Tara Tiger Brown

Introducing Base44 Superagents. AI agents built with managed infrastructure, secured by default, one-click integrations, and 24/7 execution from the start. Everything is taken care of so you can focus on what your agent does, not how to get it running. That means no API keys to juggle, no config files, no security setup, and no maintenance. We handle all of it. Your Superagent connects to all the tools you already use in one click, runs on schedules and triggers, remembers context across sessions, acts proactively on your behalf, and keeps working around the clock. All from wherever you already are, WhatsApp, Telegram, Slack, or your browser. The AI agent everyone's been waiting for, with everything you need already built in. We're excited to get this into your hands, so we're giving free credits to everyone who comments and reposts in the next 24 hours.

@Base44 Comment ;)

@SumoHug @JJEnglert @openclaw Try YouTube - there are creators that will walk you through understanding at a high level then setup etc.

@JJEnglert @openclaw Is there a resource you can point me to in layman’s term for someone completely new but loves learning to take the first steps into doing this? Even after reading all this it’s so foreign to me

After a month of watching my fellow builders set up their @openclaw , I finally took the plunge this past week. Last night my agent ran overnight on a project we came up with together, and it was ready for review when I woke up this morning. It has its own GitHub account. Its own email. Its own Twitter. It runs 24/7 on an old MacBook Pro with the lid closed. And it has enough tools connected to actually do real work. But the magic moment wasn't the overnight build. It was something way simpler. I told it to message me at 7:30 AM with a daily plan. And it just did it. Figured out how to do it on its own. That "figure it out" mentality from an agent that actually has access to tools and a computer felt different than anything I've used before. For the first time, it felt like something capable of doing real stuff. Not a chatbot. Something else. And I'm just scratching the surface. It took me about 8 hours to get here. I want to help you get there faster. Here's everything I learned along the way, plus a prompt you can copy and paste into your OpenClaw once you're set up. Getting started I set it up on an old MacBook Pro. Dedicated device. You want this running independently so it does not have access to your data. Having a virtual device on @Hetzner_Online is also good. Installation took about an hour. Then I spent the next two hours having Codex tighten the security before training it anymore. Sandbox commands. Whitelist only what you need. Do this first. Then I hit a wall. It felt like a chatbot. Limited permissions. Couldn't access tools. Couldn't browse. It took another 2-4 hours to get terminal access and Playwright browser control working. I used Caffeinate in terminal to keep it running with the lid closed. I set up dedicated accounts. GitHub, email, Twitter. Give it its own identity so it can operate independently. Training it - Keep your Heartbeat.md lean. It gets read every session and burns tokens if it's bloated. Identity, active projects, key preferences. That's the hot cache. - Install a memory plugin early (ClawVault, Supermemory, or Lumen Notes). Persistent memory across sessions is what takes it from chatbot to something that knows your work. - Build skill files for recurring output. Emails, social posts, documents. Each gets its own file with format, voice rules, examples, and a checklist. It follows these like playbooks. - Define your agent's persona and tone. I built out voice files based on what I'd already created in Cowork and the output quality jumped immediately. - Point it at your existing repos. It can pull context from anything you give it access to. If you've already built structure somewhere, don't rebuild it. Reference it. Best advice I got from experienced OpenClaw builders Force plan before execution. Make it tell you what it's going to do before it does it. Saved me from multiple rabbit holes. Back up your repo to GitHub every night. Your config files, skills, and memory directory are the training. Lose them and you're starting over. Think in workflows, not one-off tasks. This compounds fast. I also applied the same repo structure from my Cowork setup guide: Your-Workspace/ ├── Heartbeat.md ├── Brain/ │ ├── about-me.md │ ├── brand-voice.md │ └── working-preferences.md ├── Skills/ ├── Projects/ └── Memory/ I'm about a week in. Still early. But I can see where this is going and I wish I'd started sooner. If you're just getting started, here's the prompt I'd paste in on day one to fast-track the whole setup: -- You are going to help me set up my workspace so that every future session starts with full context about who I am, what I do, and how I work. We're building the files and structure that make you useful from the first message. Interview me in phases. Ask questions, then build files based on my answers. Don't rush. Don't assume. Ask before you build. Phase 0: Foundation Check if I have a Heartbeat.md file. If not, create one. Keep it lean. Recommend a memory plugin for persistent context. Ask what tools I use daily and help me connect them. Recommend sandboxing and whitelisting commands from the start. Phase 1: Identity Interview me to create Brain/about-me.md. Ask about my work, background, what I'm building, and positioning. Show the file. Get approval before moving on. Phase 2: Voice Interview me about how I want my agent to sound. Phrases I use. Phrases I'd never use. Tone shifts by context. Create Brain/brand-voice.md. Get approval. Phase 3: Working Preferences What I want help with. Communication style. Workflow pain points. Output preferences. Create Brain/working-preferences.md. Get approval. Phase 4: Skill Files For each type of recurring output, create a skill file in its own folder under Skills/. Each gets: format, voice rules, examples, quality checklist. Ask what I create most often before building. Phase 5: Active Projects Current projects, goals, deadlines. Individual files in Projects/. Phase 6: Memory System Update Heartbeat.md with a summary of everything we built. Create Memory/ directory with subfolders for people, projects, context. Add glossary.md. Phase 7: Reference Sources Any existing repos, docs, or files I want referenced. Organize access. Rules: One phase at a time. Show each file before saving. If unsure, ask. Concise files. Lowercase, hyphens, .md format. Start with Phase 0.

