Install, configure, and run your first cognitive cycle in under 5 minutes.
What you need before installing
Required for the core library and CLI. Check with python --version.
Required only for CLI chat mode. Install from ollama.com.
| Interface | Requirements |
|---|---|
| Python Library | Python 3.9+, numpy, scipy |
CLI (neuro) |
Python 3.9+ and Ollama |
| Web REPL | Browser only |
Install via pip or from source
Install from PyPI:
pip install elo-agiOr install from source with development dependencies:
git clone https://github.com/ezekaj/elo-agi.git
cd elo-agi
pip install -e ".[dev]"Run the perceive-think-act loop in Python
from neuro import CognitiveCore
core = CognitiveCore()
core.initialize()
core.perceive({"text": "Hello, world"})
core.think()
action = core.act()
print(action)
The CognitiveCore runs the active inference loop: perceive sensory input, think using free energy minimization across all 38 modules, and act based on the integrated cognitive state.
Use the neuro command-line interface
neuro # Interactive session
neuro --version # Check installation
neuro info # System informationExplore built-in demonstration scenarios
neuro-demo all # Run all demos
neuro-demo medical # Medical reasoning
neuro-demo physics # Physics simulation
neuro-demo creative # Creative problem solvingEvaluate cognitive performance across 627 tests
neuro-bench -o report.htmlGenerates an HTML report with scores across 5 categories: Causal Reasoning (0.85), Compositional Abstraction (0.74), Continual Learning (0.72), Robustness (0.71), and Language Understanding (0.69). 627 tests total.
What's Next
Dive deeper into the architecture and capabilities.
Try the interactive demo or dive into the full feature set.