Content
# LLM Study — A Collection of Learning Materials for the Large Language Model Era (2023–2026)
[](https://github.com/melocream/awesome-llm-study/commits/master)
[](LICENSE)
> From Transformers to GPT·Claude, agents·MCP·RAG, and more — **helping those who want to study the LLM era on their own**.
> All links in this repository have been verified to be active.
- Managed by: 데이터가답이다 (Dongwon Kim) · [@melocream](https://github.com/melocream)
- Created by the creator of: **[marblo.app](https://marblo.app)** — AI-native team orchestration control plane
- Principles: **prioritize authoritative primary sources**, recent (2024–2026) materials, and provide a one-line comment on "why you should read it".
## English Summary
An opinionated Korean-first, source-verified map for learning LLMs: foundations, building models, agents and MCP, RAG, evaluation, observability, and staying current. Start with the four-stage roadmap below; every resource is labelled with a prerequisite level and a first-pass time (or `참고용` for reference material you dip into as needed). Contributions are welcome in Korean or English.
## Learning Roadmap
Knowing what to do next is more important than having a lot of resources. Complete each stage in order and expand to sections that interest you.
| Stage | Goal | Recommended Resources | Estimated Time |
| ---------------------------- | ------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------- | ------------- |
| 1. Understanding the Basics | Explain token, attention, and next token prediction | [3Blue1Brown](#1-️-llm-history--basics), [Illustrated Transformer](#1-️-llm-history--basics) | 1–2 weeks |
| 2. Building a Model from Scratch | Train and evaluate a small language model | [Karpathy Zero to Hero](#2--courses), [CS336](#2--courses) | 3–6 weeks |
| 3. Connecting to Products | Combine structured output, RAG, and tool calls | [Agents·MCP](#3--agents--tool-calls--mcp), [RAG](#6--rag-search-augmented-generation) | 2–4 weeks |
| 4. Creating an Operational System | Design evaluation, observability, serving, cost, and security together | [Evals·Observability](#9--evaluation--evals--observability), [Local Execution](#10-️-local-execution--serving--quantization), [Security](#11-️-llm-security), [Cost](#12--cost--token-economics) | Ongoing |
`[Beginner]`·`[Intermediate]`·`[Advanced]` indicate **prerequisite knowledge**, and time estimates are for **first pass·1st practice**.
## Table of Contents
- [Learning Roadmap](#learning-roadmap) · [History·Basics](#1-️-llm-history--basics) · [Courses](#2--courses) · [Agents·MCP](#3--agents--tool-calls--mcp)
- [Coding Agents](#4--coding-agents) · [Prompts](#5-️-prompts--context-engineering) · [RAG](#6--rag-search-augmented-generation) · [Alignment](#7--fine-tuning--rlhf--alignment)
- [Key Papers](#8--key-papers-must-read-papers) · [Evaluation·Observability](#9--evaluation--evals--observability) · [Local Execution](#10-️-local-execution--serving--quantization) · [Security](#11-️-llm-security) · [Cost](#12--cost--token-economics) · [Multimodal](#13-️-multimodal) · [Korean Resources](#14--korean-resources) · [Staying Current](#15--staying-current)
## 1. LLM History · Basics
> Understanding Transformers → GPT → instruction tuning and more.
- [Beginner · 3 hours] [3Blue1Brown — Neural Networks series](https://www.3blue1brown.com/topics/neural-networks) · A visualization lecture that helps you understand neural networks and attention without equations.
- [Beginner · 30 minutes] [3Blue1Brown — Transformers, the tech behind LLMs (Ch.5)](https://www.youtube.com/watch?v=wjZofJX0v4M) · A 27-minute animation that explains why LLMs use Transformers.
- [Beginner · 1 hour] [Andrej Karpathy — Intro to Large Language Models](https://www.youtube.com/watch?v=zjkBMFhNj_g) · An introductory lecture that helps non-experts understand the overall picture of LLMs.
- [Intermediate · 3.5 hours] [Andrej Karpathy — Deep Dive into LLMs like ChatGPT](https://www.youtube.com/watch?v=7xTGNNLPyMI) · An in-depth lecture that covers the entire process of pre-training, SFT, and RLHF.
- [Beginner · 40 minutes] [The Illustrated Transformer — Jay Alammar](https://jalammar.github.io/illustrated-transformer/) · A blog post that visualizes the Transformer structure.
