AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

A natural language interface for computers

An AI Hedge Fund Team

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

Hyperparameter Experiments with TensorFlow and Keras

[ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis

[CVPR 2026] Official Implementations for Paper - HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives

An environment to high-frequency trading agents under reinforcement learning

This code implements a Local LLM Selector from the list of Local Installed Ollama LLMs for your specific user Query

11th place solution for APTOS 2019 Blindness Detection on Kaggle (https://www.kaggle.com/c/aptos2019-blindness-detection).

This repository contains the implementation of a trading bot for financial markets

El reconocimiento de color tanto en una transmisión de cámara web en tiempo real, en video y en una sola imagen usando el algoritmo de clasificación de aprendizaje automático de vecinos más cercano…

Create a RAG To Chat with local documents Voice 2 Voice.

El modelo keras se crea al entrenar SmallerVGGNet desde cero en alrededor de 2200 imágenes faciales (~ 1100 para cada clase). La región de la cara se recorta aplicando face detectionusando cvliblas…