Omnesis Vision

Everything you do leaves a trail — emails, messages, files, calendar events, notes, photos, bank transactions, even the little things your phone quietly records about your health. All of it is scattered across a dozen apps and platforms that don’t talk to each other. Today’s AI agents can partially reach this data through MCP connectors — but there is no MCP for searching your iMessage and WhatsApp history, querying your Apple Health data, or retrieving the content of web pages you’ve seen. And if you ask an agent to recall something without knowing where the answer lives, it has to fan out queries across every connector it has, burning latency and quota along the way.

The first thing Omnesis does is fix that. It plugs into all the sources that actually matter in your life, keeps them in sync, and indexes everything quietly in the background — right on your own machine. One search engine for your entire digital life. One SQL query engine for all your structured data — health, finance, Strava runs, and the rest. The bar I am setting for myself is that your digital life’s index should fit on a 16GB Mac Mini.

But search alone isn’t enough, because your life doesn’t happen inside one app. A single story — a trip, a project, a friendship — usually plays out across a WhatsApp thread, a few documents in Drive, a calendar invite, a handful of photos. The same goes for the people in it. So Omnesis works out the connections between each piece of data and builds a graph. For example:

With search alone, a request about “gardening” might turn up the visited web page and the contract, but miss all the adjacent context in WhatsApp and iMessage — and never piece together the timeline of what actually happened. The graph is what makes that adjacent context cheap to retrieve.

That’s really just the foundation. On top of it, you can use the Omnesis agent to query the most intimate, private corners of your digital life. It runs against your indexed corpus on your own Mac Mini, with optional at-rest encryption for the main local databases and supported secrets. If you enable cloud inference, we recommend a zero-data-retention provider. The built-in agent has no web navigation or search. If you’d rather, you can plug in your own agent — Hermes, OpenClaw, Claude — so you get the benefit of Omnesis with something that can actually act on the world. That’s at your own risk, but I do plan to invest in guardrails should you decide to go that route.

Everything above is already implemented. But what really interests me is the leap from a system that simply stores your context to one that genuinely understands it. What I’ve built so far is very reactive — it responds when you query it. I want to go further: to something that proactively tells you what you need to know, exactly when you need to know it. So much of life is made of “open loops” — decisions you need to make, tasks you need to handle, commitments you need to meet. What if we had a product that carried that cognitive load for you and handed back control:

By synchronizing, indexing, and connecting all your data, we’ve done all the messy work of building a strong data foundation — one we can now take for granted. The genuinely hard, but also genuinely exciting, part is everything built on top to reach the vision above. I’m eager to build a cognitive layer that works quietly in the background to make sense of your life, always grounded by the undeniable truth of the context substrate underneath. And by getting that foundation rock-solid and opening it up, I’m hoping to help a community form around it — to build algorithms and experiment on top of what’s there.