ask away and get live AI answers.
Instant connection to your Clawbot and zero distraction from your tasks.
Get for free here: github.com/itsnex1s/MacClaw
Found some solid security skills for OpenClaw🦞:
• skill-auditor
Scans a SKILL. md for 12 attack vectors and gives a clear verdict:
SAFE / SUSPICIOUS / DANGEROUS / BLOCK
• setup-auditor
Wizard-style flow that asks about your setup and outputs a fix-it checklist.
A convenient foundation for building CLI skills and prototyping your own Jarvis.
🔗 github.com/UseAI-pro/opencla…
If you run OpenClaw: what’s your #1 security concern right now — malicious skills, secrets exposure, or prompt injection?
38
🚀 Just spent 3 weeks deep-diving into Coding AI IDEs for Programmers (not a No-Code) landscape
@cursor_ai vs @codeiumdev vs Aider.ai Roo-Cline vs @aide_dev
Here's what I learned about the future of coding
(🧵1of9) ⬇





