Stars
GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive …
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 unbounded context processing. Process 100k+ tokens with any LLM by storing context as variables instead of prompts.
Beads - A memory upgrade for your coding agent
A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.
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)
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.
This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.