Starred repositories
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
Drop-in pandas replacement backed by PyTorch custom C++ ops — enables torch.jit.script compilation and pure C++ inference
Three-layer memory architecture for AI coding agents. Persistent facts, cross-session task tracking, and ephemeral execution — so agents stop forgetting.
A rootless, user-space sandbox runtime with Docker-like workflow - no sudo required
Open Data Platform for analysts, quants and AI agents.
股票AI操盘手：从学习、模拟到实盘，一站式平台。包含股票知识、策略实例、大模型、因子挖掘、传统策略、机器学习、深度学习、强化学习、图网络、高频交易、C++部署和聚宽实例代码等，可以方便学习、模拟及实盘交易
The world's fastest open query engine for sub-second analytics both on and off the data lakehouse. With the flexibility to support nearly any scenario, StarRocks provides best-in-class performance …
No fortress, purely open ground. OpenManus is Coming.
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
Apache Doris is a real-time analytics and hybrid search database for AI agents.
AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库
An open-source tool-augmented conversational language model from Fudan University
基于 Go 实现的 OpenAI HTTP 代理（云函数、lambda 函数、自己部署均可）
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Making large AI models cheaper, faster and more accessible
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Compiler for LightGBM gradient-boosted trees, based on LLVM. Speeds up prediction by ≥10x.
Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)
High performance datastore for time series and tick data
A Golang implemented Redis Server and Cluster. Go 语言实现的 Redis 服务器和分布式集群
Unofficial open source mtproto server written in golang with compatible telegram client.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
A Cloud Native Batch System (Project under CNCF)
Jupyter metapackage for installation and documentation
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training