From the library
Building Your Agent Team: A Practitioner's Guide to Multi-Agent AI Systems
A companion for thinking about how knowledge moves between agents, tasks and sessions.
15 pages
Open in TroveThe reading room / Living knowledge
What you learn,
worth keeping.
The useful part of a session shouldn’t end with the chat. A Living Book gives your agent a place to keep decisions, lessons and context it can return to.
Install Trove
Your wiki is a book.
You find a tricky edge case. Make a decision. Discover why the obvious approach failed. The next session needs that context, but the conversation alone is a hard place to find it.
An LLM wiki turns that knowledge into connected pages. In Trove, it lives as a Living Book: a source your agent can browse, update and cite alongside the rest of your library.
A place for the reasoning, not just the result.
Keep what will be useful again. Give it a clear home. Let your next session start with the context you already worked to uncover.
Familiar pages. Useful structure.
A Living Book uses the same building blocks as the rest of your library. You can follow what was written and see how it changes.
A table of contents
An index helps your agent find the relevant section before opening a page.
Connected pages
Concepts, decisions and examples can point to one another.
Version history
Inspect earlier versions and restore a page when an edit needs undoing.
Sources you can follow
Read the page behind an answer, with the surrounding context still intact.
Start with what matters next.
Connect Trove to your agent
Follow the install guide for the tool you use. Your library becomes available in your existing workflow.
Give the book a purpose
Decide what belongs there: project conventions, decisions, or lessons from the work. Clear instructions make a more useful book.
Read, review and build on it
Ask your agent to record useful knowledge. Review what it writes and have it consult the book when the context matters again.
From the library
Put the idea into practice.
A Living Book is one part of an agent workflow. Go deeper into how agents share context and work together with a practical guide from the library.
Questions, answered.
What is an LLM wiki?
An LLM wiki is a collection of connected pages that an AI agent writes and maintains: concepts, decisions, an index and a changelog. In Trove, this takes the form of a Living Book your agent can read and update.
What is a Living Book?
A Living Book keeps useful knowledge in your Trove library beyond a single chat. Your agent can turn what you learn into written pages, then return to those pages when they matter again. You can inspect the content and its version history.
How does the agent read it?
It browses the table of contents, opens relevant pages and cites what it reads. The index and links between pages help it navigate the material without treating the whole book as one long prompt.
Does everything get saved automatically?
What gets written depends on the book's instructions and your agent workflow. Review-first and automatic workflows serve different needs. Set clear guidance about what belongs in the book, and inspect the result.
How is this different from retrieval?
A Living Book is an evolving document you can inspect and edit. Trove gives the agent access to its contents and pages. The focus is a maintained source of knowledge, with citations and history, rather than a set of isolated search results.
For the next time it matters
Give useful knowledge a home.
Bring your sources and what you learn into one library your agent can return to.
Get started with Trove