The layer / Memory and knowledge
Knowledge engine, live
WikiLLM
From a folder of documents to a living wiki.
WikiLLM reads PDF, Word, Excel, CSV and Markdown files and produces a structured, cross-linked wiki from them. Pages are classified, written and linked automatically, and the wiki is regenerated whenever the source documents change.
Why it matters.
Documentation is rarely missing; it is scattered and unstructured. WikiLLM turns an existing document estate into navigable knowledge without asking anyone to rewrite it.
Broad format support
PDF, Word, Excel, CSV and Markdown in a single project.
Automatic structure
Topics are identified, classified and cross-linked.
Always current
Changes to source files flow through to the wiki.
Choice of model
Claude, Gemini or a local Ollama model for confidential material.
Where teams use WikiLLM.
Policy libraries
Turn a shared drive of procedures into a searchable handbook.
Project hand-over
Generate a wiki from a project's documentation in minutes.
Agent grounding
Give agents a curated, cross-linked view of company knowledge.
How WikiLLM connects.
WikiLLM relies on the shared foundations of the layer and works alongside the services below. See the full architecture.
Takes part in: a question answered from your own knowledge.
More in memory and knowledge.
Let's build it together.
Whether you want to run your own agents on the layer, discuss one of our products, or need a partner for an AI, Java or enterprise project, we respond within one working day.