- San Francisco, CA
-
06:33
(UTC -07:00) - https://orcid.org/0000-0002-8235-5969
- @gabepgomes
- in/gabe-gomes
- @gabegomes.bsky.social
Highlights
Lists (3)
Sort Name ascending (A-Z)
Starred repositories
Reaction Analysis through Imaging of Chemical Units
Python-based Informatics Kit for Analysing Chemical Units
Software package for computer aided synthesis planning
Optimize prompts, code, and more with AI-powered Reflective Text Evolution
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
LLM-powered agents for scientific research automation
Uncertainty quantification (UQ) for Machine-Learning Interatomic Potentials (MLIPs)
An Automated AI Agent Tool for Plotting Your Data in Any Paper's Figure Style.
DeepDelta is a pairwise deep learning approach based on Chemprop that processes two molecules simultaneously and learns to predict property differences between two molecules.
Simple Python interface to OPSIN: Open Parser for Systematic IUPAC nomenclature
The ReactionMechanismGenerator Database Standard and Database
Chemprop model incorporating the Arrhenius equation at the output to add physics to predictions
A Python library for building AI agents that leverage the full power of Google Antigravity.
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a querya…
Uses publisher APIs to programmatically retrieve scientific journal articles for text mining.
This set of essential and valuable microservices is designed to be accessed via API calls to support cheminformatics.
SCORE MLX Distilled CheMeleon molecular fingerprints for Apple Silicon
GPU-accelerated operations for MLX on Apple Silicon — batched linalg (Metal Cholesky/solve, 25-40x faster) + KNN (Z-tree + Metal top-k)