Think less. Remember everything.
Taggard is the memory engine for notes and documents. Every note you save gets two kinds of tags - ones you write for browsing, and ones Taggard writes for deep, cross-referenced recall you'll never have to search for by hand.
Taggard captures what you know, understands what it means, and surfaces it exactly when you need it.
Not keyword search. Intelligent retrieval.
Two kinds of tags. One set for you, one for the machine.
Visible tags are the labels you'd write anyway - a name, a project, a date - as many or as few as you want. Underneath, Taggard builds a second, hidden layer of dozens more: concept nodes, sentiment, decision points, confidence scores - signals no human would bother tagging by hand, and ordinary search can't see.
Q3 Planning Notes
Team agreed to delay the senior hire until Q4 and reallocate the budget toward contractor support. Acme renewal still open - revisit after the board review.
“Show me what this connects to.”
Most tools find documents you remember. Taggard finds documents you forgot - and explains why they're connected. Ask a question in plain English. Get an answer built from across everything you've ever captured, with sources cited.
| Keyword search | Taggard |
|---|---|
| Matches exact words | Matches meaning and intent |
| Returns files | Returns connected insights |
| You choose what to search for | Taggard surfaces what you forgot |
| Finds what you know exists | Finds what you didn't know you had |
Capture → Understand → Tag → Connect → Rediscover → Reason
Capture
Drop a document, paste text, or add a URL.
Understand
AI reads, summarises, and extracts meaning.
Tag
Visible tags you control. Hidden signals the machine learns from.
Connect
Entities, relationships, and themes mapped automatically.
Rediscover
You wrote something related to this three months ago.
Reason
Ask anything. Get answers from across your knowledge base.
Private by design. Yours by default.
Your knowledge is the most sensitive thing you own. Taggard protects it with database-enforced isolation today - and a roadmap toward fully offline processing. We never sell your data, never train models on it, and never lock you in.
Encrypted cloud
AES-256 at rest, TLS 1.3 in transit, and Row-Level Security so the database - not just the app - keeps your notes yours.
On-device embeddings
Your browser turns documents into vectors locally. The raw text never leaves your machine - only the math does.
Fully offline
A native desktop app for regulated work: local models, local vector database, local storage. The internet is optional.
How is a hidden tag different from a regular tag?
A visible tag is a word you chose. A hidden tag is a vector or concept node Taggard generates from the note's actual content - it can't be browsed, but it can be matched against every other note you've ever written.
Does Taggard replace my note app?
No - Taggard sits alongside where you already write, reading and indexing what you save so it can surface connections later.
Can I still browse by visible tags only?
Yes - the visible layer works exactly like ordinary tags. The hidden layer runs underneath, and only surfaces when it finds a connection worth showing you.
What happens to my data?
Your notes and their hidden signals stay private to your account. Nothing is used to train models outside your own workspace.
Your knowledge is already there.
Every document you capture makes the system smarter. Start with anything - a note, a PDF, a URL.
