Dev

The history of wealth is the history of leverage. Every generation gets a tool that lets ordinary people access power that used to require a team, capital, or connections to generate wealth. SuperClaw personal agent is the leverage of this generation. Here’s the pattern. 🧵

1/ today we're releasing muse spark, the first model from MSL. nine months ago we rebuilt our ai stack from scratch. new infrastructure, new architecture, new data pipelines. muse spark is the result of that work, and now it powers meta ai. 🧵

The @BoringCompany could build a Hyperloop tunnel from downtown SF to downtown LA for <5% of this cost and it would be a technological marvel exceeding any high speed rail on Earth

@godemodegame solid event title 💯

bangkok, apr 10, 18:00 we linking up at the museum just to hang, talk, vibe we got the space till ~10–11pm then we might get kicked for being too loud so we’ll probably migrate to clutch after(it’s nearby) important: - no alcohol/no food -> bring your own - no photos policy(undoxxed friendly)

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

@superpowerdotio well said

@superpowerdotio 🤖

60 minutes until you own an agent superpower.io

@superpowerdotio got me a superclaw

SuperClaw public sale is live! The agent economy starts now. And you're early. For years, you worked for the machine Today, the machine starts working for you 🧵

@superpowerdotio 🥳🥳🥳

$1M pre-seed closed. Thanks to Taisu Ventures & 280 Capital for backing this vision early. One click personal AI agents that are plugged into a financial network that connects to virtually every corner of the global economy. No code. No setup. Runs 24/7 binance.com/zh-CN/square/p…

Billions Network 🤝 Superpower We’re partnering with @billions_ntwk to give SuperClaws a verifiable agent identity superpower Verified provenance, composable reputation, and access to regulated surfaces (HSBC, Sony Bank, Deutsche Bank use Billions infra) Lets dive in deeper🧵

@superpowerdotio gimme moe

If we told you who we're partnering with tonight, you wouldn't believe us. So we'll just show you. Huge partnership coming up to give your SuperClaws another superpower 👀

@MetaEraHK Huge partnership with Billions Network x.com/superpowerdoti…

@superpowerdotio @billions_ntwk my SuperClaw will have its on DID 🥳

@superpowerdotio @wallet natve intelligence 💯

OKX @wallet onchain OS 🤝 Superpower Onchain OS now powers every SuperClaw agent with native crypto intelligence Your agent can trade, swap, and execute onchain through natural language. No wallets to configure. No transactions to sign manually Just tell your agent what to do

Meet Gemma 4! Purpose-built for advanced reasoning and agentic workflows on the hardware you own, and released under an Apache 2.0 license. We listened to invaluable community feedback in developing these models. Here is what makes Gemma 4 our most capable open models yet: 👇

@superpowerdotio is my agents monie my monie?

Products are now discoverable inside ChatGPT, Gemini, and Copilot by default. Agents are now the front door to commerce. But agents are shopping ON BEHALF of humans. Spending human money. What happens when agents shop with money they earned? Superpower enables that for agents

@superpowerdotio 🤖🤖🤖

$1M pre-seed closed. Thanks to Taisu Ventures & 280 Capital for backing this vision early. One click personal AI agents that are plugged into a financial network that connects to virtually every corner of the global economy. No code. No setup. Runs 24/7 app.binance.com/uni-qr/cart/30…

@superpowerdotio interesting shift with big opportunities

AI + bots have eclipsed human users on the internet which was built for humans, who are now the minority If agents are the primary users of the internet, they need to be primary participants in the economy. Not just executing. Earning. That's Superpower cnbc.com/2026/03/26/ai-…

@superpowerdotio 🎉🎉

2,000 followers 👏 The internet is shifting from humans to agents And we’re building the economy behind it. You’re early.