AGI_Ananas

graph-memory. Openclaw记忆插件Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse

DataGraphX_Learn. A learning project for building local knowledge bases from PDFs using LangChain, supporting multiple LLMs (DeepSeek, OpenAI). Features include PDF processing, knowledge graph construction, and natural language Q&A interface.一个基于 LangChain 的学习项目，用于构建 PDF 本地知识库，支持多种大语言模型（DeepSeek、OpenAI）。功能包括 PDF 处理、知识图谱构建和自然语言问答界面。

AGI_Ananas. 幸会！视频资料的对应仓库，时序查找

bilibili-mcp. B站 MCP Server - 支持搜索/评论/字幕/弹幕/回复

cloud-code. clau，de code 魔改版

Pretuning. A tool for creating pre-training datasets for language models, supporting one-click batch processing for both text and image datasets. 一个专为语言模型预训练设计的数据集制作工具，支持文本和图像数据集的一键式批量处理。

KG-skills. 视频配套资源

Vision-RAG. Chat with your documents using Vision Language Models. This repo implements an End to End RAG pipeline with both local and proprietary VLMs

ai-video-skill. 将任意文本材料一条龙生成带语音的 MP4 视频。

graphrag_ch. 中文语义分割版