Quick Start¶
Get Agentomics-ML running in under 5 minutes using pre-built Docker images.
Prerequisites¶
- Docker installed and running
- An API key from a configured provider, such as OpenRouter or OpenAI
Steps¶
1. Clone the Repository¶
2. Create a .env File and Set a Key¶
Docker mode requires a .env file in the repo root.
cp .env.example .env
# Edit .env and set at least one provider key:
# OPENROUTER_API_KEY, OPENAI_API_KEY, or ANTHROPIC_API_KEY
3. Run the Agent¶
4. Follow the Interactive Prompts¶
The agent will prompt you to:
- Select a model - Choose from available LLMs
- Select a dataset - Use your own or download examples
- Configure iterations - How many optimization cycles to run
The validation metric defaults to AUROC for classification and MAE for regression. To choose one explicitly, pass --val-metric; see ./run.sh --list-metrics.
Using Your Own Dataset¶
Place your data in datasets/<your_dataset_name>/:
datasets/my_dataset/
├── train/
│ ├── input/ # Required: model input files
│ └── labels.csv # Required: id,label
├── validation/ # Optional
│ ├── input/
│ └── labels.csv
└── dataset_description.md
(Optional) Put hidden test data under the matching test_datasets/ folder:
See Preparing Datasets for details.
Example Datasets¶
Download example dataset to try:
List other available examples with:
What Happens Next¶
The agent will:
- Prepare your dataset
- Run iterative ML development cycles
- Save the best model to
outputs/<agent_id>/
Results include trained models, inference scripts, markdown reports in outputs/<agent_id>/reports/markdown/, and PDF reports in outputs/<agent_id>/reports/pdf/.
Next Steps¶
- Installation Options - Docker build, local mode, Ollama
- Running the Agent - Advanced usage
- CLI Options - All available flags