Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

A collection of AI agent skills relevant to our work, including analysis and development of R/Bioconductor packages + statistical and bioinformatic analysis.

This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.

Manuscript-as-software: the manubot pattern, ergonomically, on Quarto. Design phase.

KaryoScope: rapid, alignment-free sequence annotation for the pangenome era

dtour: a tour-de-vis through high-dimensional data

This repository contains the code to run the analysis pipeline for phase 2 of goDMC released June 2024.

The computational and statistical analyses of TenK10K phase 1 multiome data

Python package for HOst-MICrobiome (homic) spatial analysis

Integrate Any Omics: Towards genome-wide data integration for patient stratification

Tidylog provides feedback about dplyr and tidyr operations. It provides wrapper functions for the most common functions, such as filter, mutate, select, and group_by, and provides detailed output f…

An R implementation of the Gene Frequency - Inverse Cell Frequency method for single cell data normalization

Onboarding for those seeking to learn agentic AI tooling.

Bioconductor new package submission using GitHub Actions and R-universe

Biomni: a general-purpose biomedical AI agent

Turn any webpage into clean, LLM-ready Markdown in one click. Strip the browser, keep the structure, then copy or download instantly.

Information for new Troyanskaya lab members

System restore tool for Linux. Creates filesystem snapshots using rsync+hardlinks, or BTRFS snapshots. Supports scheduled snapshots, multiple backup levels, and exclude filters. Snapshots can be re…

Simple c program for manipulating bed-like methylation files

Context engineering for R

Tree-sitter grammar for R

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Shiny app for visualizing TARGET pediatric AML data

Local API emulation for CI and no-network sandboxes

Template repository for Python projects

A bioinformatics tool for viewing and calculating base modification frequencies from BAM files