OpenCognit
The Brain · Neurons, Atlas, Layers

See where
your agents are working.

Your project as a living map. When an agent reads or changes a file, a pulse runs to it in the agent’s colour — so you see at a glance who works where, and what came out of it.

See it run

Three ways to see
what your agents do.

What you get

Your codebase,
drawn as it lives.

I

Neurons

Every folder a neuron, every subfolder a stem, every file a tip. When an agent reads or edits a file, a pulse runs to it — in the agent’s colour.

II

Atlas

Your codebase as a map of lobes, one per area, sized by its files. Changed cells light up, and the agents sit where they work.

III

Layers

Agents on the left, project areas in the middle, outcomes on the right: files to review, tests, commits — and who needs you.

IV

Live, not afterwards

Threads, the orchestrator and Claude Code, Codex and Gemini in a terminal show up the moment they touch a file.

V

Click to act

Click a neuron to fly there, click an agent to open its chat, click an area to pin it.

VI

Calm by default

Names and numbers appear when you point at them, so the picture stays quiet while dozens of agents work.

How it works

Three steps to the map.

I

Install OpenCognit

Linux or Windows.

II

Open a project

Its folders become the map — no setup.

III

Start your agents

Open the Graph in the left rail and watch them work.

Questions about the Brain

Which agents appear on the map?

Threads, the orchestrator and Claude Code, Codex and Gemini in a terminal right away; other terminal CLIs as soon as their log is readable.

Does the map send my code anywhere?

No. It is built from your project folder and the agents’ events on your own computer.

Does it work with big projects?

Yes — large folders are split into ranges so the map stays readable.

Does it run on macOS?

Not yet. OpenCognit is available for Linux and Windows.

What does it cost?

Free with up to 4 agents and 2 projects. Pro is a one-time purchase — no subscription on top of your plan.