❯What's the safest way to handle a redirect URL that comes from user input?
I'll check your library before recommending an approach.
Step 1: Ask.
Ask your AI anything. It'll answer. That's the problem.
Trove gives it certified knowledge, so when it answers, you know why to believe it.
Your AI learned from the internet. But more of that internet is AI-written every year, not checked, not expert, just repeated until it sounds true.
HOW IT WORKS
From install to a cited answer, in four steps.
01Install Trove
A quick plugin install connects Trove to the AI tools you already use: Claude Code, Codex, Cursor, or Cowork.
One plugin for Claude Code, Codex or Cursor.
02Add your knowledge
Upload your own docs and books to start. Subscribe to more from the marketplace as it grows.
Your docs, plus books from the marketplace.
03Your agent knows
Same agent, same workflow, just with full access to the right knowledge, reached for automatically.
Reached for automatically, no new habit.
04Trust the answer
Every answer comes with its source and page attached. No second-guessing, you know why to believe it.
Every answer arrives with its source and page.
SEE TROVE IN ACTION
Ask anything. Get the actual page it came from.
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.
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.
- Team knowledgeEverything you learn next, reviewed and kept.
- Your knowledgeYour docs and playbooks. Private to you.
- Published knowledgeCertified books from real authors and publishers.
Trove isn't another place your team has to search. It's the layer working behind the AI tools you already use.
Manuscripts
Your agent figured it out once. It never has to again.
A manuscript is a book that writes itself. Tell Trove what's worth keeping, and your agent adds it as it works: filed in the right chapter, versioned, and ready for every agent to read and cite.
You choose what gets kept
- Most tools
- A lesson ends with the chat, unless you stop to write it down.
- Manuscripts
- Name what's worth keeping, like “a decision and why it won”. Your agent writes it in when the task is done.
Filed, not piled up
- Most tools
- Notes pile up in a folder nobody has time to tidy.
- Manuscripts
- Each entry lands in the right chapter, so the book reads like a wiki, not a heap of notes.
Every version kept
- Most tools
- Someone overwrites a note, and what it said before is gone.
- Manuscripts
- Every save is a new version. See what changed, and restore any earlier one.
Read and cited next time
- Most tools
- Memory recalls something, but can't say where it came from.
- Manuscripts
- The next session reads the page and names it, so you can check the source.
Looks familiar. Works differently.
Your agent should read what you know, cite the page, and remember what it learned. Here's where the tools you already use stop short.
CMP · 000.0 · NONERe-explaining every session
Doing nothing
You explained it yesterday. You'll explain it again tomorrow.
- Today
- Every session starts from zero. You paste the same docs, retype the same decisions, and your agent fills the gaps by guessing.
- With Trove
- Your agent opens the book on its own, cites the page, and writes back what it learned, so tomorrow starts where today ended.
Keep doing it by hand if you only ever need the answer once.
Free to start. Your books go in and out as markdown.
Logos belong to their owners and are shown only to name the products compared. No product ratings have been assigned.
Don't just get an answer. Know why you should trust it.
Every answer comes with a receipt: where it came from, and why you can rely on it.
Answer receipt
- Every answer traces back to a named, certified source
- Surfaces what you didn't know to look for
- Stays current, never a stale snapshot
- Disagreement stays visible, not smoothed over
Source: Web Application Security · p. 214
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
Now I mostly just approve.
Trove gives me confidence my agents have the right context, grounded in trusted books instead of stale model knowledge or noisy web results.
When my Codex builds, it almost never asks me about architecture. It's like having the finest minds in the world review my code.
Trove has let me take my agentic workflows from 80% to 95% in a single Claude Code session.
Give your AI knowledge it can actually trust.
Try Trove freeConnect your library once. Use it across your AI tools.
The same certified knowledge shows up in every AI tool you use. Connect once, and you keep working where you already are.
One Trove library. Every supported agent.
Your knowledge stays under your control.
Never used to train models
We don't train models on your content. Not for you. Not for anyone else.
Delete a book, it's gone
Removed from storage, not just hidden.
Delete your account, your library goes too
Nothing lingers behind.
No exceptions, not even us
Everything we know lives in Trove too, under the same rules as yours.
Private by default
Visible to you, and anyone you choose to publish to.
Start small. Let your knowledge compound.
MonthlyAnnual Save 20%
Monthly billing
Personal
To get started
Free
- 5 items in your library
- 100 agent reads per month
- Uploads up to 100MB per file
- 2-week Pro trial, no card required
Try Trove free
Most popular
Pro
For unlimited, everyday use
$19/month
- Everything in Personal
- 200 items in your library
- Unlimited agent reads per month
- Uploads up to 500MB per file
- Publish to the marketplace
- Priority processing
Get Trove Pro
Team
For teams who share what they know
$30/user/month
- Everything in Pro
- Shared team libraries
- Team management
- Usage analytics
- Centralized billing
- 2-seat minimum
Get Trove Team
- 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.
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, Codex, and Cowork 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.