The original TAC has its own repo.

Follow the instructions below to build and run the TAC demo.


Make sure you are running Docker and Docker Compose.

Quick start

Clone the repo to include sub-modules.

git clone [email protected]:fetchai/agents-tac.git --recursive && cd agents-tac

Check you have pipenv.

which pipenv

If you don't have it, install it. Instructions are here.

Create and launch a virtual environment.

pipenv --python 3.7 && pipenv shell

Install the dependencies.

pipenv install

Install the package.

python install

Run the launch script. This may take a while.

python scripts/

The visdom server is now running.

The controller GUI at http://localhost:8097 provides real time insights.

In the Environment tab, make sure you have the tac_controller environment selected.

AEA Visdom UI

Alternative build and run

In a new terminal window, clone the repo, build the sandbox, and launch it.

git clone [email protected]:fetchai/agents-tac.git --recursive && cd agents-tac
pipenv --python 3.7 && pipenv shell
python install
cd sandbox && docker-compose build
docker-compose up

In a new terminal window, enter the virtual environment, and connect a template agent to the sandbox.

pipenv shell
python templates/v1/ --name my_agent --dashboard

Click through to the controller GUI.

Possible gotchas

Stop all running containers before restart.

docker stop $(docker ps -q)

To remove all images, run the following command.

# mac
docker ps -q | xargs docker stop ; docker system prune -a