patrickmcrawley
Follow
Stars
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
An open-source RAG-based tool for chatting with your documents.
A TTS model capable of generating ultra-realistic dialogue in one pass.
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Wan: Open and Advanced Large-Scale Video Generative Models
GenAI Agent Framework, the Pydantic way
Pocket Flow: Codebase to Tutorial
Proxy server to bypass Cloudflare protection
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
Open Source framework for voice and multimodal conversational AI
ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
Python binding for curl-impersonate fork via cffi. A http client that can impersonate browser tls/ja3/http2 fingerprints.
Copy playlists and liked music from Spotify to YTMusic
Speech To Speech: an effort for an open-sourced and modular GPT4-o
A nearly-live implementation of OpenAI's Whisper.
A simple, secure MCP-to-OpenAPI proxy server
Successor of Undetected-Chromedriver. Providing a blazing fast framework for web automation, webscraping, bots and any other creative ideas which are normally hindered by annoying anti bot systems …