Python 排行榜

A deep learning framework for a more agile development process

Summarize any YouTube video in 12 languages using open-source LLMs without API keys.

Object Detection with Transformers : DETR, Conditional DETR, Deformable DETR, Dynamic Head

Detect and resolve missing models in ComfyUI workflows — active-graph analysis, multi-source resolution (Civitai / Hugging Face), and checksum-verified downloads.

FableForgeAI-StoryEngine integrates cutting-edge AI technologies including Gemini-Pro, Hugging Face models, and Gradio interfaces to provide an immersive platform for generating stories, engaging with chatbots, and creating comic videos, showcasing the synergy of AI in creative storytelling and interactive content creation.

A framework to orchestrate multiple AI agents, enabling them to collaborate efficiently through smart threading, dependency management, context sharing, and distributed execution via a built-in swarm system. Built on top of smolagents, it allows the creation of an AI dream team that can scale to tackle complex tasks.

Running small but capable language models entirely offline

Detailed guide on Google's Gemma 3 AI

Text/Image search for similar products

A documentation querying engine, useful for scanning the docs in a question-answer like manner

Enterprise multi-source RAG platform with multimodal embedding, hybrid vector/BM25 retrieval, MCP & RBAC support

In-memory vector database with pluggable indexing algorithms, metadata filtering, and a FastAPI-based REST API.

NeuralCache is a drop-in reranker for Retrieval-Augmented Generation (RAG) that learns which context the model actually uses.

Voice Assistant with GPT abilities

AI News Scraper & Semantic Search: A Python application that scrapes news articles, uses GenAI to generate summaries and identify topics, and provides semantic search capabilities through vector embeddings

QDrant-NLP

Memory architectures that evolve with your agent

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.

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

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