Alan VanToai
182 posts
Alan VanToai
@VanToai
serial founder (b2b SaaS, crypto). 3x exits. now building autonomous companies.
SF Katılım Mayıs 2010
901 Takip Edilen1.2K Takipçiler
Just shipped the biggest update to OpenOats (prev OpenGranola: the open-source meeting copilot for macOS):
Meeting Templates + AI Notes ✨
Pick a template before your meeting (1:1, Customer Discovery, Hiring, Stand-Up, Weekly) and after it ends, generate structured notes from the full transcript with one click.
Notes stream in real-time as the LLM writes them. Browse past sessions, regenerate with different templates, copy to clipboard.
Also fixed a subtle bug where the last ~3 seconds of audio could be lost when stopping a session. Now the app gracefully drains all buffered speech before closing.
4 new files, 1,277 lines added. All open source.
github.com/yazinsai/OpenO…
yazin@yazins
OpenGranola now runs 100% locally with Ollama. LLM suggestions, knowledge base embeddings, transcription — all on your Mac, nothing hits the network. Just point it at Ollama instead of OpenRouter in settings and you're done. github.com/yazinsai/OpenG…
English
@_saberamani Thanks for the question Tim. Yeah man, it's a repeatable process. I'm building this into a repeatable skill that I can execute over and over again for new clients.
English
I built a $13M coach a full SaaS product and marketing engine with AI agents - in minutes.
Here's exactly what happened, and how you can do the same.
The case study: Kassidy Warren.
Real estate investor with a $13M portfolio. Growing podcast, 10K on YouTube, $9K/year private community.
Brilliant frameworks. All scattered across Google Drive.
The problem: Spreadsheets, video recordings, community call transcripts.
No product to package it. Sound familiar?
The AI build process:
Kickoff call - captured the full transcript with @meetgranola (AI note-taker that records from system audio, no bot in the Zoom)
Pulled transcripts from Kassidy's top 5 videos using AI agents
Organized everything into @obsdmd — a folder of text files that AI agents can read directly
Pointed @claudeai Code at the context directory. Asked it to generate a PRD.
Used the PRD to vibe-code the full app — a property underwriting calculator based on Kassidy's proprietary framework
The result: A working SaaS tool. Users input a property listing, get a deal score, pro forma projections, improvement suggestions, and scenario comparisons.
The monetization play:
- Value-add for existing $9K/year community members
- Standalone SaaS: $19/report or $50/month
- Free lead magnet: first report free to pull people into the funnel
But I didn't stop there.
Using the SAME knowledge base, I generated a complete marketing engine:
- Brand voice guide
- Detailed audience personas (built with Perplexity AI)
- Landing page copy
- Email sequence copy
- Social media content
All powered by Claude Skills - reusable prompt templates that take persona + voice + context and produce high-quality marketing assets.
The takeaway: The real leverage isn't in which AI tool you pick. It's in how you organize context before you touch any of them.
If you're a coach, creator, or entrepreneur with scattered knowledge across Google Drive, you're sitting on the raw material for a product and a marketing engine.
English
@Accelr8_Dan It’s an incredibly powerful unlock and worth the effort.
My two hacks:
1. Find other examples and see what other people are doing. I’ll share mine with you!
2. Yes, tinker until you like the output. Your discernment and taste is the final boss.
English
@VanToai I get scared managing Claude Skills cause I don’t know if the underlying skill itself is any good. Seems you have to tinker with markdown files and test a bunch of outputs to triage, unless there’s an easier way?
English
Grab the skills I used to make these assets here:
lucidfuture.ai/skills
English
@Gavriel_Cohen @CNBC Very well said, @Gavriel_Cohen. Appreciate the values you’re building with here. Keep up the great work.
English
I went on @CNBC and didn’t hold back about OpenClaw.
Here’s what I said, and why NanoClaw exists:
• AI agent swarms are a multiplier. Instead of one agent working for you, you have a coordinated team. That amplifies the value, but it also amplifies the risk if the foundation isn't secure.
• OpenClaw showed the world something genuinely exciting, but half a million lines of unreviewed code connected to everything is not a foundation you want to build on.
• NanoClaw is less than 1% of that size. Every agent runs in its own isolated container and only touches the data you specifically give it access to. Small, auditable, secure by design.
• And the bigger picture: whole product categories are being replaced by a few lines of text. Monitoring a website for changes used to be a SaaS product you'd pay $8 a month for. Now it's a prompt.
The potential here is enormous. But only if we build it right.
