Collective Knowledge crowd-tuning extension to let users crowdsource their experiments (using portable Collective Knowledge workflows) such as performance benchmarking, auto tuning and machine learning across diverse platforms with Linux, Windows, MacOS and Android provided by volunteers. Demo of DNN crowd-benchmarking and crowd-tuning:

A DIMensional REDuction library for reproducing and experimenting with Polis-like data pipelines.

Core Python Programming and Designing Learning Algorithms from toby segaran's book for Building Smart Web Applications using machine learning Algorithms

🐍 Aggregate computing, reimagined for Python. Develop adaptive, distributed systems with ease.

A minimalist, discrete multi-agent predator-prey archytype environment.

A Deep Learning Framework for Quantifying Collective Forest Intelligence Through Multi-Variable Temporal-Spatial Analysis

Visual tool to explore variants of Polis-like data pipelines.

(A reboot of) a Pinax-based platform for crowd-sourced collaborative corpus linguistics

Software will be for creating an online community for anonymous proposal and collaborative evaluation of public policy options, with decision support.

Service-driven collective intelligence framework for human-AI collaboration

First swarm formed through Torus abstractions, over the problem space of finding the internet's prophets.

“The Testament Uploader — GUI + CLI to archive wisdom (IA + Zenodo)”

MARL research project, where agents collaboratively self-organize inside dynamically generated geometric patterns.

a neural network architecture based on a hierarchy of groups of neurons.

🤪🧠💥 Mixture of Idiots (MoI): A Python project exploring 'Mixture of Models' (MOM) to solve complex problems by combining outputs from multiple LLMs (OpenAI, MistralAI, Gemini) using King, Duopoly, and Democracy architectures. Sometimes, a team of 'idiots' is surprisingly brilliant!

fish_school_ground_truth contains the tracking data and files of the example in the paper "A data-driven procedure for modeling collective behavior" by de Andrade et al. (2024).

Messenger BOT for helping refugees with key information in Serbia.

This project evaluated the collective intelligence potential of collaborating machine learning models, primarily large language models, that are integrated into a mult-agent system.

Study notes on 『集合知プログラミング』(Programming Collective Intelligence)