AI Agent Skills

Подробная инструкция (как в pdf, так и в md формате) о настройке своего совбственного Xray-VPS-сервера (с протоколом VLESS XTLS-Reality через панель 3x-ui), а также наст…

Retrieval and Retrieval-augmented LLMs

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.

[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

当用户发现自己在为立场辩护、看不清现实、或反复立志却改变不了自己时调用。 核心理念: 身份是认知牢笼也是行为杠杆——放下身份才能看清真相(痛苦=真相时刻), 更新自我形象才能替代自律(对外承诺)。 不适用于: 需要专业心理咨询的深层创伤。 Triggers: 立场/身份/自我/看不清现实/改变不了自己/自律失败/identity/sel…

Python implementation of behaviour trees.

Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.

RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.

This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented Generation (RAG) pipeline.

Official code for MAMMA: Markerless Accurate Multi-person Motion Acquisition.

[EMNLP'25 findings] This is the official repo for the paper, HiRAG: Retrieval-Augmented Generation with Hierarchical Knowledge.

A Survey on Multimodal Retrieval-Augmented Generation

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for L…

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

A modular graph-based Retrieval-Augmented Generation (RAG) system