Quick-Start

AGILab is a software solution to explore AI for engineering. This quick-start walks you through the minimal steps required to install the framework, open the web interface, and run one of the sample apps. For architectural context see AGILab Architecture and AGI Core Architecture.

Prerequisites

Python 3.11+ with uv installed (curl -LsSf https://astral.sh/uv/install.sh | sh).
macOS or Linux shell (use WSL2 on Windows until native support lands).
SSH key access to any remote cluster you intend to use.
Strongly recommended for development: PyCharm Professional 2025.2+ with repository-specific settings (including bundled run configurations), and Codex CLI using the repository guidance (AGENTS.md and .codex/skills).
A minimal CLI-only workflow remains available without PyCharm by using the tools/run_configs shell wrappers, so PyCharm is not an absolute requirement.
If you need to reuse Linux-dependent code paths, prefer macOS or Linux as your development environment.

Codex workflow

From this repository, use the shared workflow helper:

./tools/codex_workflow.sh review before larger edits
./tools/codex_workflow.sh exec "short change request"
./tools/codex_workflow.sh apply <task-id>

LICENSE

New BSD. See License File.

Install AGILab

Bootstrap a workspace (keeps project files and the web interface cache in a single folder):
```
mkdir ~/agi-workspace && cd ~/agi-workspace
```
Install the published wheel using uv:
```
uv add agilab
```
Launch the web interface (runs inside the managed virtual environment):
```
uv run agilab
```
The ORCHESTRATE page opens automatically. Point the sidebar to your apps directory (defaults to ~/agi-workspace/src/agilab/apps).
Run the sample ``mycode`` app either from the UI or the CLI mirror:
```
uv run python src/agilab/examples/mycode/AGI_run_mycode.py
```
This script constructs an AgiEnv, bundles the worker, and executes a full AGI run so you can inspect the generated logs under ~/log/execute/mycode.

Run without PyCharm (CLI wrappers)

If you work from a repository checkout and do not use PyCharm, run the pre-generated wrappers under tools/run_configs directly from a shell. They mirror the bundled run configurations for built-in/public apps.

List available wrappers:

find tools/run_configs -type f -name "*.sh" | sort

Examples:

bash tools/run_configs/agilab/agilab-run-dev.sh
bash tools/run_configs/apps/builtin-flight-run.sh
bash tools/run_configs/apps/builtin-flight-test-worker.sh

Cluster installs

If you want to install on a cluster, the installer must have SSH key access or credentials with permission to deploy workers. See Cluster for the full workflow. pycharm/setup_pycharm.py mirrors web interface run configurations to ~/log/execute/<app>/AGI_*.py so that IDE and CLI stay in sync.

Note

On a virgin workspace you do not need to hand-create ~/log/execute/<app> snippets. The installer dispatcher (src/agilab/apps/install.py) calls _seed_example_scripts before kicking off AGI, copying each AGI_*.py helper from src/agilab/examples/<app>/ into ~/log/execute/<app>/ so the first install has runnable mirrors. After that initial bootstrap, the web interface ORCHESTRATE page re-generates the snippets on demand according to the form inputs you provide, keeping IDE and CLI flows in sync. Field defaults are read from each app’s app_settings.toml before the form renders, so adjust that file first when you need new baselines.

Next steps

AGILab Architecture – understand how the web interface, agi_core, agi_env and agi_cluster fit together.
Project Files Structure – explore the repository layout with an annotated tree generated by docs/gen-docs.py.
About AGILab – learn how core pages and optional page bundles fit together in the UI.
Page Bundles (apps-pages) – learn how page bundles are discovered, enabled, and launched.

Support

Email: focus@thalesgroup.com