Skip to main content

What is Agivar

Agivar is a desktop AI assistant that runs on your computer. It has two abilities that feed each other:

  • It gets things done for you — it understands what you need, plans the steps itself, and then drives your desktop GUI, runs commands, and works with files to complete the task.
  • You can teach it — teach Agivar how to operate a particular app or website, enter business rules, or share your personal preferences. In particular, you can demonstrate a process with a screen recording so Agivar can retain that experience and reuse it for related tasks in the future.

In short: the more you use and teach Agivar, the better it understands your computer and the way you work.

Two working modes​

Task ModeTeach Mode
What you're doingAsking Agivar to execute a taskTeaching Agivar knowledge, a workflow, or a preference
What it doesPlan → drive the GUI / run commands → verify → reportUnderstand your explanation / demo → distill it into a reusable entry → write it to the memory base
Typical input"Compress all the images in this folder"
"Give 2 coins to this creator on Bilibili"		"Let me show you how to submit an invoice in our expense system"
(with a screen recording) "follow this workflow"
OutputTask done + summaryA memory entry (filed under platform/topic)

Both modes live in the same chat window — pick the mode when you start a new conversation. Once a conversation has any messages, its mode is locked and can't be changed.

The "teach → remember → execute" loop​

   Teach Mode                       Memory base                    Task Mode
┌────────────────┐  distilled into  ┌──────────────────────┐  read before  ┌──────────────┐
│ you explain /  │ ───────────────▶ │ platform/topic +      │ ────────────▶ │ follows the  │
│ screen-record  │                  │ operation description │   executing   │ workflow,    │
│ a demo         │                  │ + (optional) recording│               │ fewer detours│
└────────────────┘                  └──────────────────────┘               └──────────────┘
  • A screen recording is processed automatically: keyframes are extracted, a short video summary is generated, and a structured "operation description" is produced (Overview / Initial state / Step-by-step / "stage result" after each step).
  • What it learns goes into the memory base, organized as platform/topic (e.g. bilibili/coins, general/expense-rules).
  • Before running a GUI task, Task Mode consults the memory base. If an entry references a recording, Agivar can ask targeted questions about details in that recording when necessary.

Who it's for​

  • People who frequently repeat the same operations on certain sites or apps and want the AI to take over once it has learned them.
  • Teams with internal workflows that "only you know" (expenses, approvals, listing products…) that you'd like to turn into reusable know-how.
  • Anyone who wants the AI to follow their preferences and rules when working on their computer without explaining them again every time.

Next​