Research Open Source

Where Nature
Inspires
Intelligence

NatureCast is an open research initiative studying how biological systems — from neurons to ecosystems — can transform the design of artificial intelligence. We publish code, models, benchmarks, and ideas.

12+
Open Projects
38+
Research Posts
7
Research Areas
100%
Open Source

Bridging biology and machine learning

Billions of years of evolution have produced extraordinarily efficient information-processing systems. We study these systems — and translate their principles into better AI.

Neuroscience-Inspired AI

Drawing on decades of neuroscience research to design neural architectures that mirror biological learning — attention, memory consolidation, and predictive coding.

Nature-Inspired Algorithms

Evolutionary computation, swarm intelligence, and biological optimization strategies applied to the hardest open problems in machine learning.

State-of-the-Art LLMs

Rigorous benchmarking, interpretability studies, and efficiency research on frontier large language models and multimodal systems.

NatureCast Research Pipeline Biological Systems neurons · evolution Abstract Principles pattern · mechanism AI / ML Implementation model · code · eval Spiking NNs Leaky I&F · STDP low-power · temporal coding · plasticity Evolutionary GA · CMA-ES · NAS fitness landscape selection · mutation LLM Eval bench · interpret model comparison MMLU · HumanEval

Figure 1. NatureCast research pipeline — from biology to AI implementation.

A systematic pipeline from biology to code

We study biological intelligence at multiple scales — from single neurons to whole ecosystems — and systematically extract computational principles that can improve artificial systems.

Every project ships working code, reproducible benchmarks, and clear documentation so others can build on our work.

01.
Observe

Literature review and experimental analysis of biological mechanisms.

02.
Abstract

Distill computational principles that generalise beyond biology.

03.
Implement & Evaluate

Build, benchmark, and openly publish models and code.

Active Projects

View All Projects →
Neuroscience AI

NeuroSynth-SNN

Biologically-inspired spiking neural network framework implementing leaky integrate-and-fire neurons with STDP learning rules. Achieves competitive accuracy at 10× lower energy cost on temporal tasks.

Python PyTorch STDP Neuromorphic
Nature-Inspired

EvoSearch-NAS

Evolutionary neural architecture search using CMA-ES and genetic programming. Discovers efficient transformer variants inspired by natural selection and co-evolution dynamics.

Python CMA-ES NAS JAX
LLM Research

OmniEval-LLM

Comprehensive evaluation framework for large language models across reasoning, coding, science, and instruction-following benchmarks. Reproducible, hardware-aware comparisons.

Python vLLM MMLU HumanEval

From the Blog

All Posts →
📅 Apr 07, 2025 ⏱ 14 min

The LLM benchmark landscape is a mess — inconsistent prompting, unreported hardware, cherry-picked tasks. We present OmniEval, a reproducible evaluation...

📅 Mar 10, 2025 ⏱ 10 min

Spiking neural networks (SNNs) represent information the same way biological neurons do — in discrete spikes through time. After years in the shadow of ...

📅 Feb 14, 2025 ⏱ 12 min

The transformer's attention mechanism was revolutionary — but it bears only a surface resemblance to biological attention. We explore the neuroscience o...

Join the research conversation

All our code, datasets, and findings are open-source. Contribute on GitHub, follow the blog, or reach out to collaborate.