agi-core Demo

Use this page only when you intentionally want the notebook path first.

If you want the main AGILAB product path first, use Quick-Start and run the built-in flight_project from the web UI. This page is the smallest published-package notebook route for the built-in MyCode example app.

Start here

Use the Kaggle launcher first:

Open In Kaggle

This launcher installs the published AGILAB runtime packages into an isolated Kaggle venv under /kaggle/working and runs the built-in MyCode example app (mycode_project) without mutating the base notebook kernel packages.

Kaggle note: enable Internet in the notebook settings for the first install.

What will happen

The first notebook does only one thing:

  • it prepares an isolated runtime environment from published packages

  • it loads the built-in MyCode example app

  • it runs one local AGI.run(...) call

  • it shows you where the run artifacts were written

What success looks like

You are past the notebook newcomer hurdle when both are true:

  • the notebook run finishes without error

  • you can inspect fresh output under ~/log/execute/mycode

Local PyPI fallback

If you want local Jupyter instead of Kaggle, use the published packages in a clean environment:

mkdir ~/agi-core-demo && cd ~/agi-core-demo
uv venv
source .venv/bin/activate
uv pip install agilab
uv run --with jupyterlab jupyter lab

Then use the minimal notebook cells below in a blank notebook.

Minimal notebook cells

Cell 1: select the built-in MyCode example app.

from agi_env import AgiEnv

APP = "mycode_project"  # built-in MyCode example app
app_env = AgiEnv(app=APP, verbose=1)

Cell 2: run the smallest local AGI.run(...) shape.

from agi_cluster.agi_distributor import AGI, RunRequest

request = RunRequest(
    scheduler="127.0.0.1",
    workers={"127.0.0.1": 1},
    mode=AGI.PYTHON_MODE,
)
result = await AGI.run(app_env, request=request)
result

Cell 3: inspect the run artifacts.

from pathlib import Path

log_root = Path.home() / "log" / "execute" / "mycode"
print(log_root)

How this maps back to the web UI

  • Notebook AgiEnv(app=\"mycode_project\") corresponds to choosing the built-in MyCode example app in PROJECT.

  • Notebook AGI.run(...) corresponds to the generated snippet from ORCHESTRATE.

  • The output path under ~/log/execute/mycode is the same family of artifacts the UI writes and reuses.

Advanced notebook routes

If you want source-checkout launchers, benchmark notebooks, Data + DAG, worker path inspection, or the source-checkout local notebook flow, use Advanced Notebook Routes.