Stars
AI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-agent research.vibe-trading ,trading-agents,ai-trader,ai-trading
将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
LLM驱动的 A/H/美股智能分析：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US markets.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
AliSQL is a MySQL branch originated from Alibaba Group. Fetch document from Release Notes at bottom.
DeepAudit：人人拥有的 AI 黑客战队，让漏洞挖掘触手可及。国内首个开源的代码漏洞挖掘多智能体系统。小白一键部署运行，自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ，一键生成报告。支持中转站。让安全不再昂贵，让审计不再复杂。
JumpServer is an open-source Privileged Access Management (PAM) platform that provides DevOps and IT teams with on-demand and secure access to SSH, RDP, Kubernetes, Database and RemoteApp endpoints…
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Unified MySQL, Postgres & FlightSQL Server, Powered by DuckDB.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Limitlloss / revolution_history
Forked from PirateBook1/history文革史书单书籍存放库
🧰 记录每一个与运维相关的优秀项目，⚗️ 项目内表格通过 GitHub Action 自动生成，📥 当前收录项目 652 个。
"AI-Trader: 100% Fully-Automated Agent-Native Trading"
Provide secure access and control over all infrastructure
Repair malformed JSON from LLMs, APIs, logs, and user input in Python.
Performance analysis of predictive (alpha) stock factors
open-source agentic AI data assistant for the next generation of AI + Data products.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
中文Mixtral-8x7B（Chinese-Mixtral-8x7B）
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow