Domain-Agnostic
One config file customizes everything. Works for AI research, finance, healthcare, marketing, or any knowledge domain.
Ingest sources. Compile a structured wiki. Browse in Obsidian. Works with any domain.

The full pipeline: sources → /ingest → raw/ receipts → /compile → wiki/ knowledge → used via Obsidian, /query (with workspace write-back), and agents — with the deterministic script rails underneath.
URLs / Files / PDFs
|
v
+--------------+
| /ingest | Fetch + clean source → raw/
+--------------+
|
v
+--------------+
| /compile | Extract entities, build articles → wiki/
+--------------+
|
v
+--------------+
| /rebuild | Stage + validate a replacement (after deletion)
+--------------+
|
v
+--------------+
| Obsidian | Browse, graph view, backlinks
+--------------+
/rebuildis only needed after manually deleting raw source files. Normal operation uses/ingestand/compile.
The LLM writes all wiki content. You provide sources, the LLM maintains wiki/. You never edit KB articles directly — just read them in Obsidian. Create your own notes in wiki/workspaces/.