- [Beginner · 40 minutes] [The Illustrated GPT-2 — Jay Alammar](https://jalammar.github.io/illustrated-gpt2/) · A blog post that visualizes how decoder-only language models generate tokens.
- [Intermediate · 2 hours] [Andrej Karpathy — Let's build the GPT Tokenizer](https://www.youtube.com/watch?v=zduSFxRajkE) · A lecture that implements tokenization (BPE) from scratch.
- [Beginner · reference] [openai/tiktoken](https://github.com/openai/tiktoken) · A reference implementation of GPT-series BPE tokenizers.
- [Intermediate · 3 hours] [The Annotated Transformer — Harvard NLP](https://nlp.seas.harvard.edu/annotated-transformer/) · A commented implementation of the Transformer in PyTorch.
## 2. Courses
> Learning by implementing from scratch.
- [Intermediate · 40 hours+] [Stanford CS224n — NLP with Deep Learning](https://web.stanford.edu/class/cs224n/) · A graduate-level course on NLP and language models.
- [Intermediate · 30 hours] [↳ CS224n Lecture Videos (Spring 2024, YouTube)](https://www.youtube.com/playlist?list=PLoROMvodv4rOaMFbaqxPDoLWjDaRAdP9D) · Official lecture videos from Stanford Online.
- [Advanced · 60 hours+] [Stanford CS336 — Language Modeling from Scratch](https://stanford-cs336.github.io/spring2025/) · A course on building language models from scratch.
- [Advanced · 25 hours] [↳ CS336 Lecture Videos (Spring 2025, YouTube)](https://www.youtube.com/playlist?list=PLoROMvodv4rOY23Y0BoGoBGgQ1zmU_MT_) · Lecture videos for the course.
- [Intermediate · 20 hours] [Karpathy — Neural Networks: Zero to Hero](https://karpathy.ai/zero-to-hero.html) · A series of lectures on building neural networks from scratch.
- [Intermediate · 5 hours] [karpathy/nanoGPT](https://github.com/karpathy/nanoGPT) · A minimal implementation of GPT in ~300 lines of code.
- [Intermediate · 8 hours] [karpathy/makemore](https://github.com/karpathy/makemore) · A repository for building language models step-by-step.
## 3. Agents · Tool Calls · MCP
> Patterns for making models use tools.
### Structured Output · Tool Calls (first)
- [Beginner · 40 minutes] [OpenAI — Function calling](https://platform.openai.com/docs/guides/function-calling) · A guide on making models call defined functions.
- [Beginner · 40 minutes] [OpenAI — Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs) · A guide on forcing output to a JSON schema.
### MCP · Agent Patterns
- [Beginner · 30 minutes] [Model Context Protocol — Official Introduction](https://modelcontextprotocol.io/docs/getting-started/intro) · An introduction to the MCP open standard.
- [Advanced · 2 hours] [MCP Specification (2025-06-18)](https://modelcontextprotocol.io/specification/2025-06-18) · The protocol specification.
## 4. Coding Agents
> Coding agents that live in terminals.
- [Beginner · 15 minutes] [Claude Code — Overview](https://code.claude.com/docs/en/overview) · An overview of Claude Code.
- [Beginner · 30 minutes] [Claude Code — Quickstart](https://code.claude.com/docs/en/quickstart) · A quickstart guide to Claude Code.
## ... (rest of the document remains the same)
## 5. ✍️ Prompt and Context Engineering
> From learning to ask well (Prompt) to designing what to put in the context window (Context).