English
Loving the thinking and framing here by @karpathy.
Source code configurability by self-improving Claws. Claws as a new layer on top of LLMs & agents. Physical device “possessed by the soul of a personal digital house elf” ☺️
Delightful.
Andrej Karpathy@karpathy
Bought a new Mac mini to properly tinker with claws over the weekend. The apple store person told me they are selling like hotcakes and everyone is confused :) I'm definitely a bit sus'd to run OpenClaw specifically - giving my private data/keys to 400K lines of vibe coded monster that is being actively attacked at scale is not very appealing at all. Already seeing reports of exposed instances, RCE vulnerabilities, supply chain poisoning, malicious or compromised skills in the registry, it feels like a complete wild west and a security nightmare. But I do love the concept and I think that just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level. Looking around, and given that the high level idea is clear, there are a lot of smaller Claws starting to pop out. For example, on a quick skim NanoClaw looks really interesting in that the core engine is ~4000 lines of code (fits into both my head and that of AI agents, so it feels manageable, auditable, flexible, etc.) and runs everything in containers by default. I also love their approach to configurability - it's not done via config files it's done via skills! For example, /add-telegram instructs your AI agent how to modify the actual code to integrate Telegram. I haven't come across this yet and it slightly blew my mind earlier today as a new, AI-enabled approach to preventing config mess and if-then-else monsters. Basically - the implied new meta is to write the most maximally forkable repo and then have skills that fork it into any desired more exotic configuration. Very cool. Anyway there are many others - e.g. nanobot, zeroclaw, ironclaw, picoclaw (lol @ prefixes). There are also cloud-hosted alternatives but tbh I don't love these because it feels much harder to tinker with. In particular, local setup allows easy connection to home automation gadgets on the local network. And I don't know, there is something aesthetically pleasing about there being a physical device 'possessed' by a little ghost of a personal digital house elf. Not 100% sure what my setup ends up looking like just yet but Claws are an awesome, exciting new layer of the AI stack.
English
Sheeeesy boys be out here cookin 🔥🔥 nice one @howietl 💪🏾💪🏾
Howie Liu@howietl
I've been personally burning through billions of tokens a week for the past few months as a builder. Today I'm excited to announce Hyperagent, by Airtable. An agents platform where every session gets its own isolated, full computing environment in the cloud — no Mac Mini required. Real browser, code execution, image/video generation, data warehouse access, hundreds of integrations, and the ability to learn any new API as a skill. Deep domain expertise through skill learning. Teach the agent how your firm evaluates startups or how your team runs due diligence — now anyone on the team gets output that reflects your actual methodology, not a generic template. One-click deployment into Slack as intelligent coworkers. These aren't bots that wait to be @mentioned — they follow conversations, understand context, and act when relevant. And a command center to oversee and continuously improve your entire fleet of agents at scale. We're onboarding early users now. hyperagent.com
English
Easily my favorite piece on anything OpenClaw/agent related.
The role that examining & re-patterning my core beliefs and stories plays in my own growth journey makes this hit insanely hard.
Souls >
Skills
toli@tolibear_
English
@tolibear_ Easily my favorite piece on anything OpenClaw/agent related.
The role that examining & re-patterning my core beliefs and stories plays in my own growth journey makes this hit insanely hard. It’s what I am doing with @lucidvision_app
Very much inspired here. DMing you.
English
Copy/paste this article to your agent and ask it to redefine it's soul files around this.
You'll get a minimum 2x in output quality instantly.
toli@tolibear_
English
Alan VanToai retweetledi
Bostrom and Kurzweil mapped this out decades ago. There are roughly three phases between here and abundance, and your financial strategy should look completely different in each one.
Phase 1 is now through ~2030. AI eats white-collar tasks. Costs drop in specific sectors. Scarcity persists in housing, energy, healthcare, and physical goods. Traditional saving still works here because the economy still runs on the old rails.
Phase 2 is the messy middle. Maybe 2030 to 2038. Humanoid robots start scaling. Autonomous systems handle logistics, manufacturing, construction. Costs plummet across categories. This is where Musk’s thesis starts getting interesting. Your 401(k) contributions are buying assets denominated in a currency whose purchasing power is shifting underneath you. Saving “money” might matter less than owning productive assets, energy capacity, or compute.
Phase 3 is full post-scarcity. Production approaches zero marginal cost. Kurzweil’s law of accelerating returns hits escape velocity. If this arrives, the thread is right. Your brokerage account is a relic.
