Radar

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Instant voice cloning by MIT and MyShell.

VoiceForge

DeepSeek-Compatible Middleware Interface: A technical exploration project in Go, focusing on high-concurrency protocol adaptation. It serves as a reference implementation for converting diverse web protocols into standardized formats.

Stable Diffusion Webui Extension for Civitai, to manage your model much more easily.

Marching cubes implementation for PyTorch environment.

Better Head Swap. A simple headswap + faceswap implementation.

A Multi-Agents LLM Financial Trading Framework for both individual stock analysis & portfolio management

AI-powered financial analysis agent for Indian stock markets using AngelOne SmartAPI + Claude

Python Streamlit web app with an SQLite user login/authentication system. Application allows users to select multiple stocks, metrics, and visualizations. A Langchain pandas agent utilizing GPT-4 and customized stock-market/financial prompts is then initiated allowing the user to intelligently interact with their specified data.

Stock Scanner with Local LLM for Sentiment Analysis - McMaster Engineering Capstone 2025. Real-time stock market scanner with AI-driven sentiment analysis using a local LLM. Analyze news, social media for trading insights. Custom technical indicators, privacy-focused, user-friendly. Ideal for investors, traders, developers in AI finance.

🚀 Professional AI-powered stock market dashboard with real-time technical analysis, machine learning price predictions, and intelligent market insights. Built with Python, Streamlit, and scikit-learn.

Open Data Platform for analysts, quants and AI agents.

Software Automatic Mouth - Tiny Speech Synthesizer

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Generative Models by Stability AI

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

High-Fidelity Lip-Syncing with Wav2Lip and Real-ESRGAN