Python 排行榜

Implementation of Multistream Transformers in Pytorch

CryptoAgent is a professional, enterprise-grade solution designed to fetch, analyze, and summarize real-time cryptocurrency data.

Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.

Code for the paper "GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos" published at CVPR 2024

Python-based GUI to collect Feedback of Chemist in Molecules

Prompt Hardener analyzes prompt-injection-originated risk in LLM-based agents and applications.

A sophisticated RAG (Retrieval-Augmented Generation) Telegram bot that transforms articles and documents into interactive knowledge bases. Upload PDFs/URLs and get AI-powered answers with source citations.

Build a simple RAG chatbot with LangChain and Streamlit

A targeted resource for mastering LangChain, featuring practice problems, code examples, and interview-focused concepts for building AI applications with Python. Covers chaining LLMs, memory management, and tool integration for technical interview success.

Image postprocessing extension for stable diffusion webui.

Stable Diffusion WebUI & ComfyUI extension to post-process the prompt. Features include: wildcards, sending content from the prompt to the negative prompt, variables, model detection, extranetwork mapping, cleanup.

Translate a video to some AI generated stuff, extension script for AUTOMATIC1111/stable-diffusion-webui.

Merges latent diffusion models at a user-defined ratio

S2D2: Simple Stable Diffusion based on Diffusers (Hires.fix on jupyter notebook, ipython or python interactive shell)

GAKG is a multimodal Geoscience Academic Knowledge Graph (GAKG) framework by fusing papers' illustrations, text, and bibliometric data.

Efficient Multimodal Foundation Model Adaptation for Recommendation

ASRT语音识别系统的Python版SDK

The open-source foundation for production Voice AI. Build, scale, and own your AI calling infrastructure. Bridge legacy SIP to modern LLMs over ultra-low latency WebRTC pipelines. Zero platform fees, BYOK, and full data sovereignty.

Local-first video-to-notes CLI for YouTube/Bilibili transcripts, Whisper fallback, timestamped AI summaries, and Notion/Obsidian export.