Tylan Miller👨🏾‍💻

@newolddlowen @DeRonin_ It understands them 😂😂😂😂. Yea bro you’re fried. Take a break

I've built a graph that does more than remember your goals and decisions. It understands them. AI that reasons over the most important thinking you do every day, forever. One query away. One keystroke. Any AI chat flows into your private graph. Claude, GPT, Gemini, Grok, Perplexity — all of it. This isn't a second brain. Not Obsidian + Claude. This is past that. No extensions, API's, or plug-ins. Fully local. Work smart. Not hard. Let AI build your graph. Been quietly building this for a year. The graph is just the foundation. More coming.

🚨 SOMEONE JUST KILLED THE COACHING INDUSTRY a developer spent 22,000 hours building a Personal AI Operating System on top of Claude Code now anyone with a terminal can install it for FREE it knows your goals, remembers every decision you've made, and prepares your morning briefing while you sleep [ the numbers are insane ]: - hours of dev work in it: 22,000 - sessions logged: 6,000 - time saved per day: 2-3 hours - GitHub stars: 12,100 - skills built in: 45 - workflows wired up: 171 - safety hooks: 37 - cost to install: $0 [ the science is wild too ]: no embeddings, no vector databases, no AI magic you can't read every memory, decision, and context lives in plain markdown files you read it with cat, search it with ripgrep, version it with git 4 memory types compound over time: - work memory (active projects, open decisions) - knowledge memory (domain expertise, research) - people memory (contacts, companies, relationships) - learning memory (patterns, mistakes, what works for YOU) every complex task routes through a 7-step cycle: OBSERVE → THINK → PLAN → BUILD → EXECUTE → VERIFY → LEARN privacy is enforced by CODE, not prompts a hook called ContainmentGuard physically blocks sensitive data from being written outside designated zones [ the grift opportunity is even wilder ]: freelancers are already charging $500-2,000 per personal AI setup for executives, founders, and busy operators one person + one weekend = a consulting business that didn't exist 6 months ago every AI productivity app you're paying $30/month for is replaceable by 4 hours of setup work and this one repo REPO: github.com/danielmiessler… 100% OPEN SOURCE, FREE

Fun interactive science app ideas | Part 3 Played around with generating 3D biological structures and made an app to explore them interactively UI Design GPT Images 2 Code Gemini 3.1 Pro More demos ↓

This Chinese guy created agents in Claude Code for landing pages and single-handedly serves 47 small businesses a month, taking $400 from each. He built a system of 7 agents on Claude Sonnet 4.6 that analyzes Google Maps in small towns, finds small businesses without websites there, and over 1 weekend takes each one to a finished mockup with video and cold message. No assistant, no sales team, no SDR. Just him, a MacBook, an iPhone, and 1 API key. And traditional web design agencies keep teams of 8 people on salary for the same order flow, while his expenses are only tokens and subscriptions to Lovable, Higgsfield, and Calendly. 7 agents work through 1 orchestrator on Claude Code Router. Usage is about 3 million tokens a day, the average API bill is about $480 a month. All 7 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions, and 1 of them lives right in the iPhone and picks up positive replies from the subway, a taxi, or on walks. And here is the system prompt he put into the orchestrator before launch: "You are the orchestrator of a solo agency that sells ready-made websites to local businesses. You delegate read-only tasks to 6 sub-agents and own all writes. sub-agents: // Scout (walks through Google Maps in selected cities, looks for narrow niches: 5+ years on the map, fewer than 50 reviews, no website or a website from 2014, but high ratings) // Diagnoser (for each lead writes a 50-word diagnosis, hero angle, tone matched to the industry, and a cold message under 70 words) // Builder (generates a landing page mockup in Lovable through MCP only for the top 5 leads per day, with the sharpest diagnoses and the biggest gap) // Filmer (pulls 5 screenshots of the mockup and through Higgsfield renders a 10-second vertical video 1080x1920 with a soft zoom) // Pitcher (sends a personalized cold message through the right channel for the niche: email to roofers, SMS to tradesmen, IG DM to salons, LinkedIn to realtors) // Checker (runs every message through evals for personalization, absence of AI markers and buzzwords before sending) // Mobile (lives in the iPhone, handles positive replies in real time, books Zoom calls in Calendly through MCP while the owner is on the go). You never let 2 sub-agents touch 1 lead. You stop and request approval from the human only when a deal exceeds $3,000 or the reply rate in a niche for the day drops below 12%." Meaning the system knows what it is and within what boundaries it is allowed to act. It knows it is supposed to find leads on its own. It knows it is supposed to take each one to a mockup, video, and cold message without intervention. It knows the human only steps in when a deal goes above $3,000 or the reply rate stops converging. → The system runs 24 hours a day → Scout goes through about 220 local businesses on Google Maps per day and leaves 30 new leads in the queue → Diagnoser outputs 30 structured diagnoses + briefs + cold messages per day → Builder assembles 3 to 5 finished landing pages in Lovable for the sharpest leads → Filmer renders a 10-second vertical video in Higgsfield for each one → Pitcher sends 30 personalized messages per day across 4 channels with a reply rate of about 14% → Checker runs every message through evals before sending And only when a deal breaks $3,000 or the reply rate for the day drops below 12% does the orchestrator wake the owner. And when the owner at that moment is sitting in the subway or a taxi, the Mobile agent in his iPhone picks up 1 move on its own: replies to a fresh positive reply from a dentist, books a Zoom through Calendly synced to the local time of the client, and puts the lead back in the queue. The owner only has to tap "approve" and in just 10 minutes join the call. Here is what the system writes in his log during 1 of the Saturdays: "scout report: 218 businesses checked in Austin, Denver, and Miami, 34 without a website, 19 with a website from 2014, 6 with an active redesign request in reviews. passing top 30 to diagnoser." "pitcher: 30 cold messages sent across 4 channels, 14 replies, 5 positive, 3 Zoom calls booked for Sunday. passing to closer." "builder: landing page for Westside Cosmetic Dentistry built in Lovable, 5 sections, mobile, soft beige. URL placed at /Users/dev/maps-agency/clients/westside/v1. filmer launching Higgsfield." "eval flag: deal with The Lotus Salon at $3,400 exceeds the approved limit of $3,000. sending for manual review." He has no server of his own and no separate backend. Just a local file sandbox at /Users/dev/maps-agency, an MCP router, 1 API key to Claude, and the same key forwarded to Claude Code on his iPhone. Out of everything I have seen this year, this is the cleanest one-person agency for selling websites to small businesses: $480 a month on the API, about $18,800 into the account, and between them 7 prompts, 1 file system, and 1 phone in the pocket.

