47,133 repositories indexed
25–38 of 38 · Most stars
FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence
Code for all experiments.
Evidence-aware Japanese speech visualization: pitch and intonation, waveform inspection, and experimental alignment.
TransformerCPI: Improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments(BIOINFORMATICS 2020) https://doi.org/10.1093/bioinformatics/btaa524
⚗ Experimental Hermes Agent plugins built by Nous Research but not supported: community tier in the plugin catalog, up for adoption.
A/B testing for Wagtail
Experimental packages for ROS access to Open Street Map information
Python application to setup and run streaming (contextual) bandit experiments.
My MicroPython experiments
Enterprise-grade platform to generate and execute Cypress, Playwright, WebdriverIO, and Appium end-to-end tests from natural language requirements. (Appium is experimental and requires external mobile infrastructure.)
Experiment to rewrite Python into PyTeal using RedBaron
A MicroPython-based frequency generator for Raspberry Pi Pico designed to create vibrations on solenoids or speakers, enabling wave experimentation and exploration at home.
Code for the experiment proposed in Section 4.2 of the paper "The Bouncer Problem: Challenges to Remote Explainability".
Machine learning model evaluation made easy: plots, tables, HTML reports, experiment tracking and Jupyter notebook analysis.