cybersecurity

🛡️ VIPER: Stay ahead of threats with AI-driven vulnerability intelligence. Prioritize CVEs effectively using NVD, EPSS, CISA KEV, and Google Gemini insights, all on an interactive dashboard

Rational engineering system prompt for Codex and LLMs — focused on accuracy, software engineering, AI, security research, bug bounty, and reverse engineering. | 面向 Codex 与 LLM 的理性工程系统提示词：强调准确性、软件工程、AI、网络安全、漏洞研究与逆向工程。

Research framework that quantifies how steganographic obfuscation of embeddings defeats off-the-shelf statistical detection in RAG pipelines, paired with the VectorPin cryptographic-provenance defense

A living map of the AI agent security ecosystem.

AI-powered pentesting framework with automated recon and exploitation. Multi-source subdomain discovery, active vuln testing (XSS/SQLi/SSRF/IDOR), AI-driven payload generation, local inference, structured reporting. For pentesters and bug bounty hunters.

LLM-powered security log analyzer: detect threats & anomalies with zero regex — just declare a Pydantic schema. Real-time Telegram alerts, SIEM-ready with Elasticsearch/Kibana. Supports OpenAI, Ollama, vLLM.

Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents

Autonomous AI SOC for Wazuh SIEM — 11 security-expert agents triage, correlate, investigate and plan responses 24/7, every action gated by two-tier human approval. Runs on OpenClaw, Hermes or NVIDIA NemoClaw; any LLM, self-hosted vLLM, or fully air-gapped Ollama. Evidence packs, SOC KPIs, Slack approvals.

jailbreakme.xyz is an open-source decentralized app (dApp) where users are challenged to try and jailbreak pre-existing LLMs in order to find weaknesses and be rewarded. 🏆

Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

The open-source agent firewall. Prevent AI agents from leaking data, using dangerous tools, and importing poisoned dependencies.

Outside-in replication of Anthropic's Mythos Preview / Project Glasswing — open-source agentic vulnerability-discovery scaffold on Claude Opus 4.7. Eight-phase sink-guided pipeline, ~$1/run, OSS self-scan and coordinated disclosure.

High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.

🔥AI-Terminal-X is an AI-powered Linux terminal assistant🔥 that converts natural language commands into executable terminal commands using Google’s Gemini AI. It enhances productivity with safe execution checks, command suggestions, and real-time feedback.

Self-hosted PCAP analysis platform with LLM-powered incident triage, signature-based threat detection, and AI-generated incident narratives. Features network change monitoring across captures, deep packet inspection via nDPI, and automated Wireshark filter generation. Runs fully offline with local LLMs (Ollama, LM Studio).

Project Context Clues aim to vectorize CyberOps recon and threat intel data for AI driven systems.

Deterministic AI defense framework: immutable input filtering, n-model cryptographic hash consensus, and self-learning adaptive rules. Zero dependencies. Hardware-sealed. Patent Pending.

An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end using a single 7B open-source LLM (Qwen2.5-Coder) on vLLM, with AddressSanitizer as a ground-truth oracle.