THIS GUY CONNECTED OBSIDIAN TO AN AI AGENT AND NOW HIS SECOND BRAIN RUNS 7 AUTOMATED WORKFLOWS WHILE HE SLEEPS
he dropped 5 skill files into hermes agent on a saturday afternoon and configured one filesystem path pointing at his obsidian vault
by sunday night the system was reading his notes, filing his inbox, generating morning briefs and updating his project health report without him touching anything
his colleagues are still copying meeting notes into notion and wondering why they can never find anything two weeks later
the only thing separating them is one connection between a knowledge base that stores everything and an ai agent that actually acts on it
at 6am his vault generates a full brief from his own notes before he opens his eyes, at 8pm it empties his inbox automatically, every sunday it synthesizes the entire week and rewrites his priorities for monday
THIS DEV SPENT $47 ON KIMI K2 TOKENS AND NOW MAKES $28,735 A MONTH FROM A FITNESS APP
he opened openrouter on a friday night, dropped one prompt and went to sleep
by sunday he had a working mvp with stripe, supabase and an ai coach that adapts to every user automatically
his former colleagues are still waiting for sprint approval and debating architecture in notion
the only thing separating them is kimi k2 holding 256k tokens of context and seeing the entire project at once while other models lose the thread by file three
he spent $47 on tokens to build it, charges $9.99 a month, and now has 3,000 users paying him every month without a team or an office
bookmark this and check the full breakdown below
the same week nvidia launched a $249 ai box that replaces $200/month in cloud subscriptions, this person is selling a $45 diy kit that teaches you to build your own hardware from scratch and it sold out in 3 days
the kit ships with a raspberry pi zero, pre-cut components, and a soldering guide. you build it yourself in an afternoon. no experience required.
she started selling them from her apartment in london 8 weeks ago. first batch was 50 units. sold out in 72 hours. second batch was 200 units. sold out in 4 days. she is now on her third batch of 400 and has a waitlist of 600 people.
total revenue in 8 weeks is $19,350. her margin is 71% because the components cost $13 and she ships in a flat envelope.
the skills you learn building the kit take an afternoon. the understanding of how hardware actually works is something no youtube tutorial ever gave people before.
her day job paid her $38,000 a year. she matched that in 8 weeks selling kits from her kitchen table.
her employer found out and asked her to come back. she offered to sell them 50 kits for their engineering team instead.
the gap between people who buy finished hardware and people who understand how it works compounds every single day.
a chinese developer linked 2 nvidia boxes with one cable, 256gb of unified memory, and now runs models that openai charges $3,000/month for. jensen just showed what comes after that
the two boxes sit on his desk connected by a single cable. qwen 235b running locally, no cloud, no subscription, no data leaving the room. his monthly electricity bill for both boxes is $6.
he was paying $2,800/month for cloud gpus before. he bought both devices for $6,000 total and broke even in 67 days.
jensen huang walked on stage at computex holding the next generation of that hardware. models that currently take 3 weeks to train will train in 4 days. data centers running at capacity today will look like calculators compared to what this enables.
in 2018 nobody believed the gpu bet. nvidia went from $100b to $3.3 trillion in 6 years.
the developer in shanghai saw what was coming before anyone else. he already runs models on his desk that cost enterprises hundreds of thousands of dollars a year to access through the cloud.
jensen just showed what the next version of that looks like.
the gap between people who wait for the cloud to get cheaper and people who buy the hardware compounds every single day.
a 23-year-old spent 6 hours copy-pasting code and built a second brain with 1,400 notes that now generates $4,800/month in consulting work
he had zero coding experience. he just followed a guide, copy-pasted the setup into a Mac Mini, connected Claude to his Obsidian vault, and watched it start reading 1,400 notes he had accumulated over 2 years.
the first time he asked it a question about a client problem, it pulled a note he had completely forgotten about from 14 months ago that was exactly relevant. he had spent 3 hours researching the same thing twice.
that moment changed how he worked.
setup cost was $700 for the Mac Mini and $0 in monthly subscriptions. the system runs locally, nothing leaves his machine.
within 90 days he had packaged his knowledge system into a consulting offer. he now charges $1,600 per client to build the same setup for their business. he closed 3 clients in the first month.
his former employer offered him a raise to come back full time. he was already making more than the salary they offered.
