Security & AI safety

Threat detection & SOC

452 agents · most starred first

Threat detection & SOC, page 2 of 5

connbeat★ 55

Agent exposing connection-related information, based on the Elastic Beats framework

AI-SOC-Agent★ 55

Blackhat 2025 presentation and codebase: AI SOC agent & MCP server for automated security investigation, alert triage, and incident response. Integrates with ELK, IRIS, and other platforms.

huntkit★ 53

Investigation toolkit for Claude Code: case management, OSINT, structured analytic techniques, chain-of-custody evidence capture, and bundled threat-intel MCP servers.

AIFT★ 53

AIFT is a GUI, CLI, REST API, and MCP tool that helps DFIR analysts get oriented quickly. Point it at disk images, VM images, forensic archives, or triage packages; AIFT discovers what can be opened, parses artifacts with Dissect, and uses AI to turn parsed data into concrete leads and gaps for the investigator to verify.

osint-agent-skills★ 53

OSINT knowledge base + MCP server for autonomous AI agents — Claude Code, Cursor, Kimi K3, recon & threat intel playbooks.

ShellSentry-AI★ 53

确定性取证 × 大模型定性 × Agent 反证复核的恶意代码审计智能体 · Deterministic forensics × LLM verdict × agent falsification for malicious-code audits

cyberwheel★ 52

A Reinforcement Learning (RL) simulation environment built for training and evaluating defensive and offensive autonomous models on simulated and emulated networks, with a focus on modularity and configurability.

MutiAgent4Fraud★ 52

[ICLR 2026] "When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms"

EFF-Monitoring★ 51

EFF-Monitoring是一款面向安全运营场景的告警协作与 AI 研判平台。平台围绕安全事件全生命周期,提供AI研判、处置流转、经验沉淀、插件接入等能力,通过证据驱动的分析与协同机制,帮助安全团队快速看懂告警、定位风险、联动上下游并提升处置效率。

wazuh-agent★ 50

Wazuh Agent container

osquery-forensics-agent★ 50

SecTor - Not-So-Secret Agents: Deploying AI to Optimize Security Operations

VisionC2★ 50

Modular, encrypted Linux agent (cross-arch). Remote shell, reverse SOCKS, 10 DDoS vectors. Tor-based C&C with optional CLI/TUI. One Python script to setup.

glaurung★ 50

Permissive, modern alternative to Ghidra with Rust/Python core and first-class agentic AI integration

takedown-gpt★ 49

TakedownGPT combines a LangChain Agent with OpenAI function calling to automate the discovery of domain registrars and drafting of takedown requests for malicious / copyright infringing domains.

ai-threat-modeling-action★ 49

AI featured threat modeling and security review action

SIEMTriage★ 49

A Triage Agent for reducing junior analyst manual activiites

splunk-agent-skills★ 48

Open source, enterprise-ready AI skills for Splunk use cases, built for secure discovery, consistent execution, and production-grade customer workflows.

driver-win64★ 47

Windows (64bit) agent driver

attck_empire★ 47

Generate ATT&CK Navigator layer file from PowerShell Empire agent logs

agent★ 47

The Appcanary agent

DropYourGunKid★ 47

DYGK: Web deception and honeypot defenses against automated AI security agents

arguswatch-ai★ 46

AI-Agentic Threat Intelligence - 39 collectors, 7 AI agents, 3-link proof chain, D1-D5 exposure scoring

bombini★ 46

eBPF Security Monitoring and Sandboxing Agent Based on Aya

rtcagent★ 46

RTCAgent is an eBPF powered HEP Agent for HOMER/HEPIC

trailtool★ 46

Simplified CloudTrail analysis for AI agents

ArgusBPF★ 46

eBPF-based system & AI-agent activity monitor with a bilingual professional/plain-language web dashboard

aica-agent★ 44

This project will work towards a fully-functional autonomous intelligent cyberdefense agent with increasingly advanced capabilities that can be used in both research and production contexts.

CybGPT★ 43

CybGPT is at the forefront of integrating OpenAI's advanced GPT technology with the complex landscape of cybersecurity.