- [Beginner · 1 hour] [Anthropic — Prompt Engineering Overview](https://docs.claude.com/en/docs/build-with-claude/prompt-engineering/overview) · Comprehensive guide to prompt techniques (official)
- [Beginner · 6 hours] [Anthropic — Interactive Prompt Engineering Tutorial](https://github.com/anthropics/prompt-eng-interactive-tutorial) · 9-chapter interactive prompt tutorial (beginner to advanced)
- [Beginner · 45 minutes] [OpenAI — Prompt Engineering Guide](https://platform.openai.com/docs/guides/prompt-engineering) · Official guide to writing prompts for GPT series
- [Intermediate · 1.5 hours] [Anthropic — Effective Context Engineering for AI Agents](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents) · Article defining context engineering
- [Intermediate · Reference] [Prompt Engineering Guide (DAIR.AI)](https://www.promptingguide.ai/) · Community standard reference for techniques, papers, and examples
- [Intermediate · Reference] [OpenAI Cookbook](https://cookbook.openai.com/) · Recipes for prompts, tool calls, and embeddings
## 6. 📚 RAG (Retrieval-Augmented Generation)
> Designing pipelines to supplement model knowledge with external search. **The first decision is not about the pipeline, but about which embedding model to use.**
### Embedding and Vector Search Basics (first)
- [Beginner · Reference] [MTEB Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) · Standard leaderboard for comparing embedding models
- [Intermediate · Reference] [Sentence Transformers documentation](https://www.sbert.net/) · De facto standard library for embeddings and semantic search
- [Beginner · 40 minutes] [Hugging Face — Getting Started With Embeddings](https://huggingface.co/blog/getting-started-with-embeddings) · Minimal tutorial on creating semantic search with embeddings
### RAG Pipelines
- [Intermediate · 1 hour] [RAG: Retrieval-Augmented Generation (original paper, arXiv)](https://arxiv.org/abs/2005.11401) · Original 2020 paper introducing RAG
- [Advanced · 4 hours] [Retrieval-Augmented Generation for LLMs: A Survey (arXiv)](https://arxiv.org/abs/2312.10997) · Survey covering the entire landscape of RAG
- [Intermediate · 40 minutes] [Anthropic — Contextual Retrieval](https://www.anthropic.com/engineering/contextual-retrieval) · Practical technique for improving search accuracy
- [Intermediate · 3 hours] [LangChain — Retrieval documentation](https://docs.langchain.com/oss/python/langchain/retrieval) · Official guide to building RAG pipelines with code
- [Intermediate · Reference] [LlamaIndex — official documentation](https://docs.llamaindex.ai/) · RAG framework reference for document indexing and querying
- [Beginner · 1 hour] [Pinecone — Retrieval-Augmented Generation](https://www.pinecone.io/learn/retrieval-augmented-generation/) · Introduction to RAG from a vector DB perspective
- [Beginner · 1.5 hours] [Hugging Face Cookbook — Simple RAG](https://huggingface.co/learn/cookbook/rag_zephyr_langchain) · Minimal RAG example with open models and LangChain
## 7. 🎯 Fine-Tuning, RLHF, and Alignment
> Refining pre-trained models to align with human preferences — SFT, RLHF, DPO, LoRA.
- [Advanced · 2 hours] [InstructGPT: Training LMs to follow instructions (arXiv)](https://arxiv.org/abs/2203.02155) · Original paper on RLHF for ChatGPT
- [Beginner · 40 minutes] [Illustrating RLHF — Hugging Face blog](https://huggingface.co/blog/rlhf) · Introductory article on RLHF
- [Advanced · 2.5 hours] [Constitutional AI: Harmlessness from AI Feedback (arXiv)](https://arxiv.org/abs/2212.08073) · Anthropic's RLAIF paper
- [Advanced · 2 hours] [DPO: Direct Preference Optimization (arXiv)](https://arxiv.org/abs/2305.18290) · Method for optimizing preferences without reward models or RL
- [Intermediate · 1.5 hours] [LoRA: Low-Rank Adaptation (arXiv)](https://arxiv.org/abs/2106.09685) · Standard technique for efficient fine-tuning
- [Advanced · 2 hours] [QLoRA: Efficient Finetuning of Quantized LLMs (arXiv)](https://arxiv.org/abs/2305.14314) · Paper on fine-tuning large models with 4-bit quantization
- [Intermediate · Reference] [Hugging Face PEFT documentation](https://huggingface.co/docs/peft) · Official library for parameter-efficient fine-tuning
- [Intermediate · Reference] [Hugging Face TRL documentation](https://huggingface.co/docs/trl) · Library for RLHF and alignment training
## 8. 📄 Must-Read Papers
> Papers that shaped the LLM era. **All arXiv links are to abs pages to ensure title accuracy**.
