This repository contains the code and data for the paper "Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards".

A WhatsApp client library for NodeJS that connects through the WhatsApp Web browser app

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.

a skill directory for world-class specialized agents, in your terminal / IDE. more sophisticated than skills with just md files. and they're free.

The only AI app builder that knows backend

Universal Claude Code workflow plugin with agents, skills, hooks, and commands

How can we build a true AI agent? Like Claude Code.

"DeepTutor: AI-Powered Personalized Learning Assistant"

NanoGPT (124M) in 3 minutes

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Step-DeepResearch

Collection of beautifully crafted open-source layouts UI built with shadcn/ui.

Official code of Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation (NeurIPS 2025)

Point at any URL/YouTube/Podcast or file. Get the gist. CLI and Chrome Extension.

advanced, scalable, no-code RAG

🚀 FullStack FastAPI + Next.js Project Template Generator with PydanticAI/LangChain agents, WebSocket streaming, 20+ enterprise integrations, and Logfire/LangSmith observability. CLI tool to generat…

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…

Claude Code Vitamins - Marketplace for my personal workflows

Specification and documentation for Agent Skills

MedSage is a multimodal healthcare assistant that combines LLMs, vector search, and real-time reasoning to deliver fast, reliable medical insights. It supports symptom analysis, medical document Q&…

The official repository for Trust-Region Adaptive Policy Optimization (TRAPO) – a novel hybrid framework designed to enhance large language models' reasoning abilities by interleaving SFT and RL wi…

100+ RAG interview questions with answers.

OpenTinker is an RL-as-a-Service infrastructure for foundation models

Paper list for Efficient Reasoning.