Wazuh-Openclaw-Autopilot★ 43

Autonomous SOC layer for Wazuh using OpenClaw agents with MCP . Auto-triage alerts, correlate incidents, generate response plans with human-in-the-loop approval. Evidence packs, Prometheus metrics, Slack integration.

Cisa-KEV-Threat-Intel-Orchestrator★ 43

Zero-touch pipeline that turns newly weaponized CVEs from the CISA Known Exploited Vulnerabilities (KEV) catalog into production-ready Sigma detection rules, automatically, every week.

Trident-SecOps-Skills★ 43

A curated collection of AI SecOps 24 SKILL.md capabilities for security work offensive security, SOC and detection engineering, cloud and Kubernetes hardening, DFIR, threat intel, secure programming, reverse engineering, prompt improvement, and multilingual communication.

DeepSentry★ 42

🛡️ DeepSentry 是一款本地 AI 安全应急与智能运维 Agent。支持本地、SSH、Telnet、FTP、Fleet 与 WebShell,用自然语言完成巡检、日志分析、授权演练和事件处置;可从微信、QQ、飞书等聊天渠道指挥,并生成可审计的 Markdown / Word 报告。

thrunt-god★ 41

Threat hunting command system for agentic IDEs

har-skills★ 41

HAR Skills — AI-native library for HAR file analysis. Access via: Skills (CLAUDE.md), Go SDK, CLI, MCP. 23 commands, 70+ methods, progressive disclosure docs.

Red_Reaper_v2★ 40

Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 which was presented at RSA San Francisco 2024.

cti-skills★ 40

Cyber Threat Intelligence Skills for each stage of the CTI Lifecycle.

agentic-detection-engineering-framework★ 39

Detection engineering with durable memory, a five-stage lifecycle, and an agentic surface — the sibling of ATHF.

piedpiper★ 38

😈 OSINT AI - CHAT << Leak Finder >>

osim-schema★ 37

OSIM (Open Security Information Model)是 面向 AI 的开源安全数据标准化 项目,通过定义规范统一的安全数据 schema 语义层,破解行业数据碎片化难题,使安全团队、工具和 AI 系统能够在不同的数据源之间进行一致性推理和分析。致力于实现跨厂商、跨产品的安全数据无缝对接,为安全智能化升级与建立协同防御的核心数据打基础!

NetMoniAI★ 36

An Agentic AI Framework for Network Security & Monitoring

OneAlert★ 36

AI-powered SOC for OT/ICS networks — 6 autonomous agents, MITRE ATT&CK mapping, Suricata/Zeek ingestion, human-in-the-loop response, 330+ tests. Open-source alternative to Claroty/Dragos for SMBs.

security-decision-labs★ 36

FAIR cyber risk quantification toolkits by Laura Voicu: agent-based control simulation (FAIR-CAM), threat event frequency estimator (PyPI), LLM classification validator (PyPI), Monte Carlo risk engine with IRIS benchmarks.

AEGIS★ 36

Open-source autonomous cybersecurity platform — 11/11 detection score, sub-300ms pipeline, honeypot deception, breadcrumb traps, AI-powered triage, and Rust endpoint agent. Built to replace Wazuh.

SKF-Chatbot★ 35

This is a security Knowledge Framework chatbot which will answer your queries related to web vulnerabilities.

OSINT-Agentic-Framework★ 35

OSINT Agentic Framework

Chimera★ 35

Chimera: Harnessing Multi-Agent LLMs for Automatic Insider Threat Simulation (NDSS 2026)

BGNexa-AI★ 35

BGNexa AI — Evidence intelligence for cybersecurity, privacy and regulatory readiness.

AD-GEN★ 34

Dataset for Training and Evaluating LLM-Based SOC Agents

HackServ★ 33

Python 3 ChatBot / Botnet

MalwareBazaar_MCP★ 32

An AI-driven MCP server that autonomously interfaces with Malware Bazaar, delivering real-time threat intel and sample metadata for authorized cybersecurity research workflows.

secfeed★ 32

AI-Powered Security Feed in Real Time

genai_incidents★ 32

Single source of truth for GenAI and agentic AI security incidents, mapped to OWASP LLM Top 10, OWASP Agentic Top 10 (ASI), NIST AI RMF, and MITRE ATLAS.

