Compile knowledge once. Query it forever.
The wiki that maintains itself: ingests documents, extracts entities, and compiles a persistent, interconnected markdown knowledge base agents can query over MCP.
npm install -g axiom-wiki
axiom-wiki init # provider, wiki directory, source folder
axiom-wiki ingest # drop files into raw/ and compileRetrieval re-derives. Compilation persists.
Ask a question, search raw sources, rebuild context from scratch — every query pays the full cost again, and the same source can yield different answers depending on retrieval luck.
Ingest sources once into interconnected markdown pages — entities, links, indexes, and graph structure — then keep them current as new material arrives. The knowledge base compounds instead of resetting.
Inspired by Andrej Karpathy's llm-wiki: the LLM should maintain a persistent wiki rather than re-derive answers from raw sources on every query.
From raw/ to a living wiki.
Ingest
Drop documents into raw/. Axiom extracts entities and compiles them into wiki pages with links, indexes, and search built in.
Auto-wiki mode
The wiki decides what deserves a page and how pages connect, instead of mirroring your folder structure.
Incremental compilation
New sources update existing pages rather than regenerating from scratch — cost and time stay proportional to what changed.
Self-maintaining sync
As sources evolve, the wiki reconciles: pages stay current without manual curation.
Every page, connected.
Entity pages
Sources compile into markdown pages organized around entities, not files.
Links & graph
Pages reference each other, forming a browsable structure of what's known.
Indexes & search
Hybrid search across the wiki, so lookups stay fast as it grows.
Agent instructions
The wiki documents itself for LLM consumption, not just human reading.
The same knowledge base, over MCP.
Axiom ships an MCP server, so coding agents and assistants query the same compiled wiki people do — through hybrid search and the page graph rather than raw-file retrieval. Provider-agnostic by design, with health and cost visibility so compilation stays observable.