Security & AI safety

Threat detection & SOC

Threat detection and SOC projects watch systems and network traffic, triage alerts, and investigate suspicious activity. AiSOC shows the pattern: it fuses alerts, runs LLM-agent triage, and maps findings to MITRE ATT&CK while keeping a replayable ledger of each decision. Others focus on narrower jobs, like Tracecat's security automation workflows or blocking malicious bots at the web server.

452 agents · most starred first

Top 100 of 452

AiSOC★ 7,021

Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.

nginx-ultimate-bad-bot-blocker★ 4,847

Nginx Block Bad Bots, Spam Referrer Blocker, Vulnerability Scanners, User-Agents, Malware, Adware, Ransomware, Malicious Sites, with anti-DDOS, Wordpress Theme Detector Blocking and Fail2Ban Jail for Repeat Offenders

tracecat★ 3,908

Open-source agentic security automation platform.

device-detector★ 3,552

The Universal Device Detection library will parse any User Agent and detect the browser, operating system, device used (desktop, tablet, mobile, tv, cars, console, etc.), brand and model.

OpenOSINT★ 1,951

Open-source OSINT agent: 21 public-source tools behind natural-language chat, an MCP server and a Claude Code plugin. Passive by default, no keys to start.

EDRSilencer★ 1,863

A tool uses Windows Filtering Platform (WFP) to block Endpoint Detection and Response (EDR) agents from reporting security events to the server.

agentic-soc-platform★ 1,235

Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operations platform (AI SOC)

Third-Eye★ 781

A production-grade OSINT platform that provides situational awareness across multiple intelligence domains.

galah★ 675

Galah: An LLM-powered web honeypot.

Security-Copilot★ 651

Microsoft Security Copilot is a generative AI-powered security solution that helps increase the efficiency and capabilities of defenders to improve security outcomes at machine speed and scale, while remaining compliant to responsible AI principles

grim-prompter★ 601

Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.

Apollo★ 564

A .NET Framework 4.0 Windows Agent

Richkware★ 548

Richkware is a modern C++20 framework for building educational malware agents. It provides a comprehensive, secure, and modular architecture for understanding malware mechanics and cybersecurity defense strategies.

EDRPrison★ 486

Leverage a legitimate WFP callout driver to prevent EDR agents from sending telemetry

Argus-Agentic-SOC-Platform★ 482

An open source AI-native agentic SOC platform

flocks★ 479

Flocks is an agentic SecOps platform.

vigil★ 451

Open-source agentic AI SOC: specialized LLM agents and WORKFLOW.md playbooks for triage, investigation, threat hunting, and human-approved response, connected to your stack over MCP. Apache 2.0, local-first, runs against your own LLM.

dkim-exchange★ 433

DKIM Signing Agent for Microsoft Exchange Server

agentic-threat-hunting-framework★ 425

ATHF is a framework for agentic threat hunting - building systems that can remember, learn, and act with increasing autonomy.

foniod★ 408

Data first monitoring agent using (e)BPF, built on RedBPF

Orca-AI-Incident-Archive★ 379

An open database of real-world AI agent incidents.

sigwood★ 373

Local-first threat hunting for the logs you already have: Zeek, Pi-hole, syslog or the systemd journal, CloudTrail. Every run names the technique behind each detector. No agent, no daemon, no black box - between grep and a SIEM.

