# Awesome LLM Resources — Updated LLM Index

> Frequently updated index of LLM resources across agents, multimodal, training, inference, eval, and AI coding. Use it for quick references and comparisons.

## Install

Copy the content below into your project:

## Quick Use

```bash
git clone https://github.com/WangRongsheng/awesome-LLM-resources
cd awesome-LLM-resources
rg -n "Agent|RAG|Inference|Evaluation" README.md
```

## Intro

Awesome LLM Resources is a frequently updated index of LLM learning and engineering resources, useful for quickly locating references across the modern LLM stack.

**Best for:** Keeping a curated reading list for LLM engineering and agent systems

**Works with:** Any OS; content is Markdown; use as a curated index then follow source links

**Setup time:** 3–10 minutes

### Key facts (verified)

- Updated recently (GitHub pushed_at in verification snapshot).
- Covers multiple categories across the LLM stack as organized in the README.
- GitHub: 8,273 stars · 852 forks; pushed 2026-05-12 (GitHub API verified).

## Main

A useful way to consume large resource lists:

1) Pick one topic (eval, inference, agents) and choose 3 primary sources to read end-to-end.
2) Turn what you learned into a checklist (metrics, pitfalls, recommended tooling) and keep it versioned.
3) Add internal notes next to links you validated so future readers don’t repeat the same triage.


### README excerpt (verbatim)

![](./assets/logo6.png)

<p align="center">全世界最好的大语言模型资源汇总 持续更新</p>

<p align="center">
  <a href="https://github.com/WangRongsheng/awesome-LLM-resourses"><img src=https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg ></a>
  <a href="https://github.com/WangRongsheng/awesome-LLM-resourses"><img src=https://img.shields.io/github/forks/WangRongsheng/awesome-LLM-resourses.svg?style=social ></a>
  <a href="https://github.com/WangRongsheng/awesome-LLM-resourses"><img src=https://img.shields.io/github/stars/WangRongsheng/awesome-LLM-resourses.svg?style=social ></a>
  <a href="https://github.com/WangRongsheng/awesome-LLM-resourses"><img src=https://img.shields.io/github/watchers/WangRongsheng/awesome-LLM-resourses.svg?style=social ></a>
  <a href="https://gitcode.com/wangrongsheng/awesome-LLM-resources"><img src="https://raw.githubusercontent.com/WangRongsheng/awesome-LLM-resources/main/assets/gitcode.png" height="25" alt="gitcode">
</a>
</p>

> [!TIP]
> 如果您对**医疗数据集/大模型/多模态/评估相关资源感兴趣**！请访问我们的 🤗 [Awesome-AI4Med](https://github.com/FreedomIntelligence/Awesome-AI4Med) !
> 
> 如果您希望赞助此项目，欢迎邮件联系：**wrs6@88.com**
> 
> 赞助项目会被置顶显示在该仓库！

---

#### Contents

- [推荐 Suggestion](#推荐-Suggestion) 🌟
- [数据 Data](#数据-Data)
- [微调 Fine-Tuning](#微调-Fine-Tuning) 🌟
- [Agentic RL](#Agentic-RL) 🌟
- [推理 Inference](#推理-Inference)
- [评估 Evaluation](#评估-Evaluation)
- [体验 Usage](#体验-Usage)
- [知识库 RAG](#知识库-RAG)
- [智能体 Agents](#智能体-Agents)
- [研究 Research](#研究-Research) 🔥
- [代码 Coding](#代码-Coding)
- [视频 Video](#视频-Video) 🌟
- [图片 Image](#图片-Image) 🌟
- [搜索 Search](#搜索-Search)
- [语音 Speech](#语音-Speech) 🌟
- [龙虾 OpenClaw](#龙虾-OpenClaw) 🔥
- [统一模型 Unified Model](#统一模型-Unified-Model) 🌟
- [书籍 Book](#书籍-Book)
- [课程 Course](#课程-Course)
- [教程 Tutorial](#教程-Tutorial)
- [论文 Paper](#论文-Paper)
- [社区 Community](#社区-Community)
- [模型上下文协议 MCP](#模型上下文协议-MCP)
- [技能 Skills](#技能-Skills) 🔥
- [推理 Open o1](#推理-Open-o1)
- [推理 Open o3](#推理-Open-o3)
- [小语言模型 Small Language Model](#小语言模型-Small-Language-Model) 🌟
- [小多模态模型 Small Vision Language Model](#小多模态模型-Small-Vision-Language-Model) 🌟
- [技巧 Tips](#技巧-tips)

![](https://camo.githubusercontent.com/2722992d519a722218f896d5f5231d49f337aaff4514e78bd59ac935334e916a/68747470733a2f2f692e696d6775722e636f6d2f77617856496d762e706e67)

## 推荐 Suggestion

#### Podcast

- [140. 对姚顺宇的4小时访谈：请允许我小疯一下！在Anthropic和Gemini训模型、技术预测、英雄主义已过去](https://www.youtube.com/watch?v=Gk_KUg3qED0)
- [张驰: A Year Inside ByteDance's AI Lab](https://changche.substack.com/p/a-year-inside-bytedances-ai-lab)

### FAQ

**Q: Is it a tutorial repo?**
A: It’s a curated index—follow the links to the original sources for full details.

**Q: How do I keep it actionable?**
A: Translate reading into checklists and repo templates you can reuse.

**Q: How do I avoid stale links?**
A: Prefer recently updated sections and keep your own shortlist in a doc you maintain.

