Star 总榜

Part of the LangChain.NET project. Has separate abstractions, does not contain dependencies on the main project and can be used independently

QDrant-NLP

No longer maintained, please see the TypeScript client

A collection of ready-to-use n8n workflow templates for building intelligent automations using Pinecone.

Memory architectures that evolve with your agent

TRIBE v2 — multimodal fMRI brain encoding model inference in Rust

Chinese-Multimodal-Sentiment-Analysis is an innovative project that integrates advanced deep learning techniques to analyze sentiments in Chinese language data. Utilizing a sophisticated blend of textual, audio, and visual modalities, this project offers a comprehensive approach to understanding and interpreting complex emotional expressions.

Run Ornith, Qwen, Nemotron & DeepSeek optimized on AMD Strix Halo — unified OpenAI-compatible server with tuned ROCmFP4 quants, validated 262K context, vision support & hot-swap model zoo (iGPU + NPU)

Pytorch code for "BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Digital Behavioural Change"

[EACL'23] COVID-VTS: Fact Extraction and Verification on Short Video Platforms

Repository to train multimodal latent reasoning tokens for Qwen 2.5 VL.

项目描述：为解决电商客服在物流、售后等高频咨询场景下，人工重复查询、知识定位慢及信息需反复核对等痛点，搭建 Agent 智能客服系统。通过意图分流、业务工具调用与 RAG 知识库检索，完成订单物流查询、售后信息收集和商品问答，提升响应效率与回答准确性。

Benchmarking Cross-Modal Learning from Naturalistic Egocentric Video Data

CLI, MCP server, and TypeScript library that extracts text, layout, and page images from PDFs for AI agents — when extraction goes wrong, it says so per page and says what to do next.

MultiModal Classifier Hierarchy (MMoCHi)

This repository implements a learning-based beamforming approach leveraging multimodal feature fusion. It includes data preprocessing, augmentation, and a transformer-based network for efficient beam prediction.

Build your own local-first digital lifeform: an AI companion with memory, soul, multimodal perception, proactive dialogue, and auditable execution.

A comprehensive framework to explore whether embodied multimodal models are plausibly resilient

EgoNormia | Benchmarking Physical Social Norm Understanding in VLMs

Multimodal recorder for activity recognition