Highlights
Stars
Tencent Hunyuan A13B (short as Hunyuan-A13B), an innovative and open-source LLM built on a fine-grained MoE architecture.
Official Python wrapper for OpenFHE. Current release is v1.3.0.0 (released on May 21, 2025).
Agent Framework / shim to use Pydantic with LLMs
Lightweight coding agent that runs in your terminal
A JSON Web Token authentication plugin for the Django REST Framework.
Real-time webcam demo with SmolVLM and llama.cpp server
Simple, unified interface to multiple Generative AI providers
Tensors and Dynamic neural networks in Python with strong GPU acceleration
An implementation of Shazam's song recognition algorithm.
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
Getting crystal-like representations with harmonic loss
Mixture is a powerful node-based tool crafted in unity to generate all kinds of textures in realtime
StyleGAN2-ADA - Official PyTorch implementation
Prowler is the Open Cloud Security platform for AWS, Azure, GCP, Kubernetes, M365 and more. It helps for continuos monitoring, security assessments and audits, incident response, compliance, harden…
A modern runtime for JavaScript and TypeScript.
[ICLR 2025] Autoregressive Video Generation without Vector Quantization
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
A code-first agent framework for seamlessly planning and executing data analytics tasks.
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
A simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model.
real time face swap and one-click video deepfake with only a single image
Instant voice cloning by MIT and MyShell. Audio foundation model.
A developer-friendly API for converting numerous document formats into PDF files, and more!