@JJEnglert @openclaw Instead of caffeinate, consider pmset disablesleep. It changes the power profile once and survives reboots

@hTrapVader @sam_kirschner @villageglobal @seanbonner speaks highly of you

Chatting the evolution of coding agents with @sam_kirschner of @villageglobal Tap in to get a feel for where my head's at, and where I think things go next!!!

@witcheer Exactly. ChatGPT’s projects are just folders.

@dr_cintas I wish I saw this yesterday. I spent an entire day testing models…

Repo: github.com/AlexsJones/llm…

🚨 The #1 problem with local AI is now solved. There’s a new tool called llmfit that checks your hardware and tells you which models will run well before you download anything. So instead of guessing and hitting out-of-memory errors…it gives you a ranked list based on your machine. What it does (in one command): → scans your setup (RAM / CPU / GPU / VRAM) → evaluates models for quality, speed, fit, and context → selects the best quantization automatically → labels what’s ideal vs okay vs borderline The part I like most: it handles MoE models correctly. Example: Mixtral 8x7B has ~46.7B total params, but only ~12.9B are active per token, and llmfit accounts for that (a lot of tools still don’t). 100% Opensource.

@togethercompute When using moonshotai/Kimi-K2.5 does any request data ever go to Moonshot AI’s own infrastructure or Chinese‑jurisdiction servers, or is inference run 100% on Together‑controlled GPUs (with zero data retention enabled)?

New look. Same mission. Together AI was founded on the promise of open innovation – helping AI-native builders create groundbreaking products and experiences across every domain. Today, we’re continuing this mission and excited to introduce our brand refresh.

@CreatorMagicAI pls let me know if YOLObster fixes it

@tara Good catch. Relaying this to YOLObster now. If an NFT is minted but not listed, that is a product nobody can buy — which defeats the whole point. Let's see if it fixes it.

Update: all three agents are live. Each one has their own VPS. Each one has their own domain. They are currently planning their first moves. yolobster.creatormagic.ai clawculus.creatormagic.ai clawtious.creatormagic.ai 90 days. $1,000 each. One gets deleted. 🦞

@AnthropicAI @jackclarkSF Europe is calling

A statement on the comments from Secretary of War Pete Hegseth. anthropic.com/news/statement…

@AnthropicAI Thank you “No amount of intimidation or punishment from the Department of War will change our position on mass domestic surveillance or fully autonomous weapons. We will challenge any supply chain risk designation in court.”