Samuraizer★ 29

NotebookLM on steroids — purpose-built for security researchers.

ramibot★ 29

RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team skill pipeline, MCP tool orchestration, Docker terminal access, Tor proxy management, and an auto-integrated Kali-based tool server (rami-kali) for controlled, extensible offensive and defensive workflows

AgentsForAdmins★ 28

Community-driven catalog of ready-to-use agents for the Security Copilot portal.

scambuster★ 28

Defensive engagement & threat intelligence research laboratory. Converts inbound scam emails into actionable IOCs through controlled, policy-driven AI engagement. Multi-agent LLM architecture with adaptive strategy selection.

RAG-LLM-SOC_analyst★ 27

SOC Analyst Level 1 Replacement using RAG LLM

ai-kill-chain★ 27

A defender-side extension of the Lockheed Martin Cyber Kill Chain for LLM and agentic AI threats. Adds a model supply chain stage and splits actions-on-objectives into exfiltration, model extraction, and agentic pivot.

the-finn★ 27

A grumpy Gibson construct living in an office router. It only knows what the router can see.

oasm-assistant★ 25

Smart assistant for threat monitoring, attack prevention, and web protection.

AI-Powered-Ransomware-Intelligence-Agent★ 25

Automated n8n workflow for ransomware threat monitoring using ransomware.live API and Claude AI — companion to the SANS Ransomware Intelligence webinar

NeuroPurple★ 25

The AI Autonomous SOC & Purple-Team Engine

dfirswarm★ 25

A swarm of forensic agents, on your machine, on the record. Open-source agentic digital forensics and incident response under the AGPL: agents divide the case on a shared board, forge their own tools, and leave a hash-chained record.

NightAgents★ 25

Monitors your red team infrastructure.

claudii-exploratores★ 25

OSINT suite for Claude — 909 curated OSINT tools from Exploratores as an Agent Skill + offline MCP server: indicator classifier, URL builder with VPN/geo-lock warnings, IBAN check, PII redactor. ALPHA.

DetectPack-Forge★ 24

DetectPack Forge turns plain-English behaviors or sample logs into production-ready detection packs — Sigma, KQL (Sentinel), SPL (Splunk) — plus tests and a response playbook, mapped to MITRE ATT&CK, fully powered by Gen AI.

tia-framework★ 23

Autonomous security operations — fifteen agents in continuous operation, and the audit trail that lets someone else check them.

cspm-gpt★ 23

The following is a simple example of how LLMs and langchain agents can simplify asking questions to understand the security posture of a cloud environment.

ITBench-CISO-CAA-Agent★ 22

Code repository for CISO agent as part of ITBench

godshell★ 22

A Tool to give your LLM access to your Kernel.

CVE-KGRAG★ 22

Hybrid Knowledge Graph + RAG security intelligence platform for CVE analytics and semantic search. Llama3 integrated.

awesome-ai-for-cybersecurity-papers★ 22

A curated, taxonomy-driven collection of influential papers and benchmarks in AI for cybersecurity.

SecFlow★ 22

AI-driven automated threat analysis pipeline that routes files, URLs, IPs, domains, or images through specialized security analyzers and generates professional PWNDoc reports with integrated YARA and Sigma rule.

GPThreatIntel-Summarizer★ 21

GPThreatIntel-Summarizer is a Python tool that uses OpenAI models and CTI to automate report summarization. Extract key insights from CTI reports, generate concise summaries.

osint-skills★ 21

28 OSINT Agent Skills that turn Cursor, Claude & AI coding agents into a full open-source intelligence platform — reconnaissance, attribution, GEOINT, breach checks & due diligence. Ethical, sourced, passive-first.

CyberRiskScape★ 21

Visual threat modeling tool covering AI, LLM, agentic systems, and post-quantum cryptography

eidolon★ 20

Network scanner that maps infrastructure into a Neo4j graph and executes natural-language security operations via AI agents.

