Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

real time face swap and one-click video deepfake with only a single image

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Official inference framework for 1-bit LLMs

Universal LLM Deployment Engine with ML Compilation

SGLang is a fast serving framework for large language models and vision language models.

Rembg is a tool to remove images background

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

SoTA open-source TTS

Gel supercharges Postgres with a modern data model, graph queries, Auth & AI solutions, and much more.

Agent Zero AI framework

Build Conversational AI in minutes ⚡️

Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.

Your image is almost there!

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

Multilingual Voice Understanding Model

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

[AAAI 2025] EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching

😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Using GPT to parse PDF

A simple, easy-to-hack GraphRAG implementation

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment