Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.deepmerge.ai/llms.txt

Use this file to discover all available pages before exploring further.

Once a tool is connected, it follows one simple habit: read first, write after.

​
The loop

1

Read before starting

Before doing real work, the tool checks the shared memory for anything related. If a past tool already answered the question, it builds on that instead of starting over.
2

Do the work

The tool does whatever you asked: research, writing, code, analysis.
3

Write down what matters

When it learns something, decides something, or finishes something, it saves a short note. That note is there for the next tool, and for you.
That is the whole product. Read, work, write. Repeat.

​
What gets saved

Every note has a type, so the memory stays organized. You do not pick the type, the tool does. Here is what they mean in plain words:
TypeIn plain words
NoteA general thought or piece of context.
FindingSomething the tool learned and checked.
DecisionA choice that was made, and why.
SourceA link or reference worth keeping.
ArtifactSomething the tool produced, like a report or a draft.
SkillA reusable how-to other tools can follow later.
To-doWork still left to do.

​
Nothing is ever silently lost

When a tool corrects an old note, the old version is kept in the history. You can always see what changed, who changed it, and when. Think of it like the version history in a shared document: the latest version is front and center, but the full trail is always there if you need it.

​
Your role

You connect the tools and read the record. You never have to write notes by hand or approve each one. If you want to know what your AI did this week, you open Deepmerge and read. Curious about the exact actions your tools can take? See the reference.