HackBot★ 368

AI-powered cybersecurity chatbot designed to provide helpful and accurate answers to your cybersecurity-related queries and also do code analysis and scan analysis.

admyral★ 338

🤖 Admyral enables continuous control monitoring for any custom control

agentic-malware-analysis★ 336

Agentic malware analysis environment with MCP-connected disassemblers, RE tooling, and structured workflows for Claude Code and Codex CLI.

getIPIntel★ 333

IP Intelligence is a free Proxy VPN TOR and Bad IP detection tool to prevent Fraud, stolen content, and malicious users. Block proxies, VPN connections, web host IPs, TOR IPs, and compromised systems with a simple API. GeoIP lookup available.

lyrie-ai★ 328

Lyrie.ai — The world's first autonomous AI cybersecurity agent. Built by OTT Cybersecurity LLC.

artifactcollector★ 307

🧭 The artifactcollector is a customizable agent to collect forensic artifacts on any Windows, macOS or Linux system

TiEtwAgent★ 298

PoC memory injection detection agent based on ETW, for offensive and defensive research purposes

osint-d2★ 298

Agentic OSINT toolkit. Autonomous identity triangulation, 6-dimension cognitive profiling, breach analysis. CLI-first. 30+ platforms. 5 languages.

threat-designer★ 296

Threat Designer is a GenerativeAI application designed to automate and streamline the threat modeling process for secure system design.

deepsoc★ 290

通过多智能体(Multi-Agent)打造的革命性的安全运营解决方案

artex-ko-plus★ 280

ARTEX 한국어판 ·AI 기반 침해사고 대응 기능 추가 (upstream: Autumn-27/ARTEX, AGPL-3.0)

SecurityClaw★ 279

A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors OpenSearch/Elasticsearch data, builds RAG-based behavioral memory, and validates real-time anomalies using LLMs.

kavach★ 261

Tactical AI Workspace Monitor & EDR

AgentSmith-HUB★ 258

Enterprise Security Data Pipeline Platform (SDPP) — Real-Time Threat Detection + Deeply Integrated LLM Agents

julius★ 256

Simple LLM service identification - translate IP:Port to Ollama, vLLM, LiteLLM, or 60+ other AI services in seconds

IDA-Skill★ 239

使用skill让 AI Agent 像安全分析师一样分析恶意样本 | AI Agent skill for automated malware analysis using IDA Pro

cynative★ 233

Open-source AI agent framework for security engineering across AWS, GCP, Azure, Kubernetes, GitHub & GitLab: AI-powered security review, findings triage, detection and response.

allama★ 205

🔥🔥🔥 AI security automation platform. Build visual workflows, deploy autonomous agents, and automate threat detection and response. 80+ integrations with SIEM, EDR, ticketing, and cloud tools. Self-hosted SOAR alternative.

microsoft-security-skills★ 182

Curated Microsoft Security skills for AI agents - Defender, Sentinel, Entra, Purview, Intune, Security Copilot

ai_osint★ 180

🤖 Curated AI OSINT resources — Google dorks, Shodan queries, GitHub dorks, and techniques to discover exposed LLM endpoints, leaked AI API keys, misconfigured vector databases, and unprotected AI agents

AI_SOC★ 176

Open-source AI-augmented Security Operations Center using LLMs + Multi-Agent Orchestration | Foundation-Sec-8B | Wazuh | TheHive | RAG

Intrusion-and-anomaly-detection-with-machine-learning★ 175

Unsupervised, AI-augmented detection of attacks in application logs.

Awesome-LLMSecOps★ 172

LLM | Agentic | Security | Operations in one github repo with good links and pictures.

Aether★ 172

Autonomous AI Driven OSINT & security-research desktop agent (macOS/Windows) that builds a live knowledge graph. Authorized use only

osint-skill★ 169

OSINT Skill for AI agents (Claude Code, OpenClaw, Codex, OpenCode) — from a name to a scored dossier with psychoprofile, career map, and confidence grades. 55+ Apify actors, 7 search APIs, swarm mode. Early Beta.

AISecOps★ 168

📚【更新中】AISecOps: AI-Driven Enterprise Security|AI 驱动的安全体系。一套将 AI 能力嵌入企业安全体系的方法论框架,以及支撑它落地的完整工程实践——从安全架构、GRC、云原生、数据隐私到 SOC 运营、身份治理与 AI 系统安全。开源中文技术专著,CC BY-NC-SA 4.0。/*⚡🌊🛡️*/

SecRL★ 165

Benchmarking LLM agents on Cyber Threat Investigation.

