livn

A testbed for learning to interact with in vitro neural networks

🧪 Multiple Backends

Run simulations using brian2, NEURON, or JAX backends depending on your needs.

Observe neural activity through realistic multi-electrode array configurations.

Differentiate through the simulation environment when using the JAX backend.

Standard Gymnasium interface for reinforcement learning experiments.

Access pre-generated datasets on Hugging Face for training and evaluation.

Scale up with MPI-based parallel simulations for large-scale experiments on CPU and GPU.