Welcome to the EvOC (Evolutionary Algorithms On Click) organization!
EvOC is a user-friendly framework for designing, executing, and analyzing various evolutionary algorithms (EA, GP, PSO, ML Tuning) through an intuitive graphical interface. Perfect for learners, researchers, and educators – no coding required to get started!
- Intuitive Configuration: Visually configure parameters for Genetic Algorithms (GA), Genetic Programming (GP), Particle Swarm Optimization (PSO), and EA for ML Tuning via a simple GUI
- Powerful Visualizations: Instantly visualize algorithm progress with fitness plots, understand results with GP trees, or observe swarm behavior with PSO animations
- Transparent Code Generation: Generate the underlying Python code (using the DEAP library) based on your GUI setup for transparency, learning, or further customization
- EA for ML Tuning: Optimize Machine Learning model features or hyperparameters using Evolutionary Algorithms
- AI-Powered Explanations: Integrated AI for clear explanations of generated code and EA concepts
- Execute, Save & Collaborate: Run experiments, track execution history, download logs, and easily share configurations and results
For detailed user documentation, visit: https://evolutionary-algorithms-on-click.github.io/user_docs/
This organization maintains the following active repositories:
- evolve_frontend - Frontend source code for Evolve On Click tool (Next.js, JavaScript)
- auth_microservice - Go Backend for authentication (Go, CockroachDB)
- runner_controller_microservice - Go Implementation of the algorithm runner controller microservice (Go, gRPC)
- runner - Algo Run Scheduler x RabbitMQ (Python, RabbitMQ)
- operations - Repository for EvOC DevOps Configs (Docker, Shell)
- user_docs - User documentation for EvOC (VitePress, Markdown)
Under development for new features
- controller_microservice_v2 - Controller microservice that handles data to and from frontend and jupyter kernel gateway (Go)
If you use EvOC in your research or work, please cite it as follows:
@inproceedings{10.1145/3712255.3726652,
author = {Murali, Ritwik and Sivamani, Ashwin Narayanan and Ramakrishnan, Abhinav and Arul, Hariharan and R, Ananya},
title = {Evolve On Click (EvOC) - An Intuitive Web Platform to Collaboratively Implement, Execute, and Visualize Evolutionary Algorithms},
year = {2025},
isbn = {9798400714641},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3712255.3726652},
doi = {10.1145/3712255.3726652},
abstract = {This paper proposes "Evolve On Click" (EvOC) - an open-source intuitive web-based platform to simplify the implementation, execution, and visualization of Evolutionary Algorithms (EAs) including genetic programming, by providing a user-friendly interface. This facilitates easier accessibility of evolutionary algorithm software packages such as DEAP, to users with minimal programming experience. EvOC guides users through the EA design process, allowing them to experiment with different algorithms, parameters, and configurations without the need for programming expertise. The platform also incorporates features to show code created based on the configuration so that users can also learn from it, thus enhancing collaboration and enabling users to easily share their results with others. The architecture used by EvOC also supports ease of access for parallel and distributed EAs with real-time log streaming / monitoring and visualization of the evolution runs. By incorporating the latest DevOps techniques during the development process, EvOC does not require extensive maintenance and allows for the platform to be run as a service, supporting multiple users on a single instance. This paper details the design, implementation, and evaluation of EvOC towards increasing accessibility and ease of comfort with EAs for novice learners - thus broadening the reach of the community.},
booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference Companion},
pages = {147–150},
numpages = {4},
keywords = {evolutionary algorithms, distributed artificial intelligence, distributed evolutionary algorithms in python, DEAP, software architectures, evolutionary computation},
location = {NH Malaga Hotel, Malaga, Spain},
series = {GECCO '25 Companion}
}This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details.