### Landmarks (2017–2023)
- [Advanced · 3 hours] [Attention Is All You Need (2017)](https://arxiv.org/abs/1706.03762) · Original transformer paper
- [Advanced · 2 hours] [Scaling Laws for Neural Language Models (2020)](https://arxiv.org/abs/2001.08361) · Scaling laws for model performance
- [Intermediate · 2.5 hours] [GPT-3: Language Models are Few-Shot Learners (2020)](https://arxiv.org/abs/2005.14165) · Paper on few-shot learning with large models
- [Advanced · 1.5 hours] [Chinchilla: Training Compute-Optimal LLMs (2022)](https://arxiv.org/abs/2203.15556) · Compute-optimal training methods
- [Intermediate · 1 hour] [Chain-of-Thought Prompting (2022)](https://arxiv.org/abs/2201.11903) · Prompt technique for improving reasoning
- [Advanced · 2 hours] [InstructGPT / RLHF (2022)](https://arxiv.org/abs/2203.02155) · Original paper on RLHF for ChatGPT
- [Intermediate · 1 hour] [Self-Instruct (2022)](https://arxiv.org/abs/2212.10560) · Method for self-supervised instruction generation
- [Intermediate · 3 hours] [Llama 2 (2023)](https://arxiv.org/abs/2307.09288) · Technical report on Llama 2
- [Intermediate · 1 hour] [ReAct (2023)](https://arxiv.org/abs/2210.03629) · Conceptual foundation for LLM agents
- [Beginner · 1.5 hours] [GPT-4 Technical Report (2023)](https://arxiv.org/abs/2303.08774) · Technical report on GPT-4
### 2024–2026 Frontiers — MoE, Long Context, Reasoning, SSM
> Four areas explaining why current models exist.
**MoE (Mixture of Experts) — Scaling parameters efficiently**
- [Advanced · 2 hours] [Mixtral of Experts (2024)](https://arxiv.org/abs/2401.04088) · Technical report on sparse MoE
- [Advanced · 2.5 hours] [DeepSeek-V3 Technical Report (2024)](https://arxiv.org/abs/2412.19437) · Report on training a large MoE model
**Long Context — How context windows have expanded**
- [Advanced · 2 hours] [LongRoPE (2024)](https://arxiv.org/abs/2402.13753) · Method for extending context windows
- [Advanced · 2 hours] [Gemini 1.5 (2024)](https://arxiv.org/abs/2403.05530) · Technical report on large context models
- [Advanced · 1.5 hours] [RULER: What's the Real Context Size of Your Long-Context LMs? (2024)](https://arxiv.org/abs/2404.06654) · Benchmark for evaluating long context models
**Test-time compute · Reasoning models — Investing in inference**
- [Advanced · 2 hours] [Scaling LLM Test-Time Compute Optimally (2024)](https://arxiv.org/abs/2408.03314) · Analysis of test-time compute optimality
- [Advanced · 2 hours] [DeepSeek-R1 (2025)](https://arxiv.org/abs/2501.12948) · Report on open reasoning models
**SSM — Beyond attention**
- [Advanced · 2 hours] [Mamba: Linear-Time Sequence Modeling with Selective State Spaces (2023)](https://arxiv.org/abs/2312.00752) · Introduction to SSMs
- [Advanced · 2.5 hours] [Transformers are SSMs (Mamba-2, 2024)](https://arxiv.org/abs/2405.21060) · Connection between transformers and SSMs
## 9. ✅ Evaluation, Evals, and Observability
> Reproducibly verifying model, prompt, and agent performance.
### Evaluation and Evals
- [Intermediate · Reference] [EleutherAI LM Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) · Widely used evaluation tool
- [Beginner · Reference] [promptfoo](https://www.promptfoo.dev/docs/intro/) · Practical tool for testing prompts and agents
- [Beginner · 20 minutes] [LMSYS Chatbot Arena](https://lmarena.ai/) · Leaderboard based on human preferences
- [Intermediate · Reference] [SWE-bench](https://www.swebench.com/) · Benchmark for coding agents
### Observability and Tracing (for operating multiple agents)
- [Beginner · Reference] [Langfuse](https://langfuse.com/docs) · Open-source tracing and evaluation tool
- [Beginner · Reference] [LangSmith Observability](https://docs.langchain.com/langsmith/observability) · Observability platform for chains and agents
- [Intermediate · 40 minutes] [OpenTelemetry for Generative AI](https://opentelemetry.io/blog/2024/otel-generative-ai/) · Semantic conventions for observability
## 10. 🖥️ Local Execution, Serving, and Quantization
> Running models on your own machine and server.
