Stars
AI agents running research on single-GPU nanochat training automatically
ACE-Step: A Step Towards Music Generation Foundation Model
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
🤗 smolagents: a barebones library for agents that think in code.
Generate any location from the real world in Minecraft with a high level of detail.
Python tool for converting files and office documents to Markdown.
This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Document to Markdown OCR library with Llama 3.2 vision
LLM-powered multiagent persona simulation for imagination enhancement and business insights.
Entropy Based Sampling and Parallel CoT Decoding
SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.
Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs
A modular graph-based Retrieval-Augmented Generation (RAG) system
Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.
Like "ls", but for images. Shows thumbnails in terminal using sixel graphics.
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
Software that allows Figma to talk to hardware, enabling the creation of rapid prototypes of physical devices.
a state-of-the-art-level open visual language model | 多模态预训练模型
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
A library for making RepE control vectors
Unified framework for building enterprise RAG pipelines with small, specialized models
A Python frontend and library for ComfyUI
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Machine Learning Engineering Open Book