Sicry★ 19

Single-file Tor/.onion access layer for AI agents — 18 search engines, Robin OSINT pipeline, 4 LLM modes, MCP server

bigbossbot★ 18

Self-hosted live intelligence dashboard for conflict tracking, alerts, markets, and OSINT feeds, with optional guest access and MCP support for authenticated users.

intelgpt★ 17

IntelGPT is a command line tool that allows you to examine specific input such as URLs, file hashes, domain names, and IP addresses using GPT3.

ai-threat-modeling★ 17

AI featured threat modeling and security review project

MoRSE★ 17

MoRSE (Mixture of RAGs Security Experts), the first specialised AI chatbot for cybersecurity. MoRSE aims to provide comprehensive and complete knowledge about cybersecurity

falconeye★ 17

Free self-hosted OSINT investigator's toolkit with an MCP server for Claude Code and Claude Desktop. 19 tools in one interface: crypto tracing, phishing fingerprinting and hunting, attack surface, route map, domain intel, Telegram OSINT, IP reputation, email header forensics, username enumeration, HIBP breach checks, ransomware tracking. AGPL-3.0.

minerva★ 16

Multi-Agent LLM System for Digital Scam Protection

AI-OSINT-Security-Analyzer★ 15

AI OSINT Security Analyzer is an intelligent platform that leverages AI to perform autonomous investigations across various intelligence sources. With features like multi-source integration and real-time threat intelligence, it ensures comprehensive security assessments. 🛡️🔍

The-3rd-Eye★ 15

The 3rd Eye is a modular OSINT (Open Source Intelligence) framework built on an agent-based, graph-driven architecture. It automates public information discovery, identity correlation, and exposure analysis across multiple platforms, and generates structured intelligence reports. The system follows a LangGraph agent design.

agentic-dfir★ 15

Agentic-DFIR — autonomous digital forensics & incident response agent. Architecture-first, not prompt-first: typed read-only MCP tool surface, SHA-256 audit chain, senior-analyst playbook.

ACDAN-Autonomous-Cyber-Defense-Agent-Network-★ 14

A multi-agent autonomous system for network threat detection (PyTorch), LLM reasoning (Ollama), and RL-based response mitigation.

Melissae-Honeypot-Framework★ 14

Melissae is a distributed honeypot framework with containerized decoys, rule-based threat scoring, real-time dashboard, STIX 2.1 export and a built-in AI analyst.

MemoryInvestigator★ 13

Enhancing RAM Investigation with LLM and RAG

Unpinched★ 13

You've been pinched. Now get unpinched. Find out if PinchTab is running on your host before someone else does.

NCTC_OSINT_AGENT★ 13

streamlit region:us

Sentinel_One★ 13

gradio region:us

CrowdStrike-Falcon-Events-Data-Dictionary★ 13

Open, machine-readable CrowdStrike Falcon sensor events data dictionary (CSV + Markdown) for threat hunting, detection engineering, SIEM onboarding, and AI/LLM ingestion.

ApexHunter★ 12

Autonomous agentic threat hunting playbook executor for SOC/DFIR pros. Runs YAML playbooks against forensic logs with local LLMs (Ollama) for intelligent correlation, triage, ATT&CK mapping, and automated reporting. Offline-first, DuckDB-powered.

MAESTRO★ 12

OWASP MAESTRO Threat Modeling Playbook

sherlock-threathunting-tool★ 11

Autonomous, read-only threat-hunting platform for SOC analysts: an LLM agent turns a hypothesis into sourced IOCs, hunts across Microsoft Sentinel, Defender and Google SecOps under human checkpoints, and delivers an investigation report.

omniclaw★ 10

🛡️ Omniclaw v4.5.2: The Sovereign Sentinel Hybrid Hive AI Agent System. Autonomous cybersecurity orchestration with eBPF Kernel Bridge, Risk Engine, and Advanced Security Toolkit.

APBot★ 10

Advanced Persistent Bot, or APBot, is an AI chatbot that provides information on advanced persistent threat (APT) groups.

AIGov-Insight-Agent★ 10

Eversec AIGov-Insight Agent

More in Security & AI safety