the gap between people who store notes and people who build systems that think with their notes compounds every single day.
a 23-year-old spent 6 hours copy-pasting code and built a second brain with 1,400 notes that now generates $4,800/month in consulting work
he had zero coding experience. he just followed a guide, copy-pasted the setup into a Mac Mini, connected Claude to his Obsidian vault, and watched it start reading 1,400 notes he had accumulated over 2 years.
the first time he asked it a question about a client problem, it pulled a note he had completely forgotten about from 14 months ago that was exactly relevant. he had spent 3 hours researching the same thing twice.
that moment changed how he worked.
setup cost was $700 for the Mac Mini and $0 in monthly subscriptions. the system runs locally, nothing leaves his machine.
within 90 days he had packaged his knowledge system into a consulting offer. he now charges $1,600 per client to build the same setup for their business. he closed 3 clients in the first month.
his former employer offered him a raise to come back full time. he was already making more than the salary they offered.
the gap between people who store notes and people who build systems that think with their notes compounds every single day.
a 26-year-old from Pittsburgh set up an automated trading bot on a $700 Mac Mini and it now runs his entire income
the setup took one afternoon. he used 7 specialized agents, each owning one part of the build. one researched the market, one defined the product scope, one designed the logic, one built the scoring system, one attacked it for bugs, one wrote the launch copy.
no context switching. no one model trying to think like a researcher and an engineer at the same time. each agent stayed in its lane and produced one clean artifact.
by the end of the afternoon he had a validated market, a complete product spec, a scoring system with 100 specific checks, a UI structure, a QA checklist, and a cold email template.
the Mac Mini runs 24/7 on a cardboard box next to his desk. no cloud subscription. no server bill. total hardware cost was $700.
last month it generated $6,200 in automated revenue while he was at his day job.
his manager found out he was building on the side and offered him a promotion to keep him focused.
he handed in his notice the same week.
the gap between people who ask AI to do everything and people who build systems where each agent owns one job compounds every single day.
$96,000 a year from a brain with 1 million neurons and 1.19 billion synapses he coded from scratch
a former game developer from Amsterdam spent 2 years building a neural simulation that actually grows and learns like a juvenile nervous system. working memory, meta control, sensory cortex, reflex arc, all of it running live on a home server.
he built it because every second brain tool he tried felt static. notes that sit there. connections that never form on their own. he wanted something that actually thinks between sessions.
the simulation runs at 0.28 steps per second. 1.19 billion synapses firing in real time. the system is currently in juvenile stage, which means it is still developing new connection patterns every day.
he connected it to his research workflow the same way most people connect Obsidian to an AI. daily briefs generated automatically. patterns surfaced before he consciously recognizes them. insights from 3 months ago connected to notes from this morning.
six research teams are now paying $1,300 a month each for access to the system and its outputs.
his former employer at the game studio found out. they asked if he wanted to come back at double his old salary.
he sent them a demo instead and quoted $40,000 for a custom implementation.
the gap between people who use AI tools and people who build systems that think on their own compounds every single day.
a retired electrician from Osaka spent 6 months building an AI brain out of salvaged hardware and it now manages his entire consulting business
the box sits on his workshop floor next to his old tools. Arduino boards, salvaged GPU, MiLink modules wired by hand. Qwen 3.6 running locally, no subscription, no cloud, no data leaving the room.
he spent the first 3 months on the hardware. the next 3 months configuring the intelligence layer. custom instructions, knowledge files, scheduled tasks, client briefings, all of it set up the way 99% of people never bother to set up even a $20/month subscription.
6am every morning the box reads his calendar, summarizes overnight emails, pulls his active project statuses, and saves a complete daily brief to a local file before he touches his phone.
he has 4 consulting clients. each one gets a pre-call brief generated automatically 30 minutes before every meeting. none of them know it runs on salvaged parts in a workshop in Osaka.
his monthly overhead is $0. his monthly revenue is $14,000.
a big firm offered him a partnership last year. he asked them what their AI setup looked like. they showed him a ChatGPT Team subscription.
the gap between people who use AI as a chatbot and people who build systems around it compounds every single day.
a 17-year-old spent 2 years learning hardware from scratch in his bedroom
Arduino, Raspberry Pi, custom PCBs, a mini drone he built by hand. no school for it. no mentor. just YouTube and a soldering iron.
