Stars
pgsty / silo
Forked from minio/minioS3-Compatible Object Storage. A MinIO fork maintained by PGSTY
Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code.
SSH workspace, SFTP, and terminals in one
NESTTOR: Detecting Tor-over-Proxy Traffic with Factorized Decisions
玄鉴 Relay：本地优先、隐私友好的 AI 智能体模型流量中转工具，支持脱敏轨迹上报、桌面应用与无头 CLI。
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
Run-scoped LLM observation proxy with an embedded Bifrost data plane
Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.
将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。
Python tool for converting files and office documents to Markdown.
HyperTor: Classification of Imbalanced Darknet Traffic Using Few-Shot Learning with Weights Generated by Transformers.
High performance (real time / offline) darknet flow feature extraction tool built in Rust using eBPF.
LuaN1aoAgent is a fully autonomous AI penetration testing agent driven by graph-based cognitive reasoning, developed by postgraduate researchers from Prof. Lu Hui's Intelligent Offensive and Defens…
Pentest Copilot is an AI-powered browser based ethical hacking assistant tool designed to streamline pentesting workflows.
A curated list of awesome resources about LLM supply chain security (including papers, security reports and CVEs)
The perfect companion for ClaudeCode/OpenClaw/Agent, Give your AI Agent the ability to reach information across the entire web, fetching real-time data from Bilibili, Zhihu, Twitter/X, YouTube, Wei…
轻量级 Nginx 访问日志分析与可视化面板，提供实时统计、PV 过滤、IP 归属地与客户端解析。
The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works w…
A AI general-purpose state-space search engine, validated first on autonomous penetration testing.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1