GitNexus: The Zero-Server Code Intelligence Engine

Fast, accurate & comprehensive text measurement & layout

Unified SDK for headless AI coders (Codex, Claude, Gemini)

Python package for reading, writing, verifying and translating ENDF-6 formatted files

Statistical software for TALYS: Uncertainties, sensitivities and optimization

Coupled-Channels optical model and Hauser-Feshbach theory for nuclear reactions

ENDF-6 data interface and nuclear data evaluation assist code

Recursive Language Models for efficient long-context processing. Analyze 1M+ tokens by storing context in a Python REPL while reducing LLM token usage.

The open source coding agent.

Beads - A memory upgrade for your coding agent

A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.

Building blocks for agents in C++

WKS alpha

Enforce total test coverage through public APIs; includes DesignToTest guidance

Intelligent prompt improver hook for Claude Code. Type vibes, ship precision.

The official repository of "R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Integration"

Toolkit for linearizing PDFs for LLM datasets/training

Simple proxy worker for using ollama in cursor

Convert PDF to markdown + JSON quickly with high accuracy

CodeSage: Code Representation Learning At Scale (ICLR 2024)

MSR Necromancer machine learning project

This repository explores CAG and its integration with Granite language models, demonstrating how Granite’s extended context windows and processing power enhance efficiency by directly utilizing pre…

Fully automated end-to-end framework to extract data from bar plots and other figures in scientific research papers using modules such as OpenCV, AWS-Rekognition.

End-to-end documentation to set up your own local & fully private LLM server on Debian. Equipped with chat, web search, RAG, model management, MCP servers, image generation, and TTS.

Python tool for converting files and office documents to Markdown.

A programming framework for agentic AI

This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.