Starred repositories
专业的金融数据获取工具库 - A Professional Financial Data Fetching Toolkit for Python
Agentic AI Infrastructure for magnifying HUMAN capabilities.
Fully automatic censorship removal for language models
Over 450 terminal color schemes/themes for iTerm/iTerm2. Includes ports to Terminal, Konsole, PuTTY, Xresources, XRDB, Remmina, Termite, XFCE, Tilda, FreeBSD VT, Terminator, Kitty, MobaXterm, LXTer…
LLM驱动的 A/H/美股智能分析器：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.
omo; the best agent harness - previously oh-my-opencode
😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond
⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
Entropy is a CLI tool that will scan your codebase for high entropy lines, which are often secrets.
Lightweight LLM firewall: masks PII, routes calls, leaves zero trace.
The web framework for content-driven websites. ⭐️ Star to support our work!
Nova-Proximity is a MCP and Agent Skills security scanner powered with NOVA
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
Implement a reasoning LLM in PyTorch from scratch, step by step
基于Pytorch的Bert应用，包括命名实体识别、情感分析、文本分类以及文本相似度等
A collection of awesome resources related AI security
Oh my tmux! My self-contained, pretty & versatile tmux configuration made with 💛🩷💙🖤❤️🤍
a security scanner for custom LLM applications
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
Security scanner for AI agents, MCP servers and agent skills.
[EMNLP2025 Findings] Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction
Official implementation of “Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models” (AAAI 2026).