at month 8 he built a second brain in Obsidian that captured every tutorial he watched, every mistake he made, every circuit that failed. the system connected his notes automatically and surfaced patterns he never noticed while he was learning.
by month 14 it told him he had spent 340 hours on embedded systems and 12 hours on power management. that gap was why his projects kept failing at the battery stage.
he fixed the gap in 3 weeks.
at month 24 he started selling custom hardware projects on Upwork. first project was $400. six months later his average project is $4,200. last month he cleared $11,000.
the hardware knowledge got him the clients. the second brain got him there twice as fast.
most people learn by consuming. he learned by building a system that thought about what he was consuming while he slept.
the gap between people who just watch tutorials and people who build systems around what they learn compounds every single day.
a 24-year-old dropout from Austin runs a 7-agent software factory out of his bedroom
he approves checkpoints from his phone while his friends are at their 9-to-5s. his office is wherever his laptop is.
he quoted $30,000 for a scope a local firm priced at $80,000
the firm has 12 people. he has 7 agents and a Claude subscription.
one agent researches. one writes specs. one codes. one tests. one validates. one handles frontend. one handles backend. they run in parallel, hand off to each other, and he reviews checkpoints when the work is ready.
a local firm charges $80,000 because they have 12 salaries, an office, and three layers of approval. he charges $30,000 because his overhead is a $15/month server and Claude API costs.
his margin is higher than theirs.
last month he closed 3 projects simultaneously. his former employer found out and offered him a full-time position. he sent them a quote instead.
the gap between people who understand how to build with agents and people who don't compounds every single day.
$8,000 a month from a YouTube channel he spends 3 hours a week on.
Claude picks the niche, writes the script, 11labs voices it and the whole thing runs while he's doing something else.
https://t.co/GKpNUbmi4e
$20,000 a month from a channel that never shows a face.
one video about a plant got 21 million views while the owner was asleep.
most people stare at a blank screen while this channel prints money from ideas it didn't even come up with.
https://t.co/pzDiAsRdwd
$2,801 in 7 days from videos he never appears in, running on $3 a day.
he grabs viral clips, drops them into AI and posts before lunch then closes his laptop.
most people spend years on a personal brand and this guy made $700 yesterday faceless.
https://t.co/N1R4U92zbL
he built an AI water gun that shoots pigeons off his balcony using a $35 chip and a toy from a dollar store.
most people buy a fake owl and call it a day and this guy trained a computer vision model to do it for him.
https://t.co/kPYelDmQjc
Cursor pays engineers $1,100,000 a year to run teams of AI agents that ship code while they sleep
the CEO explained in 9 minutes how they do it and the playbook is simpler than you think
engineers no longer babysit one assistant. they manage dozens of agents working in parallel, each on its own remote machine
validation contract before code, not after. humans only at scoping and review
the agent team handles the full loop: planning, coding, testing, shipping PRs with each agent specialized for one role
Netflix uses the same architecture to analyze hundreds of build logs at once. Harvey uses it for legal work. Shopify is pushing toward 90% autonomous coding by Q3 2026
these are not experiments. these are production systems running right now
the people learning these patterns today will have a massive head start when this becomes the default way all software gets built
watch the full breakdown in the video. save it before you forget
he asked his AI how much he made today and it said $15,998.90 across 11 orders then opened Spotify on its own.
most people set 6am alarms for a job that never loved them back and this guy built one that works while he sleeps.
https://t.co/dsHPJHTvoa
a developer fed 1,816 sources into one AI brain and killed a $22,000 coaching business overnight.
now it thinks for him, connects ideas and generates content while he sleeps.
most people still pay $500 an hour for answers sitting inside their own head.
https://t.co/Xi5135wDut
this guy built an Obsidian vault that runs his entire business while he sleeps
every morning at 6AM it generates a project pulse, a content brief, and an intelligence report. 30 minutes before a client call it writes a full pre-call brief automatically
the average knowledge worker spends 4 to 6 hours a day on admin work. updating statuses, moving context between tools, compiling reports
this system removes you from that entirely. not faster. gone
three layers: Obsidian, Claude Code via MCP, N8N. total cost to run is $5 a month
after 6 months it knows your business at a depth that would take a human employee years to develop
full breakdown in the video. bookmark it before you forget