AI 开源项目榜。

Implementation of “DreamDiffusion: Generating High-Quality Images from Brain EEG Signals”

Official implementation of the paper "Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis" in ICLR 2021

Connect your AI agent to the world — Web search, Social media, Crypto & On-chain data. One plugin, zero extra config.

The main component of AI DIAL, which provides unified API to different chat completion and embedding models, assistants, and applications

An implementation of Grad-CAM with keras

Deep Learning with TensorFlow, Keras, and PyTorch

Seoul World Model: Grounding World Simulation Models in a Real-World Metropolis

Inception Score for GANs in Pytorch

machine learning with logical rules in Python

An awesome collection of Jev use cases, workflows, and agent skills.

"ChatBot" AI application, supporting GPT, Gemini Pro, Cohere & Ollama models

A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.

Build agent that uses 80% less token and delivers better results.

The official repo for "Vidi: Large Multimodal Models for Video Understanding and Editing"

Inspect, visualize and intervene on any operation in any neural network. Capture every activation and gradient, the full computational graph and 800+ metadata fields without changing model code. Supports PyTorch, JAX, TensorFlow, MLX, PaddlePaddle and tinygrad. Validated on 6,400+ models. Built for researchers and their AI agents.

This is an official repository of End-to-end Lane Shape Prediction with Transformers.

A simple and flexible code for Reservoir Computing architectures like Echo State Networks

Querying local documents, powered by LLM

Implementation of web friendly ML models using TensorFlow.js. pix2pix, face segmentation, fast style transfer and many more ...

This repository has been merged into Canner/WrenAI under the core/ directory

An agentic workflow tool that provides context engineering support for opencode

Community-driven AI agent skills for Claude Code, OpenCode, and other AI assistants. Curated patterns and community contributions.

Give Claude/Cursor email powers. 27 MCP tools — inbox, send, reply, contacts, search. Free, no signup.

The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.

Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.

Source-available LLM router and AI cost optimizer. Routes simple prompts to cheap or local models and complex ones to premium models, automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor and OpenClaw. Self-hosted, no middleman.

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.