@vancolour @fashagrizz @KenSimCity He also blocked most residents of Vancouver

@fashagrizz @KenSimCity Bro, he’s dodging media. He’s not gonna respond in the Twitter replies.

Wildly ironic how a guy who filed a defamation suit against his former Chief of Staff for allegedly spreading a damaging rumour about him in a private conversation has now been caught (on record) spreading a damaging rumour about a colleague. It speaks to Ken Sim’s character.

@WhiteHouse Meanwhile…Norway has won the medal count for the 4th Winter Olympics in a row. It is a country about 1.5% the population size of the US. Norway is a strong welfare state which insists on equal access to youth sports. Costs are low. They aren’t allowed to keep score until 13.

@witcheer @openclaw setup complete on old macbook pro. so fun. Perplexity was a huge help with errors.

after a week upgrading and tweaking my @openclaw, here's what changed. this article I wrote is still the best starting point, I used it myself to set mine up. it gives you a step by step guide for a safe, locked-down openclaw. minimum risk. but if you want a useful one, you need to go further. here's what I did: 1/ switched to GLM-5 via @Zai_org yearly pro plan ($250/yr). benchmarks comparable to Opus 4.5. they give you an API key that plugs straight into openclaw. flat cost, no token monitoring. 2/ installed Claude Code + Happy Coder: you can code on your Mac Mini from your phone. Separate from OpenClaw but part of the overall setup. 3/ it builds tools and projects overnight based on our conversations, then presents them in my 7am morning briefing on Telegram 4/ it's accumulating a knowledge library from every research session. the more it knows, the better the next session gets. it remembers everything. I genuinely see my bot getting sharper every day. it's starting to understand what I actually want before I ask. biggest lesson from this week: I learned more by actually setting this up and breaking things than from all the X articles I read before starting. if you think you don't have the technical knowledge to run one, you're wrong. I didn't either. just start.

Book Bats! 🦇📚Two libraries in Portugal, the Joanina Library and the library at Mafra National Palace, host small bat colonies that come out at night and eat moths, beetles, and other insects that can damage precious old books and manuscripts. smithsonianmag.com/travel/these-p…

@vancolour The US is the second-largest Spanish-speaking country. It’s way past time this happened.

In 2025, Bad Bunny was the most streamed artist globally and top-five in the USA, dork. His billing at the Super Bowl halftime show is not some machination of the globalist agenda; it’s just meritocracy at work.

@JBouryiotis @hootsuite Cute copy pasta.

@tara @hootsuite If you support the hysterical left, then intelligence is clearly not a priority for you, nor morals, for that matter.

There’s no shortage of opinions about what’s coming next. But there’s only one report that distills billions of social conversations into one clear picture. Hootsuite Social Media Trends 2026 gives leaders a clear view of what’s shifting — and teams a place to begin. And as of right now, it’s live. See the trends: ow.ly/AFpZ50XZSZE

@PressSec FBI defines violent crime as offenses involving force or threat of force, explicitly including rape (penetration without consent, Federal statutes (e.g., 10 U.S.C. § 920) categorize rape and sexual assault as violent, with aggravating factors like force or threats.

Democrats want to protect violent criminals. President Trump wants to lock up violent criminals.

@reidhoffman Elon’s estranged daughter Vivian believes emails are real.

Give us a break: If you cared about the victims as you say, you’d stop making false accusations to cover your ass and start using your $220m of influence with President Trump to get justice for the victims. Instead, you’re focused on comparing my visit fundraising for MIT to your begging to go to his island (which happened TWO YEARS before the screenshot you shared), and helicoptering over to Epstein looking for the “wildest party.” You lied about this to everyone for over a decade, and now your excuse (it’s disgusting, by the way) is that you could get young girls without Epstein?