Everything I read is somewhere. I can't find any of it. The newsletter quote, the podcast notes, the chapter highlights, the screenshot of the diagram I swore I'd come back to — they exist, but they might as well not.
Capture works. Recall doesn't. We didn't build another note app — we built the part your biological brain isn't built for: the part that brings what matters back to you when you need it. Some people will call this a second brain. We call it the missing function of yours.
The problem isn't that you don't have notes. You have a hundred. A thousand. Highlights from books, screenshots of diagrams, the newsletter quote you saved at 11pm. They're all there, somewhere, in something.
The problem is that the words you wrote and the words you'd search for now don't match. Capture is solved — voice, web clipper, conversation-to-note, drag-and-drop. What stays unsolved is the moment, three months later, when the right note doesn't surface because you can't remember the phrasing you used to file it.
That's not a notes problem. It's a recall problem. And a biological brain isn't built to solve it — recognition is what brains do well. We forget where; we remember when we see it.
Knovya is the part of the system that does recall — so you only ever have to do recognition. Hybrid search reads keywords and meaning at once. NoteRank scores each note by how connected it is to the rest of your archive, so the strongest material rises before you finish typing the question.
AI memory surfaces forgotten notes when their topic comes up in a new draft, a new conversation, a new question — even if you didn't ask for them. The archive starts answering things you almost asked, and that's the moment a second brain begins to feel like one.
We don't call ourselves a second brain. We call it the missing function of the one you already have.
The right note, surfaced at the right moment, without you remembering you needed it.
Three moments of a typical week. Pick one — the archive lights up the part of itself it would actually use. No live data, no signup; the moves are real, the notes are illustrative.
A 14-second voice note, eyes closed, before the idea evaporates.
It surfaces three older notes already chasing the same thought, and quietly links itself in.
Tomorrow's draft opens with this idea already on the page — you didn't search for it.
When you finally write the brief, half of it is sentences you forgot you'd written.
Forte called these four moves CODE. We call them what an archive ought to do for you on its own.
Knovya doesn't ask you to follow CODE — the archive does. Here's which features carry which move, mapped to the elements you'll find on the periodic table at /features.
Get the thought out of your head before it dissolves — voice, web, conversation, drag.
Speak the idea, get a structured note.
A Claude or ChatGPT chat, saved as a real entry.
Any URL becomes a note with the source intact.
The archive arranges itself — backlinks, semantic neighbors, ranked by what's actually load-bearing.
Notes ranked by how connected they are, not when you typed them.
A view of where the dense regions of your thinking are.
Every reference visible from both sides, automatically.
The right note finds you. Hybrid search, surfacing, the precedents you forgot you had.
Keyword and meaning, ranked together.
Past decisions surface alongside the new one — the precedents are doing the talking.
Outline a chapter, summarize a meeting, extract a list.
Forgotten notes return when their topic comes up again.
The archive is the start of the next thing — drafts, briefs, exposed to every AI you use.
Publish a single note, a thread, or a cluster — keeping the rest private.
Claude, ChatGPT, Cursor — they read your archive natively.
The "second brain" arrived as a phrase in 2017. The need arrived earlier — every generation that builds knowledge faster than they can hold it. Knovya is the latest answer to a very old question: how do we keep what we know?
Bush's "As We May Think" describes a microfilm desk that links documents by association. Forty years before the web, fifty before hyperlinks, he names the move: knowledge isn't kept in folders, it's kept in trails.
A German sociologist builds a wooden slip-box of 90,000 index cards, each linked to others by hand. He cites it as his second author. The principle: keep ideas small, link them often, let connections become the work.
Ahrens translates Luhmann's slip-box for a digital audience. The book quietly seeds a decade of PKM software — Roam, Obsidian, Logseq, every app that thinks linking is the point.
Forte names the four moves: Capture, Organize, Distill, Express. The phrase "second brain" enters mainstream productivity. The methodology travels faster than any single app implementing it.
Mem 2.0, Capacities, Reflect, NotebookLM — semantic search and embeddings finally cheap enough that organization can happen after capture, not before. The "Organize" burden falls to the machine. CODE survives; the manual labor doesn't.
We built the part Bush imagined, Luhmann hand-built, Ahrens articulated, and Forte named: the trail you don't have to maintain. NoteRank ranks, Experience Envelope precedents, MCP exposes the archive to every tool you already work in. The missing function, finally external.
Every tool in this category is wagering on a piece of CODE — usually one piece, sometimes two. The honest comparison isn't features. It's which move each app decided to be best at, and which it's leaving to you.
The bet A flexible structure for everything — pages, databases, views. If you can model your work as a schema, Notion will hold it.
What's left to you Distill and surface. The content sits where you put it. Search is keyword-only; the right page doesn't come find you.
