🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档，以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。

世界上最好的提示词 （总计估值超过300亿的提示词）外国网友x1xh成功获取了 v0、Manus、Cursor、Same.dev 和 Lovable 的完整官方系统提示词和内部工具。

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

A scalable, end-to-end training pipeline for general-purpose agents

Latest Advances on System-2 Reasoning

Nano vLLM

PPO x Family DRL Tutorial Course（决策智能入门级公开课：8节课帮你盘清算法理论，理顺代码逻辑，玩转决策AI应用实践 ）

Democratizing Reinforcement Learning for LLMs

A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architectures

Summarize existing representative LLMs text datasets.

The RedStone repository includes code for preparing extensive datasets used in training large language models.

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Sky-T1: Train your own O1 preview model within $450

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

本项目为量化开源课程，可以帮助人们快速掌握量化金融知识以及使用Python进行量化开发的能力。

A live reading list for LLM data synthesis (Updated to July, 2025).

A reading list on LLM based Synthetic Data Generation 🔥

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

A library for advanced large language model reasoning

Modeling, training, eval, and inference code for OLMo

DSPy: The framework for programming—not prompting—language models

Framework for enhancing LLMs for RAG tasks using fine-tuning.

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Let your Claude able to think