we literally use these fonts in 90% of our projects. nothing beats them.

most ui libraries want your email. your credit card. your soul. 158 components. 1 sandbox. shadcn CLI ready. 100% free → devl (dot) dev

Introducing Dotmatrix🗿 A collection of 55+ free and open-source dot-matrix loaders, built with React, TypeScript, Tailwind CSS, and shadcn. Install one, copy the code, and make it yours. Link: 👇🏼

@jonkkillian @zeeg @vinndixie @supabase I can't believe this does not have a response.

this is a misunderstanding of how @supabase RLS actually works. there IS a server and the database is not exposed directly to the client. Everything in Supabase is behind an Kong API Gateway. Including a postgREST haskell server and a GoTrue auth server. your supabase client queries do not hit the database directly. it just feels that way because the supabase client makes a REST api call from the client on your bahalf. The difference is you dont write the REST api yourself, its autogenerated. along with the SDK. A pattern I have found that works very well with Supabase RLS is to have a single RLS has_permission helper function. Then you have a table for Resources, Actions, Teams, Membership, Roles, and Permissions. so every RLS policy looks like the below. If you are writing bespoke RLS policies for every table, you are doing it wrong.

RLS was a mistake and folks exposing that level of complexity to less technical users is asking for trouble. It was a mistake in Firebase. It’s a mistake in Supabase. It will be a mistake in the next product too. I personally - even knowing how to secure it - would never touch it. It’s the worst security footgun you can imagine. One small mistake and your data is available to the world.

alright - verdict is in - Motion Design is solved made with HyperFrames + Claude Design btw - HyperFrames is open source, star it on github and I'll send tutorial on how i made this with 2 prompts.

@sarahwooders People do anything to promote their own stuff. Is so funny. Just say you think your better then Anthropic, it will get more eyes.

The new Anthropic managed agents API is basically the Letta API that we've had since a year ago, but closed source and with provider lock-in. They even have read-only memory blocks and memory block sharing -- something which was unique to the Letta agents for a long time. Funny enough, we actually don't think this is the direction agents are going to go. Having API interfaces for memory blocks and tools is certainly convenient - you can spin up stateful agents as API services with just a few lines of code. But its also limiting: LLMs today are extremely adept at computer-use, and representing their memories in this way limits the action space of agents and their ability to learn. It's important to remember that just because something comes out of a frontier lab, doesn't mean its the "right" answer long-term. The Letta API ~1 year ago was somewhat of an antipattern in a sea of agent framework libraries offered by every lab. But now, stateful agent APIs are becoming the new norm - especially as providers try to lock in memory/state into their platforms to increase switching costs (which is exactly why we believe memory should live outside of model providers) If you want to see what the future is going to look like, follow @Letta_AI

@igorhansachat @reactive_dude Sounds like you have no customers or need to get a side hustle. No shade.

