LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

VeighNa框架的期权波动率交易模块

Truly independent web browser

An open-source AI agent that brings the power of Gemini directly into your terminal.

CUDA implementation of "Were RNNs All We Needed?" - minLSTM and minGRU models with fewer parameters and full training parallelization

Contexts Optical Compression

Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).

Implementations of various linear RNN layers using pytorch and triton

FactorHub是一个自研的现代化量化因子分析平台，专为量化投资研究者设计。平台完全自主研发，集成了「数据获取-因子管理-因子分析-策略回测-因子挖掘」的完整工作流程，通过直观的Web界面和强大的计算引擎，大幅降低量化分析的门槛，提高研究效率。 FactorHub = Factor（因子） + Hub（中心），意为因子分析和管理的核心枢纽。

OpenStock is an open-source alternative to expensive market platforms. Track real-time prices, set personalized alerts, and explore detailed company insights — built openly, for everyone, forever f…

The best ChatGPT that $100 can buy.

科技爱好者周刊，每周五发布

verl: Volcano Engine Reinforcement Learning for LLMs

Fast and memory-efficient exact kmeans

Federated query engine for AI - The only MCP Server you'll ever need

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

QuantConnect Wiki Style Documentation Behind QuantConnect

Finnhub Python API Client. Finnhub API provides institutional-grade financial data to investors, fintech startups and investment firms. We support real-time stock price, global fundamentals, global…

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

AgentScope: Agent-Oriented Programming for Building LLM Applications

Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

A high-throughput and memory-efficient inference and serving engine for LLMs

1️⃣🐝🏎️ The One Billion Row Challenge -- A fun exploration of how quickly 1B rows from a text file can be aggregated with Java

E-mails, subdomains and names Harvester - OSINT