AI 开源项目榜。

[ECCV 2026] SLAM-Former: Putting SLAM into One Transformer

StarCraft environment for OpenAI Gym, based on Facebook's TorchCraft. (In progress)

Comprehensive UI/UX and Backend component design skills for AI-assisted development with Claude

This repository lets you train neural networks models for performing end-to-end full-page handwriting recognition using the Apache MXNet deep learning frameworks on the IAM Dataset.

PyTorch implementations of neural network models for keyword spotting

🚀 Universal SDK for building next-gen MCP servers

Bayesian Optimization and Design of Experiments

Automatic Speech Recognition(ASR), Text-To-Speech(TTS) engine. 中英语音识别、多角色语音合成，支持多语言，准确率高

Self-hosted Lovable/v0 alternative. Realtime database & storage included.

tensorflow and theano cnn code for insurance QA(question Answer matching)

A general-purpose, flexible, and easy-to-use simulator alongside an OpenAI Gym trading environment for MetaTrader 5 trading platform (Approved by OpenAI Gym)

Examples for Cerebrium Serverless GPUs

[ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers

⭐️ A cross-platform web-based All-in-One assistant tool for Claude Code, Codex & Gemini CLI, based on CC Switch.

CLI

Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.

Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

Geometric GNN Dojo provides unified implementations and experiments to explore the design space of Geometric Graph Neural Networks (ICML 2023)

Tutorial for building a custom CUDA function for Pytorch

Allows to scale the ChatGPT API to multiple simultaneous sessions with infinite contextual and adaptive memory powered by GPT and Redis datastore.

TensorFlow Implementation of "DRAW: A Recurrent Neural Network For Image Generation"

(已不维护)Rasa中文聊天机器人

OpenClaw-ready macOS VMs

Richer Convolutional Features for Edge Detection model in pytorch CVPR2017

Dynamic Memory Management for Serving LLMs without PagedAttention

Moxin is a family of fully open-source and reproducible LLMs

🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-directed editorial posters with GPT Image. 中国古建筑与在地文化照片 → 艺术指导海报

A centralized manager for Model Context Protocol (MCP) servers with dynamic server management and monitoring