-
Hanyang University
- Seoul, Korea.
- https://nlp.hanyang.ac.kr
- @galsang1000
Stars
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
List of Science courses with video lectures
Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and pub…
Claude Code 한국어 입문 가이드 | Korean Beginner Guide for Claude Code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.
Build Real-Time Knowledge Graphs for AI Agents
Stanford CS146S: The Modern Software Developer - Korean Edition
The paper list of "Memory in the Age of AI Agents: A Survey"
A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing
LLM Council works together to answer your hardest questions
Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University
Advanced NLP, Fall 2025 https://cmu-l3.github.io/anlp-fall2025/
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravit…
About Awesome things towards foundation agents. Papers / Repos / Blogs / ...
Awesome Reasoning LLM Tutorial/Survey/Guide
Jupyter notebooks and other resources for Think Python by Allen Downey, published by O'Reilly Media.
Official Repository for "Hyper-CL: Conditioning Sentence Representations with Hypernetworks"
The Korean version of the HumanEval benchmark, where the original docstrings are translated into Korean
Official Repository for "Revisiting the Impact of Pursuing Modularity for Code Generation"
Official Repository for "BlendX: Complex Multi-intent Detection with Blended Patterns"
KISS : Korean-english Idioms in Sentences dataSet
Doing simple retrieval from LLM models at various context lengths to measure accuracy
LLM2CLIP significantly improves already state-of-the-art CLIP models.