You keep working in the AI you already use. When it needs knowledge, Trove finds the passage and brings it back with the citation attached.
Example 1 of 9
WarpSearch sessions, agents, files…
❯What's the safest way to handle a redirect URL that comes from user input?
I'll check your library before recommending an approach.
Trove LibrarianFinding relevant books…
Web Application Security
Trove ReaderReading relevant passages…
Web Application Security · p. 214
Validate and allow-list outbound URLs server-side. Never trust a client-supplied redirect.
Web Application Securityp. 214
Step 1: Ask.
✻ Claude Code · Trove connected
❯
➜ demo-projectmain · Claude Code
Terminal~/demo-project
01 / 09
Every example above is a real session from a real Trove user.
When sources disagree
Two certified sources. Two different answers. No invented consensus. You see both, with where each one came from.
Even when you don't know what to ask
Trove doesn't just wait for a question. It surfaces a relevant book or passage on its own, and if the right book isn't in your library yet, it tells you that too, instead of guessing.
LIVING KNOWLEDGE
All the knowledge your AI should have.
One place.
Published knowledge
Certified books and expertise from real authors and publishers, made readable by AI.
Your knowledge
Your documents, playbooks, and guidelines. Private to you, and your company if you're part of one.
Team knowledge
Everything you learn next, reviewed and kept for the next time it matters.
Trove isn't another place your team has to search. It's the layer working behind the AI tools you already use.
What you learn, nobody has to repeat.
The gotcha you find at 1am shouldn't die with the chat. Approve it once, and your next session already knows. So does your team's.
How ≠ Why
SkillsThe how
Reusable steps, written down on purpose.
The why
What's in your head stays there. Unless it's in Trove.
Don't just get an answer. Know why you should trust it.
Every answer traces back to a named, certified source. No black-box guesses.
Surfaces what your team didn't know to look for, not just what they searched.
Knowledge stays current automatically. Never a stale snapshot.
Disagreement stays visible instead of getting smoothed into one confident answer.
Draft comparison · final criteria and content pending
Looks familiar. Works differently.
Comparison layout placeholder. No product ratings have been assigned.
Criteria to be defined
Trove
Other approaches
Criterion 1 · pending
To be defined
To be defined
Criterion 2 · pending
To be defined
To be defined
Criterion 3 · pending
To be defined
To be defined
Criterion 4 · pending
To be defined
To be defined
Illustrative story · draft, not a verified customer result
ALREADY TRUE FOR PEOPLE LIKE YOU
From 80% to 100%, on the document that mattered.
A compliance team wanted every tender checked against the real standard before filing, not against a general sense of what usually works. Their agent reads the standard through Trove and checks the tender line by line.
Illustrative result, pending verification
Illustrative story80% to 100% tender approval quality.
Now I mostly just approve.
M. MarudiAI Engineer, Cyera
Trove gives me confidence my agents have the right context, grounded in trusted books instead of stale model knowledge or noisy web results.
Placeholder, real customer quote needed
Namerole, company
Real customer quote goes here.
Placeholder, real customer quote needed
Namerole, company
Real customer quote goes here.
Illustrative result, pending verification
Illustrative story80% to 100% tender approval quality.
Now I mostly just approve.
M. MarudiAI Engineer, Cyera
Trove gives me confidence my agents have the right context, grounded in trusted books instead of stale model knowledge or noisy web results.
An "item" is anything in your library, a published book, your own document, or a manuscript.
An "agent read" is counted each time an agent opens a page.
"Publish" means putting a book or manuscript into the marketplace for others to use.
Start free. Upgrade when your library needs more room.
Questions, answered
The important things to know before you get started
A living library for AI agents. Your agents work from certified knowledge, and every answer traces back to a real, named source.
No. Claude Code, Cursor, and Codex are where you work. Trove is the certified library they read from, so you keep using the tools you already have, just backed by knowledge they can cite.
No. The Trove librarian, your agent's own research assistant, finds the relevant books, reads them, and cites what it used. If nothing in your library fits, it says so and suggests the book to add.
Every answer comes back with the actual source and page cited, so you can check it yourself instead of taking it on faith.
A lot of what you actually need isn't on the web at all, your team's decisions, the paid books, the playbook your best engineer carries in her head. What is on the web is noisy and increasingly AI writing about AI. With a library, the shelf is stocked in advance and your agent reads human-written, vetted books it can cite.
You see both, each with its own citation, instead of one confident-sounding blend.
No. Personal is free and built for exactly that, one person, one library.
No. We don't train models on your content, and we don't use it to train anyone else's.
Personal is free, no card required for the trial. Cancellation and refund terms are being defined now.
Your AI is already powerful. Give it something worth knowing.
Your agents work from certified knowledge, and teach each other everything your team learns.