The bet Ownership and durability. Plain markdown on your machine, plugin-extensible, outlives any company.
What's left to you Organize. The vault is yours to maintain. Plugins help, but the linking discipline is on you, every day.
The bet Frictionless input. Drop a thought; the AI tags, links, and surfaces it later. The organize step disappears into the background.
What's left to you Distill into output. Capture is great; the synthesis layer — outlining, drafting, publishing — is thinner than the capture layer.
The bet The daily entry as the unit. Voice, AI assist, encrypted, journaling-shaped. Tight scope, polished surface.
What's left to you The connection graph. Entries are private and beautiful, but they don't consistently surface what you wrote three months ago when it's relevant today.
The bet The loop is the product. Capture, organize, distill, and express belong in one archive — and the archive should expose itself to every AI you already use through MCP.
What's left to you Picking what matters. Recall is on the system. Recognition — the part your brain is good at — is the only piece left for you.
We didn't pick a move to be best at. We picked the loop.
A second brain is only useful if it's reachable in the four seconds you have between thinking the thing and forgetting it. Knovya works on every surface where those seconds exist.
In the car, in the shower, mid-walk — speak the idea, get a structured note waiting on the desktop.
The graph view shows where the dense regions are forming — the topics you've returned to, the ones that drifted, the ones connecting now.
The Chrome extension turns any page into a note with the source attached and the semantic neighbors already wired in.
Through MCP, every tool you already use can read and write to your second brain — no copy-paste, no context-switch.
A second brain isn't a feature — it's a shape that the whole archive takes when its parts cooperate. Here's the constellation around this page.
Forgotten notes return when their topic comes up.
See featureNotes ranked by how connected they are to the rest.
See featureA view of where the dense regions of your thinking are forming.
See featureClaude, ChatGPT, Cursor read your archive natively.
See feature"Six weeks of Zettelkasten in Obsidian. Three hundred orphan cards."
A slip-box that organizes itself — semantic neighbors live, not after-the-fact.
See the workflow Problem 04 · Chapter I"I have a Notion full of pages. Half are stubs. The other half aren't linked to anything."
A personal wiki that builds its own spine — backlinks, semantic search, graph view.
See the workflowThe eighty-year history, the four moves Tiago Forte named, and what AI has changed since 2024.
Read the primer DefinitionThe practice underneath the second-brain idea — capture, retrieval, the recall-to-recognition shift.
Read the primerA second brain isn't built in one sitting. It's built one captured thought, one surfaced precedent, one re-read note at a time. The archive starts compounding the moment you do.
Or scroll back to the diagnosis.
Eight questions we keep getting. If yours isn't here, the contact page reaches us directly.
A second brain is an external system that holds the things your biological brain isn't built to retain — references, half-formed ideas, decisions, conversations — and brings them back to you at the moment they're useful. The term was popularized by Tiago Forte in 2017; the practice goes back to Vannevar Bush's Memex (1945) and Niklas Luhmann's slip-box.
A note app stores. A second brain surfaces. Knovya combines hybrid search (keyword and meaning at once), NoteRank (a ranking signal that scores each note by how connected it is to your archive), and AI memory that brings forgotten notes to the surface when their topic comes up in a new draft, conversation, or question.
Knovya supports the four moves Tiago Forte identified — Capture, Organize, Distill, Express — but doesn't require you to follow them rigidly. The archive does most of the organizing automatically through backlinks, NoteRank, and semantic neighbors, so the methodology becomes ambient rather than something you maintain.
Notion is a database with pages on top — strong on structure, weak on surfacing. Obsidian is local-first markdown with bidirectional links — strong on ownership, weak on automatic organization. Mem 2.0 is auto-organized AI capture — strong on quick input, narrower on synthesis. Knovya connects all four moves end to end and exposes the archive to Claude, ChatGPT, and Cursor through MCP.
Yes. Knovya Free is forever-free with 50 notes, 50 AI credits per month, and 50 MCP calls per month — enough to run a full second brain workflow on Claude or Cursor and see whether the archive starts to compound for you before paying anything.
PKM is the broader practice — capturing, organizing, retrieving the information you need to think and work. A second brain is one particular shape PKM takes: a single external archive that holds everything, organized so that what you need finds you. Knovya treats both as the same recall-to-recognition problem.
In 2026 the limiting step has moved. Capture is solved — voice, web clipping, conversation-to-note. Organization is solved on autopilot — backlinks, semantic links, NoteRank. The work AI does now is in distillation and surfacing: finding the right note when a new question arrives, drafting an outline from related entries, suggesting the connection you almost missed.
Pro and Team plans include note-level end-to-end encryption (AES-256-GCM); encrypted notes are not searchable or embeddable on the server. The Free tier uses transport encryption. Login is hardened with 2FA, device fingerprinting, and anomaly detection.