- [Beginner · 30 minutes] [Ollama](https://ollama.com/) · Simple way to run local models
- [Intermediate · Reference] [vLLM](https://docs.vllm.ai/) · High-performance LLM serving
- [Intermediate · Reference] [llama.cpp](https://github.com/ggml-org/llama.cpp) · Efficient model execution on CPU and Apple Silicon
- [Intermediate · 45 minutes] [Hugging Face — Bitsandbytes quantization](https://huggingface.co/docs/transformers/quantization/bitsandbytes) · Code examples for quantization
## 11. 🛡️ LLM Security
> Security considerations for using LLMs.
- [Beginner · 40 minutes] [OWASP Top 10 for LLM Applications](https://genai.owasp.org/llm-top-10/) · Overview of common risks and mitigations
- [Intermediate · 1 hour] [Anthropic — Mitigate jailbreaks and prompt injections](https://docs.claude.com/en/docs/test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks) · Defense strategies against attacks
- [Intermediate · Reference] [promptfoo red teaming](https://www.promptfoo.dev/docs/red-team/) · Automated testing for injection and data exfiltration scenarios
## 12. 💸 Cost · Token Economics
> A good product manages not only quality but also token, latency, cache, and model selection costs together. (See [Section 1 — LLM Basics](#1-️-llm-basics) first for better understanding.)
- [Beginner · 30 minutes] [OpenAI — Prompt caching](https://platform.openai.com/docs/guides/prompt-caching) · A starting point for cache design to reduce repeated long context costs
- [Intermediate · 40 minutes] [Anthropic — Token counting](https://docs.claude.com/en/docs/build-with-claude/token-counting) · How to measure tokens before calling to control budget, limits, and UX
- [Intermediate · Reference] [Google Cloud — AI/ML cost optimization](https://docs.cloud.google.com/architecture/framework/perspectives/ai-ml/cost-optimization) · A Well-Architected framework for managing model, infrastructure, and operational costs with KPIs
## 13. 🖼️ Multimodal
> The flow of LLMs handling and generating images, voices, and documents, beyond just text. **An extension of Roadmap Step 3 "Connecting to Products"** — to be considered when creating products that require image input.
- [Beginner · 40 minutes] [OpenAI — Images and vision](https://platform.openai.com/docs/guides/images-vision) · Official guide to safely integrating image input and generation features into product workflows
- [Beginner · 40 minutes] [Anthropic — Vision](https://docs.claude.com/en/docs/build-with-claude/vision) · Official guide to integrating image input with Claude
- [Advanced · 1.5 hours] [CLIP: Learning Transferable Visual Models (2021, arXiv)](https://arxiv.org/abs/2103.00020) · A foundational paper on multimodal, aligning images and text in the same space
- [Advanced · 1.5 hours] [ViT: An Image is Worth 16x16 Words (2020, arXiv)](https://arxiv.org/abs/2010.11929) · Vision Transformer that cuts images into patch tokens and feeds them into transformers
- [Intermediate · 1 hour] [LLaVA: Large Language and Vision Assistant (arXiv)](https://arxiv.org/abs/2304.08485) · A representative paper on multimodal assistants combining vision encoders and language models
- [Intermediate · 1.5 hours] [Qwen2-VL (2024, arXiv)](https://arxiv.org/abs/2409.12191) · Technical report on open vision-language models handling arbitrary resolution inputs (current open SOTA lineage)
- [Intermediate · Reference] [Hugging Face — Multimodal task guides](https://huggingface.co/docs/transformers/tasks/vision) · A practical starting point for experimenting with vision and document tasks using open models
## 14. 🇰🇷 Korean Resources
> Living resources that allow for in-depth exploration in Korean.
