SigNoz is an open-source observability platform native to OpenTelemetry with logs, traces and metrics in a single application. An open-source alternative to DataDog, NewRelic, etc. 🔥 🖥. 👉 Open sour…

Transformers for Natural Language Processing, published by Packt

Unified framework for building enterprise RAG pipelines with small, specialized models

RAG architecture: index and query any data using LLM and natural language, track sources, show citations, asynchronous memory patterns.

AI wearables

An API for e-commerce works, built using NodeJS & MongoDB

FRP Fork

Secure open source cloud runtime for AI apps & AI agents

[NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web"

Code samples for my book "Neural Networks and Deep Learning"

Cleans un necessary tags from html cotent so that LLMs can understand it easily

Python SDK for agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks like CrewAI, Langchain, and Autogen

Confidential AI deployment with secure enclaves 🔒

Official code for the paper "StreamMultiDiffusion: Real-Time Interactive Generation with Region-Based Semantic Control."

Containers for machine learning

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

Large Action Model framework to develop AI Web Agents

The GitButler version control client, backed by Git, powered by Tauri/Rust/Svelte

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app

🚀🎬 ShortGPT - Experimental AI framework for youtube shorts / tiktok channel automation

Drive a browser with GPT-3

Build AI-powered Agents for Twitter🐣

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

Handsfree-stable-diffusion is a CloudFormation template plus script for deploying Stable Diffusion webui (Automatic1111) with some tweaks

Faster Talking Face Animation on Xeon CPU

本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

A nice 3D avatar that can speak input text with facial expressions