AskJOE★ 164

AI-Powered Malware Analysis & Threat Intelligence for Ghidra Transform your static analysis workflow with cutting-edge AI capabilities, comprehensive malware detection, and advanced threat intelligence.

Awesome-AI-For-Security★ 156

A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focuses on modern AI technologies like Large Language Models (LLMs), Agents, and Multi-Modal systems and their applications in security operations.

binary-cartography★ 152

Technical webinars on reverse engineering, malware analysis, and software protection.

ai-runbooks★ 133
argus★ 121

Open-source agentic security operations platform:

Atlas-Community★ 120

Autonomous DFIR agent: point it at disk images, memory dumps or log exports and get back an investigation that shows its work. Volatility 3, Plaso, YARA and any OpenAI-compatible LLM.

pcap-hunter★ 117

PCAP Hunter is an AI threat hunting workbench. It uses Zeek and Tshark to analyze PCAPs, enriched by OSINT. Features include a world map, JA3 forensics, and C2 detection. It generates multi-language security reports via local or cloud LLMs, prioritizing privacy and speed.

kipi★ 114

Open-source, self-hosted OSINT investigation platform: turn documents into a live, investigated entity graph. Autonomous agent, graph analytics (centrality, communities, pathfinding), keyless-first tool belt.

TI-Mindmap-GPT★ 112

AI-powered tool designed to help producing Threat Intelligence Mindmap.

Crow-Eye★ 112

Windows forensics Engine

owasp-social-osint-agent★ 107

AI-powered OSINT framework for multi-platform social media intelligence gathering using OpenAI-compatible APIs. Features vision analysis, network mapping, and dual web/CLI interfaces.

Cyber-Claude★ 104

An AI-powered cybersecurity agent inspired by Claude Agent SDK, designed exclusively for defensive security operations.

ICMP-Ghost-A-Fileless-x64-Assembly-C2-Agent★ 102

A fileless C2 framework written in pure x64 Linux Assembly with zero libc dependencies. Features dynamic protocol pivoting between raw ICMP sockets and DNS (UDP/53) via in-memory VTable manipulation. 100% direct syscalls, no disk writes, and strict mathematical packet authentication.

Wazuh-MCP-Server★ 100

Wazuh MCP Server: AI-Driven SOC Automation

XposedOrNot-API★ 100

Open-source API to check if an email has been exposed in a data breach and monitor breaches across your verified domains. Real-time alerts and breach analytics protect your online identity.

azazel★ 99

eBPF-powered silent observer for containerized runtimes, built for malware analysis sandboxes and Agentic AI monitoring.

netra★ 99

One binary. Lightweight, high-performance. Observe your network with eBPF. Ask AI. Extend with MCP

OnionClaw★ 98

OnionClaw™ — OpenClaw skill for full Tor dark web access: search .onion sites, fetch hidden services, rotate identity, run OSINT pipeline, craw.

mulder★ 98

Agentic DFIR

Navi★ 97

An Interface for AI built for cybersecurity professionals

TSUKUYOMI★ 95

##Note: this is really old now, and the janky pseudo methods are probably only working out of sheer coincidence. This was an early experiment in how jargon & combinations of artificial weights in pseudocode can influence LLM behaviour without retraining. This was probably ahead of its time

SigmAIQ★ 95

A pySigma wrapper and langchain toolkit for automatic rule creation/translation

MemShellKiller★ 95

基于Agent技术实现的Java内存马查杀、防护工具。

cve-intel★ 95

Local security intelligence for CVE triage - 39 data sources and 36 tools, risk scores and an MCP server for AI agents, all in native Rust. Private by default.

supercharge★ 94

Fully Undetectable Native C++ Remote Access Agent / Botnet.

soctalk★ 93

AI-powered multi-tenant SOC automation agent using LangGraph with Wazuh, Cortex, TheHive & MISP integration

zeek-agent-v2★ 92

Open source endpoint agent providing host information to Zeek. [v2]

adk_runbooks★ 92
cage-challenge-4★ 88

The TTCP CAGE Challenges are a series of public challenges instigated to foster the development of autonomous cyber defensive agents. This CAGE Challenge 4 (CC4) returns to a defence industry enterprise environment, and introduces a Multi-Agent Reinforcement Learning (MARL) scenario.