- [Beginner · Reference] [TeddyNote (teddylee777) Blog](https://teddylee777.github.io/) · A Korean tech blog rich in LangChain, RAG, and LLM practical examples
- [Beginner · Reference] [TeddyNote — YouTube](https://www.youtube.com/@teddynote) · A channel consistently covering LLM/LangChain in Korean
- [Beginner · 10 hours] [teddylee777/langchain-kr](https://github.com/teddylee777/langchain-kr) · A tutorial repository reconstructing the LangChain official documentation in Korean
- [Intermediate · 15 hours] [ratsgo's NLPBOOK](https://ratsgo.github.io/nlpbook/) · An e-book deeply covering transformers, BERT, and GPT in Korean
- [Intermediate · Reference] [Pseudo-Lab — GitHub](https://github.com/Pseudo-Lab) · A collection of projects and resources from Korea's largest open AI study community
- [Beginner · 20 hours] [Machine Learning/Deep Learning for Everyone — Sung Kim](https://hunkim.github.io/ml/) · A classic Korean introduction to deep learning, for building foundational concepts
- [Intermediate · 12 hours] [rickiepark/nlp-with-transformers](https://github.com/rickiepark/nlp-with-transformers) · Example code for the Korean version of "Natural Language Processing with Transformers"
- [Intermediate · Reference] [Hyukpenhaim — AI & Deep Learning Lectures (YouTube)](https://www.youtube.com/@hyukppen) · A lecture channel explaining deep learning theories, including attention and transformers, in Korean
- [Advanced · Reference] [Seoul National University DSBA Lab (YouTube)](https://www.youtube.com/@dsba2979) · A graduate seminar channel presenting and explaining recent LLM and deep learning papers in Korean
- [Beginner · Reference] [JoCoding (YouTube)](https://www.youtube.com/@jocoding) · A practical channel where non-developers and beginners create AI apps using LLM APIs
### 🧭 Getting Started — Data is the Answer (Repository Maintainer)
> Korean starter materials by **데이터가 답이다 (Dongwon Kim, [@melocream](https://github.com/melocream))**, the repository maintainer. For those new to Claude Code and Marblo.
- [Beginner · Reference] [데이터가 답이다 — YouTube Channel](https://www.youtube.com/@%EB%8C%98%EB%A1%88%ED%85%90%EB%8B%88%EB%8B%A4) · A channel covering Claude Code, hybrid AI agents, and Marblo in Korean
- [Beginner · Reference] [Complete Claude Code Setup Guide (Video)](https://www.youtube.com/watch?v=lqn2kFKUYss) · A practical Korean guide to setting up Claude Code from scratch
- [Beginner · Reference] [gstack — Claude Code Setup Experience (Video)](https://www.youtube.com/watch?v=uL7qVo1W2K0) · A practical Korean video on building a website without a single line of code by adding gstack skill stacks to Claude Code
- [Beginner · Reference] [Marblo — Getting Started with OK (Korean Guide)](https://marblo.app/ko/guide) · The official starter guide for Marblo, explaining how to decompose goals into tickets and spawn, track, and safely merge multiple coding agents in parallel
## 15. 📡 Staying Updated
> Curated repositories become outdated. **This list will also be outdated in 6 months** — so we provide information on what to subscribe to for self-updating.
- [Beginner · Reference] [Latent Space](https://www.latent.space/) · A newsletter and podcast covering LLM practicalities and product workflows from an engineering perspective
- [Beginner · Reference] [The Batch — DeepLearning.AI](https://www.deeplearning.ai/the-batch/) · A weekly AI news and analysis by Andrew Ng's team (balanced overview)
- [Beginner · Reference] [Import AI — Jack Clark](https://importai.substack.com/) · A weekly newsletter covering policy, research, and frontiers, read by the industry
- [Beginner · Reference] [Hugging Face — Daily Papers](https://huggingface.co/papers) · A page curating daily popular papers through community voting (a starting point for paper tracking)
---
## 📁 Future Repository Structure
The README is currently maintained as a verified index. The structure below will be created when notes and practical exercises actually accumulate.
<details>
<summary>View Planned Structure</summary>
```text
01-foundations/ # Conceptual notes and visualizations
02-courses/ # Lecture notes and practical exercises
03-agents-mcp/ # Toolcall and MCP experiments
06-rag/ # Retrieval-augmented generation practical exercises
08-papers/ # Paper summaries
```
</details>
---
> 🔗 Issues/PRs are welcome for incorrect links or additional resources to include.
> Contribution guidelines can be found in [CONTRIBUTING.md](CONTRIBUTING.md), and usage conditions in [CC BY 4.0](LICENSE).
> Maintained by 데이터가답이다 (Dongwon Kim) · [@melocream](https://github.com/melocream) · Built with [marblo.app](https://marblo.app)
Connection Info
You Might Also Like
No recommendations available