@levelsio One of my clients is a restaurant.
We have over 200 items on the menu including drinks and alot of it is made fresh. We do have a large grill and wood fire pizza section. The prep is mostly sauces and dips. I don’t think this is true for every case.
Experimenting with ai agents + phantom wallet integration. thinking about autonomous trading on $100 to learn how it breaks.
Interested in what happens when you remove the human from the loop entirely.
Anyone built this yet?
Introducing the Phantom MCP Server 🦞
Agents can swap, sign, and manage addresses across all of Phantom's supported chains.
Ready to work with Claude, OpenClaw, or any MCP-compatible client.
POV: your OpenClaw after you didn’t set up a second brain system.
Paste this prompt to fix that: 👇
I want you to build me a second brain memory system.
Create a memory/ folder and a https://t.co/Msllm4OWRv file in your workspace. Every session, read these FIRST before doing anything, they are your entire memory.
memory/YYYY-MM-DD.md are your daily journals. As we talk each day, log everything in real-time - decisions, tasks, preferences, context, mistakes.
Timestamp each entry. These are your raw notes.
https://t.co/Msllm4OWRv is your long-term memory. This is curated, who I am, my goals, my preferences, active projects, lessons learned, key decisions and why.
Every few days, review your daily journals and distill the important stuff into here.
The rule: if it's not written to a file, you don't remember it.
When I say "remember this", write it immediately. When you make a mistake,document it so you never repeat it.
When you learn something about me update https://t.co/Msllm4OWRv.
Over time you should know my communication style, what I care about, what annoys me, my projects, my goals.
After a week this should feel like a real assistant that actually knows me. After a month, indispensable.
@levelsio Tell it to keep the context for 1 year. Add the bot to different telegram groups with different subject threads so it keeps context and it doesn’t get mixed up.
I'm one of the most advanced users of OpenClaw.
OpenClaw + GPT5.3 Codex + Opus 4.6 has been the trifecta that changed everything.
I made a video going over everything I'm doing with these tools.
Learn these tools, stay ahead.
Watch this video right now.
0:00 Intro
1:02 Overview
4:17 Sponsor
5:12 Personal CRM
7:11 Knowledge Base
8:30 Video Idea Pipeline
11:09 Twitter/X Search
12:47 Analytics Tracker
13:33 Data Review
15:34 HubSpot
16:13 Humanizer
16:52 Image/Video Generation
18:22 To-Do List
19:37 Usage Tracker (Saves Money)
20:45 Services
21:25 Automations
22:42 Backup
23:30 Memory
24:06 Building OpenClaw
25:22 Updating Files
You should never ever expose a VPS to the entire internet
Always firewall it to subnets
If you host a website you should only allow port 443 (HTTPS) inbound from Cloudflare's IP range / subnets
Port 22 (SSH) only from your Tailscale subnet range
That means you create a "tunnel" from Cloudflare and Tailscale (your laptop) to your server's door
You still need your SSH key to open the door btw
If you don't, ANYONE in the entire world can connect to your VPS and if there's just one security vulnerability and you didn't upgrade your VPS you can get hacked
If you do have it firewalled with Tailscale subnet only, it means only if they hack your laptop they could get in via your Tailscale there
Another thing is ask OpenClaw or Claude Code to enable unattended upgrades with auto reboot
Spanish PM Pedro Sánchez just declared war on the open internet. Under the guise of "safety" and "accountability," his government is launching a full-scale assault on free speech, specifically targeting platforms that refuse to bend the knee to state-approved narratives.
In a direct hit to the "freedom of reach," Spain will now criminalize the amplification of content the state deems "illegal." This gives the government the power to dictate how software is written. If an algorithm happens to show a truth that makes the ruling party look bad, it’s a "criminal offense."
Under the pretext of "protecting the children," Spain is banning anyone under 16 from social media and demanding "real barriers" for age verification. This is a massive Trojan Horse for a National Digital ID. To "save the kids," Sánchez is effectively demanding that every Spanish citizen hand over their private biometric or legal data just to scroll a feed.
He has also vowed to make platform executives like Elon Musk legally accountable for what users post, effectively holding tech leaders’ personal freedom hostage. It’s a transparent attempt to force Silicon Valley (and Austin) to build "kill switches" for any content the Spanish government doesn't like.
Sánchez dropped the mask at the end, specifically naming Grok, the one AI committed to the unvarnished truth, alongside TikTok and Instagram for investigation.
I'm Boris and I created Claude Code. I wanted to quickly share a few tips for using Claude Code, sourced directly from the Claude Code team. The way the team uses Claude is different than how I use it. Remember: there is no one right way to use Claude Code -- everyones' setup is different. You should experiment to see what works for you!