Nobody knows the transition speed between phases. The jump from Phase 1 to Phase 3 could take 5 years. Could take 50. Vernor Vinge called this the “event horizon” problem. You cannot see past the singularity because the rules change too fast to model.
The smartest play: save aggressively in Phase 1 (you’re in it), but tilt your portfolio toward assets that appreciate during the transition. Companies building the infrastructure of abundance. Energy. Compute. Robotics. Physical AI.
You’re betting on surviving the lag between when old systems break and new ones arrive.
The sci-fi version: the starship is coming, but you still need oxygen for the walk to the launch pad.
Dustin@r0ck3t23
Elon Musk just said saving for retirement becomes pointless in 10 to 20 years. Not speculation. Math. Musk: “Don’t worry about squirreling money away for retirement in like ten or 20 years. It won’t matter.” We passed the event horizon. Retirement savings assumes scarcity persists. It won’t. AI and robotics collapse labor costs to zero. Living costs follow. You’re not saving for security. You’re saving for a world that stops existing. Musk: “If any of the things that we’ve said are true, saving for retirement will be irrelevant.” Age of Abundance isn’t vision. It’s physics. Economic laws executing whether you believe them or not. 5,000 days. Fourteen years. Global GDP uncaps. Production approaches infinite. Net worth as concept dies. Only scarcity left is meaning. Money stops being the constraint. Timeline is shorter than your brain accepts. Fourteen years. We transition from survival work to Universal High Income in that window. Event horizon isn’t coming. You’re in it. Operating under old rules while ground disappears beneath you means you already lost. Production costs hit zero through automation. Everything priced on human labor reprices instantly. Housing. Food. Goods. Services. All reset when scarcity evaporates. Traditional planning assumes structure persists. Save for decades. Retire on capital returns in scarcity markets. That model shatters when abundance becomes baseline. You’re optimizing for a world vanishing while the replacement materializes. Your strategy becomes obsolete before you finish executing it. The retirement you’re building toward assumes costs stay high. They collapse. And your savings designed for expensive scarcity become irrelevant in cheap abundance. Every dollar you put away for future scarcity is a bet against the transformation already happening. And that bet loses the moment production costs hit zero and the economy you planned for stops functioning. You’re not preparing for the future. You’re clinging to a past that’s ending whether you accept it or not. And fourteen years from now, the question won’t be whether you saved enough. It’ll be why you wasted time saving for conditions that don’t exist anymore.
English
.@MatthewBerman absolutely cooked 🔥
Matthew Berman@MatthewBerman
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
English
Thank you. We just did the update. Love your care
GIF
Alan VanToai@VanToai
@bc1beat @openclaw Looks good. Reminder to update the readme:
English
ClawRouter for @openclaw
reach 2.2K stars🌟 within 10d launch.
We’ve been working hard on new improvements—specifically around cost optimization. Check out the latest updates below! 👇
E.H. Vicky@bc1beat
English
@SahilBloom Exactly what I’m looking to do with lucidfuture.ai
Would love to partner.
English
There's an opportunity right now to build a $100k per month side hustle as an AI Concierge.
And you don't even have to be *that* technical to do it. Just high agency.
There are probably millions of people out there who see all of the latest AI innovations like Claude Cowork, want to take advantage of them, but have no idea how to actually do that.
I know, because I'm one of those people...
I had dinner last night with the CEO of a multi-billion dollar tech startup. He was telling me about the full digital assistant/employee he just hacked together over the weekend. All of the things it's doing, how it's been an unlock for his workflows and life.
I told him I'd gladly pay him $5000 to come to my house and spend the day building me one using the same approach.
He laughed that he'd happily do that (though obviously won't given his day job).
There's a real, high cash flow opportunity for a hustler to launch a services business as an AI Concierge for the tech curious.
Ideally they would physically show up and build out a tool (or suite) to help an individual leverage the latest for their business and life.
I bet you could charge $5-10k for the initial upfront work and then some low ongoing service fee to keep the thing up to date (if the person wants that and needs help with it).
5-10 clients per month and you have a meaningful cash flow engine.
All comes down to the quality of what you deliver long term, but my guess is people would see a Month 1 positive ROI on the investment and referrals to their friends would drive the entire business.
Just a thought...
English
Alan VanToai retweetledi
My friend @VanToai just released his guided meditation and visualization app.
Great UX, particularly the AI text and speech services, built-in pacing and pauses and music. Relaxing, personalized meditations!
apps.apple.com/kz/app/lucid-v…
English