## Source & Thanks

> Source: https://github.com/WangRongsheng/awesome-LLM-resources
> License: Apache-2.0
> GitHub stars: 8,273 · forks: 852

---

<!-- ZH -->

## 快速使用

```bash
git clone https://github.com/WangRongsheng/awesome-LLM-resources
cd awesome-LLM-resources
rg -n "Agent|RAG|Inference|Evaluation" README.md
```

## 简介

Awesome LLM Resources 是一个高频更新的 LLM 学习与工程资料索引，适合快速定位现代 LLM 技术栈的参考内容。

**最适合：** 为 LLM 工程与 Agent 系统维护一份可持续更新的阅读清单

**适配：** 任意系统；内容为 Markdown；适合先做索引再进入源链接阅读

**配置时间：** 3–10 分钟

### 关键事实（已验证）

- 更新较新（见 GitHub pushed_at 验证信息）。
- README 按类别覆盖 LLM 技术栈多个方向，可作为团队资料索引入口。
- GitHub：8,273 stars · 852 forks；最近更新 2026-05-12（GitHub API 验证）。

## 正文

建议用“主题 → 主线资料 → 沉淀”方式消化大目录：

1) 先选一个主题（评测/推理/agents 等），挑 3 个主线来源完整读完。
2) 把结论沉淀为 checklist（指标、坑点、推荐工具），并做版本化维护。
3) 对你验证过的链接加内部备注，减少后续重复分诊成本。


### README 原文节选（verbatim）

![](./assets/logo6.png)

<p align="center">全世界最好的大语言模型资源汇总 持续更新</p>

<p align="center">
  <a href="https://github.com/WangRongsheng/awesome-LLM-resourses"><img src=https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg ></a>
  <a href="https://github.com/WangRongsheng/awesome-LLM-resourses"><img src=https://img.shields.io/github/forks/WangRongsheng/awesome-LLM-resourses.svg?style=social ></a>
  <a href="https://github.com/WangRongsheng/awesome-LLM-resourses"><img src=https://img.shields.io/github/stars/WangRongsheng/awesome-LLM-resourses.svg?style=social ></a>
  <a href="https://github.com/WangRongsheng/awesome-LLM-resourses"><img src=https://img.shields.io/github/watchers/WangRongsheng/awesome-LLM-resourses.svg?style=social ></a>
  <a href="https://gitcode.com/wangrongsheng/awesome-LLM-resources"><img src="https://raw.githubusercontent.com/WangRongsheng/awesome-LLM-resources/main/assets/gitcode.png" height="25" alt="gitcode">
</a>
</p>

> [!TIP]
> 如果您对**医疗数据集/大模型/多模态/评估相关资源感兴趣**！请访问我们的 🤗 [Awesome-AI4Med](https://github.com/FreedomIntelligence/Awesome-AI4Med) !
> 
> 如果您希望赞助此项目，欢迎邮件联系：**wrs6@88.com**
> 
> 赞助项目会被置顶显示在该仓库！

---

#### Contents

- [推荐 Suggestion](#推荐-Suggestion) 🌟
- [数据 Data](#数据-Data)
- [微调 Fine-Tuning](#微调-Fine-Tuning) 🌟
- [Agentic RL](#Agentic-RL) 🌟
- [推理 Inference](#推理-Inference)
- [评估 Evaluation](#评估-Evaluation)
- [体验 Usage](#体验-Usage)
- [知识库 RAG](#知识库-RAG)
- [智能体 Agents](#智能体-Agents)
- [研究 Research](#研究-Research) 🔥
- [代码 Coding](#代码-Coding)
- [视频 Video](#视频-Video) 🌟
- [图片 Image](#图片-Image) 🌟
- [搜索 Search](#搜索-Search)
- [语音 Speech](#语音-Speech) 🌟
- [龙虾 OpenClaw](#龙虾-OpenClaw) 🔥
- [统一模型 Unified Model](#统一模型-Unified-Model) 🌟
- [书籍 Book](#书籍-Book)
- [课程 Course](#课程-Course)
- [教程 Tutorial](#教程-Tutorial)
- [论文 Paper](#论文-Paper)
- [社区 Community](#社区-Community)
- [模型上下文协议 MCP](#模型上下文协议-MCP)
- [技能 Skills](#技能-Skills) 🔥
- [推理 Open o1](#推理-Open-o1)
- [推理 Open o3](#推理-Open-o3)
- [小语言模型 Small Language Model](#小语言模型-Small-Language-Model) 🌟
- [小多模态模型 Small Vision Language Model](#小多模态模型-Small-Vision-Language-Model) 🌟
- [技巧 Tips](#技巧-tips)

![](https://camo.githubusercontent.com/2722992d519a722218f896d5f5231d49f337aaff4514e78bd59ac935334e916a/68747470733a2f2f692e696d6775722e636f6d2f77617856496d762e706e67)

## 推荐 Suggestion

#### Podcast

- [140. 对姚顺宇的4小时访谈：请允许我小疯一下！在Anthropic和Gemini训模型、技术预测、英雄主义已过去](https://www.youtube.com/watch?v=Gk_KUg3qED0)
- [张驰: A Year Inside ByteDance's AI Lab](https://changche.substack.com/p/a-year-inside-bytedances-ai-lab)

### FAQ

**这是教程仓库吗？**
答：它更像索引目录；完整细节需要进入每条目的源链接阅读。

**怎么让它更可执行？**
答：把阅读结果转成 checklist 与可复用模板，而不是只收藏链接。

**怎么避免链接过期？**
答：优先看近期更新内容，并维护一份你自己筛选过的短名单文档。

## 来源与感谢

> Source: https://github.com/WangRongsheng/awesome-LLM-resources
> License: Apache-2.0
> GitHub stars: 8,273 · forks: 852


---
Source: https://tokrepo.com/en/workflows/awesome-llm-resources-updated-llm-index
Author: AI Open Source