P4wnP1_WiFi_covert_channel_client★ 87

P4wnP1 - WiFi covert channel - Client agent (experimental Proof of Concept) by MaMe82

Hannibal★ 86

Mythic C2 Agent written in x64 PIC C

pouchnexus★ 81

A multi-agent SOC/DFIR assistant powered by LangChain, LangGraph, and OpenAI models. Automates IOC extraction, MITRE ATT&CK mapping, CVE correlation, investigation planning, and report generation for cybersecurity incident analysis.

AgentSonar★ 81

Detect shadow AI agents by monitoring network traffic and classifying process-to-domain pairs.

sample-agentic-attack-tree-generator★ 81

AI-Driven Threat Modeling & Attack Tree Generation with MITRE ATT&CK Integration

intellyweave★ 79

AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy.

cloud-risk-assessment-agent★ 77

Welcome to the Cybertron AI Agent project, an open-source initiative leveraging the Trend Micro Cybertron AI model in the NIM catalog.

AETHER★ 76

An AI-powered reverse-engineering copilot for assisting tedious malware analysis in IDA Pro.

kodeblue★ 71

SOC, incident response and SecOps for Linux servers in one agent: learns each host, watches it with zero-token sensors, triages with a small model, and contains attacks under a root-owned policy. Optional hub for fleets.

socbench★ 70

An Open Harness and Benchmark for AI in Cybersecurity Operations.

trudi★ 70

Autonomous DFIR agent — SANS SIFT Workstation MCP server for incident response

YAWNING-TITAN★ 69

YAWNING TITAN is an abstract, graph based cyber-security simulation environment that supports the training of intelligent agents for autonomous cyber operations.

LogSentinelAI★ 68

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.

zettelforge★ 67

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

Wazuh-Autopilot★ 67

Agentic SOC for Wazuh built on Strands Agents: a 13-agent swarm with 37 Wazuh-verified skills triages, investigates and plans response through the Wazuh MCP Server. Policy-gated autonomy, approvals, RBAC, audit, tracing and evals in one Docker stack. Bedrock, Anthropic, NVIDIA NIM, vLLM, LiteLLM or air-gapped Ollama.

PEAK-Assistant★ 66

An AI-backed threat hunting assistant that aligns to the PEAK framework.

Skills★ 65

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.

osint-mcp-server★ 63

OSINT intelligence MCP server for AI agents — 37 tools, 12 sources. Shodan, VirusTotal, Censys, SecurityTrails, DNS reconnaissance, WHOIS, certificate transparency, BGP routing, Wayback Machine, GeoIP. Automated open source intelligence and attack surface mapping via Model Context Protocol.

darkweb-forums-tracker★ 62

This is a darkweb forums tracker that monitors forum posts and sends alerts to Discord

SYNINT★ 60

SYNINT: Agentic OSINT & Intelligence Framework – Modular, Stealthy, API-Free, Multi-Agent System for Automated Intelligence Collection & Analysis.

honeyagents★ 59

HoneyAgents is a PoC demo of an AI-driven system that combines honeypots with autonomous AI agents to detect and mitigate cyber threats. Features include intelligent threat analysis, automated deny list updates, and detailed natural language threat reports.

CyberGuard★ 56

Evidence-driven autonomous SOC team on AgentTeams: hash-bound approvals, HMAC audit chain, rollback and reproducible attack scenarios — auditable governance primitives for agent infrastructure.

More in Security & AI safety