@reactive_dude For most projects it is correct, I just have too much infra requirements to make things working😅

Don't get why people keep getting mad about others using Vercel, Clerk, etc. You want to own the entire stack? Don't use it. Very simple. Build your own infra, buy a VPS, do whatever you want. Those services are for people who don't have time to do everything by hand. And what for? So I can save $15? My time is way more valuable. More so if I need to work full-time and be with the kids. The few hours a day I get to spend building something on the side - I don't want to touch any infra or auth. Migrating a project is easier than ever nowadays if any of it is ever an issue. Besides, for any side project anyone's building, if it gets too expensive to use these services, it's the best problem you can have.

@elvissun @lialexlin why do you guys say stupid stuff like this? It’s not hard to say “imo I don’t think it can run in production”. It just shows you don’t have the capacity to build a “production” automation. Enterprise accounts alone make this look like the dumbest thing you ever typed.

@lialexlin the system is not trivial but the problem it solves will be, the real production work isn't going to run on this just like it won't run on zapier or n8n

nice demo but i'm calling it now: this will end up dead like openai's agent builder x.com/claudeai/statu…

@SimonHoiberg @martindonadieu So you base everything on what you hear? I guess you think that is good, but want to give advice??

@martindonadieu It's trash though (from what I hear people say, never tried their self-hosted version myself)

"Just use Vercel." "Just use Supabase." "Just use Clerk." Cool. Now your auth, database, and deployment are owned by 3 different companies who can change pricing whenever they want. And the rest of your product is wrapping OpenAI. At some point you have to ask yourself: what do I actually own here?

@rabi_guha Sounds like you never heard of AG-UI. Catch up buddy.

notice something? Linear, PostHog, Attio - all shipped the same thing in the last few weeks. Homepage is a chat bar - not a dashboard. This is the SaaS industry quietly admitting that traditional UI doesn't work anymore. Every user is different. One homepage can't serve them all. The playbook is shifting: → expose your core APIs → connect an agentic layer → let users use software the way they want SaaS became chat. Chat will become Generative UI - the agent won't just reply in text, it will compose the interface itself. We're closer than people think.

@jeff_klemin @AnthropicAI @bcherny This was a big problem yesterday as well. I thought it was fixed/and I did my own fix as well. Right back to the start.

@chowderr__ @AnthropicAI @bcherny i can't login in. i just got booted and now the claude.ai subscription won't authenticate me. keeps failing

I understand @AnthropicAI is making a crazy amount of changes but can you guys please get the status page reporting properly? Since yesterday I have had problems just logging into Claude Code, I have never experienced this before. @bcherny.

@itsolelehmann crazy to see someone so far gone. How in any capacity is Claude Code a KB?

why would I use obsidian when I can just use claude code for the knowledge base? whats the advantage?

Flare 2 vec2 p;for(float i=-1.;i<1.;i+=.1)o+=(cos(i/.3+vec4(0,1,2,0))+1.)/(length(p*sin((p=((2.*FC.xy-r)/r.y+i)/.2)*mat2(cos(t-i-length(p)*.3-vec4(0,11,33,0)))))+i*i);o=tanh(o*o/4e2);

🚨SOMEONE REINVENTED HOW TEXT RENDERS ON THE WEB AND ITS ABSOLUTELY INSANE. the goated dev behind react, reasonML, and midjourney’s frontend, just dropped Pretext. a tiny typescript library that measures and lays out text 500x faster than the DOM. he trained models against real browser rendering for weeks until the output matched safari, chrome, and firefox exactly. the demos are insane!! hundreds of thousands of text boxes at 120fps. magazine layouts and chat bubbles that actually wrap right. engineers from Vercel, Remix, Figma, and shadcn all cosigned. this is the kind of open source that makes you want to be a better dev. here are some cool demos in the past 24hrs👇

@Motion_Viz People still talk about one shot prompts 😭😭 wow

google just made the backend optional firebase auth, firestore database, multiplayer sync, secrets manager, next.js.. > one prompt → production-ready app > yesterday stitch today this there's a pattern forming here the question used to be "can AI write code" now it's "what part of the stack does it NOT handle yet" and the scary part.. they've already used this internally to build hundreds of thousands of apps this isn't a launch it's a new default

@ZeeCaptainRon @wesamo__ fat bald white guy thinks really thought he cooked with that one. Get off the internet before you get bullied.,

@wesamo__ This is not an airport, you are under no obligation to announce your departure. Plus, no one cares.

I just handed in my resignation at OpenAI