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。

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

[ICLR 2025] The official implementation of our ICLR2025 paper "AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs".

agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

Free ChatGPT API Key，免费ChatGPT API，支持GPT4 API（免费），ChatGPT国内可用免费转发API，直连无需代理。可以搭配ChatBox等软件/插件使用，极大降低接口使用成本。国内即可无限制畅快聊天。

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

Combining GDB and GPT.

Tools for merging pretrained large language models.

Ret2GPT: Advanced AI-powered binary analysis tool leveraging OpenAI's LangChain technology, revolutionizing CTF Pwners' experience in binary file interpretation and vulnerability detection.

OpenAgents: An Open Platform for Language Agents in the Wild

Code and documents of LongLoRA and LongAlpaca

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Efficient Streaming Language Models with Attention Sinks

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain

A GPT-empowered penetration testing tool

Repository for materials of "Modern fuzzing of C/C++ Projects" workshop.

EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit

Prompt-BERT: Prompt makes BERT Better at Sentence Embeddings

An Open-Source Toolkit for Prompt-Learning.

Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming. Outperforming `GPT-3` on SuperGLUE Few-Shot text classification. https://aclanthology.org/2021.acl-long.381/

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Few-shot Learning of GPT-3

PyTorch code for "Prototypical Contrastive Learning of Unsupervised Representations"

Zero-shot Intent Classification and Unknown Intent Detection