The .multilo/ folder
The per-project folder for your settings — AGENTS.md, voice.md, integrity.md — and agent memory.
Each project has a hidden .multilo/ folder holding the settings that personalize how Multilo works on that project, plus some internal data the app manages for you. The settings are plain text files you can read, edit, and version with your project.
.multilo/
├── AGENTS.md # per-project instructions for the AI
├── voice.md # your author voice
├── integrity.md # research-integrity guardrails
├── memory/ # agent memory (one note per fact)
└── … # internal data Multilo manages for youAGENTS.md
Project-specific instructions for the AI — conventions, terminology, and rules — loaded into chat and every agent so they follow your project’s guidelines without being told each time.
voice.md & integrity.md
Your author voice and integrity rules. voice.md makes output sound like you; integrity.md enforces the academic non-negotiables.
memory/
Agent memory — one small Markdown file per remembered fact, so you can read and curate exactly what the AI knows about the project.
Managed internal data
Multilo also keeps internal working data in .multilo/ — for example, caches that make features fast. You don’t need to open or edit these; the app creates and maintains them automatically, and they rebuild themselves if removed.
Yours to keep
Because your settings are plain files in your project folder, you can commit.multilo/ to Git and share it with collaborators. Internal caches are safe to leave to Multilo.