One Mac Mini and $120 a month: how a trader built an analytical machine on Obsidian and AI and earned $180,000
The cryptocurrency market is entering an era where advantage comes not so much from capital as from the architecture of information processing. A vivid confirmation of this is the story of an anonymous trader from China who, according to crypto investor CyrilXBT, built a personal analytical system at the intersection of the note-taking app Obsidian and a neural network. The result is impressive: $180,000 in net profit over six months with monthly costs of just $120 for the API.
How this "analytical factory" works
At the core of the system is a minimalist yet effective stack: a Mac Mini, an iPhone, and local Obsidian storage. Six automatic pipelines on the N8N platform operate around the clock, collecting into a single repository absolutely everything the trader reads, listens to in podcasts, and dictates via voice messages in a Telegram bot. Here, N8N acts as the connecting link between disparate data sources and the central repository.
The key element is nighttime processing. Every night, the neural network scans about 4,000 linked notes, searching for the strongest correlations between fresh information and already accumulated ideas. At 6:00 AM, a digest arrives by email: three trading ideas with a confidence rating, a forming idea of the week, and any note that contradicts the current open position.
The system is designed to wake the owner only in two cases: when a new note contradicts their current thesis, or when confidence in an idea exceeds the 90% threshold. This is not noise, but a pure signal.
The cost and market reality
CyrilXBT estimates the monthly return of this system at approximately $30,000, and the total profit over six months at $180,000. It is important to emphasize: these figures remain unverifiable. However, the example itself is not about specific numbers, but about a paradigm shift. A retail trader on a single Mac Mini and a budget of $120 per month achieved a result that previously required a team of eight analysts and access to expensive terminals like Bloomberg.
We are observing a trend that will change the landscape of retail trading: retail traders are increasingly assembling combinations of local note-taking apps, AI models, and automation platforms. This is the democratization of analytics that was previously only available to institutions.
My analysis: Such cases are a powerful signal for the market. If previously the edge was given by access to information, now the edge is given by the ability to structure and process information faster than others. However, I warn: loud sums on social networks are usually not accompanied by evidence. It is worth building such systems, but with a cool head and realistic expectations. This is a tool, not a grail.