Threat detection & SOC
452 agents · most starred first
Threat detection & SOC, page 4 of 5
Autonomous Red vs. Blue AI Fraud Simulation & Defense System for UPI & Digital Payments. Features LLM-driven zero-day attack generation (F3 Taxonomy), PyTorch Bidirectional LSTM + LightGBM + GraphSAGE multi-model defense, and real-time SIEM dashboard.
Autonomous Network Attack Forecasting & Multi-Agent SOC Co-Pilot powered by Temporal World Models, MITRE ATT&CK, CAPEC, CVE/NVD, and Dual Statutory Reporting (CERT-In + NCIIPC). Built for SIH 2026 (PS: 26153).
Agentic SOC alert-triage service: ingests from Splunk, CrowdStrike, AWS GuardDuty and Sentinel, normalizes to OCSF, and runs a LangGraph multi-agent DAG with MITRE ATT&CK-routed enrichment to emit a structured TriageVerdict. Python, FastAPI, Redis, Langfuse, pluggable LLM backend.
Agentic AI security operations copilot: RAG over MITRE ATT&CK, CNN and Isolation Forest models, human-approved responses, a live 3D threat lab, FastAPI and Docker.
NexaGuard — Autonomous infrastructure defense mesh with live Groq LLM multi-agent reasoning, real-time CNN vision (MobileNet), RAG-grounded triage, and a 3D digital twin. Built by NIKHIL CHARY SRIRAMOJU.....
Quantum-safe autonomous cognitive security fabric: Raft consensus, hybrid post-quantum crypto (ML-KEM/ML-DSA), agentic zero trust, GraphRAG and a CNN+Transformer traffic analyzer, with a live 3D simulator.
AI cyber defense platform with Agentic AI, RAG, CNN, LLM and Docker, plus a responsive 3D dashboard. Designed and developed by NIKHIL CHARY SRIRAMOJU....
One AI Security Platform: Protect, Operate, Respond
Classify web traffic from server log entries and header capture into human, AI agent, AI crawler, AI assistant, programmatic, and other bot categories. No analytics service or middleware required.
PHAGE — developed as part of Cybersecurity and AI coursework at Esprit School of Engineering. Real-time threat detection using machine learning and a multi-agent AI system.
Agentic AI threat modeling using the lets-threat-model-core Docker container. This action produces Markdown, optional JSON, and SARIF reports—seamlessly integrating security assessments into your CI/CD pipeline and supporting GitHub Code Scanning.
A bio-inspired multi-agent defense framework with self-diagnosis, self-healing, and self-evolution capabilities, built with LangGraph
AI-powered ransomware threat intelligence platform. Monitor 300+ leak sites, track 24,000+ victims, and analyze threat actors with real-time dark web scraping and ML-based enrichment.
Agentic Physical Security Platform- Edge AI
streamlit region:us
Benchmark code and interactive results for autonomous network-attack detection by tool-using LLM agents investigating raw PCAPs.
Contract-first anomaly detection across ~30 formats — logs, security telemetry (syslog, CEF/LEEF, EVTX, Suricata EVE, osquery, CloudTrail), network (pcap, NetFlow, DNS), observability (OTLP, Prometheus, journald), data (CSV/JSON/Parquet/SQLite/Avro/ORC). Deterministic Rust CLI; 9 detectors / 7 classes; NIST-validated, mutation-tested.
🛡️🤖 A curated atlas of AI agents that secure the software lifecycle — from threat modeling to SOC response
An autonomous Windows hardening agent with a local language model. It decides with an embedded model, fixes only what it can undo, verifies every change, and rolls back anything that made the machine worse.
Autonomous LLM agent that investigates Microsoft Defender XDR and Sentinel alerts, with a Training Lab benchmark of 14 known-answer scenarios to score your own agent
Unofficial Darktrace MCP server for SOC investigations and incident response in Claude, Cursor, Codex and VS Code.
🏆 1st Place – OpenAI Track (National Security) | SCSP x AGI House Hackathon 2025
DER-SecAgent: A Multi-Agent based Cybersecurity Framework for Distributed Energy Resources
AI multi-agent system for network automation and security.
Autonomous DFIR agent driving SANS SIFT forensic tools via an MCP server + LangGraph, with guardrails and a hash-chained audit trail.
gradio region:us
gradio region:us
gradio region:us
docker region:us
Easy-to-use, customizable, high-quality threat modeling skills for AI agents.
A threat hunter that lives in your terminal with memories in Notion.
AI-SOC — detects, explains and contains cyberattacks on critical infrastructure. Isolation Forest detection + RAG/MITRE attribution + policy-gated response, wired end-to-end. ET AI Hackathon 2026, PS7.
🛡️ Modular Python framework for Cybersecurity LLM agents, purple team automation, log triage, and detection engineering in lab environments.
Demon Cry core - AI-powered OSINT engine
Behavioral biometric detection of AI web agents — distinguishing humans from scripted bots, LLM-driven agents, and custom autonomous agents using mouse, keystroke, and interaction-timing signals. Live testbed at charweb.net.
LLM-powered multi-stage CTI-to-ATT&CK pipeline for extracting adversary behaviors from cyber threat intelligence reports and mapping them to MITRE ATT&CK techniques using reasoning-driven prompts.
A production-grade OpenEnv-compliant reinforcement learning environment simulating a Security Operations Center (SOC) analyst workflow.
Open-source AI EDR that detects and stops ransomware, Cobalt Strike, and living-off-the-land attacks in real time — with a beautiful web dashboard and ChatGPT-style AI analyst you can talk to.
CoAnalyst: a LangGraph research analyst for OT/IT alert triage with human review.
gradio mcp-server region:us
docker region:us
docker region:us
docker region:us
streamlit region:us
docker streamlit region:us
gradio region:us
StopScam review: compare features, pricing, use cases, access model, and alternatives for this AI Security agent in 2026. Scam Detector Pro
Talk to your security data in plain English to find threats faster.
Automate security tasks and answer customer questions faster with AI.
The world's first autonomous AI agent with built-in cybersecurity
YARA-powered Droid: The next generation of autonomous agent interfaces.
YARA CLI and integration tools for autonomous agent orchestration.
Autonomous cybersecurity execution agent for the terminal.
SPECTRA -- Security Protocol Engineering for Cyber Threat Response & Assessment. Multi-agent cybersecurity framework.
Honeytoken transmission, reception and analysis.
Enterprise Security Monitoring SDK for AI Agents - Secure any AI agent in just 3 lines of code with real-time threat detection, behavioral analysis, and separate logging and threat reporting for comprehensive security monitoring
Agentic Threat Hunting Framework - Memory and AI for threat hunters
Runtime behavioral anomaly detection for AI agents
Swarm Ops - Pytorch
AI Agent Network Scanner - Detect AI agents on your network
Linux iptables Policy Enforcer & Auditor
Pydantic v2 models for AWS securityagent, shipped as a PEP 420 namespace extension of aws-resource-validator.
ChitraGupt: A powerful OSINT framework with a plugin-based architecture.
CloudSecGPT super-charges raw cloud-security findings with AI. Analyzes OCSF/Parquet exports and live data from AWS Security Hub, GCP Security Command Center, and Azure Defender to provide risk scores, summaries, remediation steps, alert clustering, and interactive chat capabilities.
Compares pair of user-agent strings to detect stolen authentication cookie.
Retired CrowdStrike package
The Red Canary EDR validation tool.
Evolve Agent to connect your systems to the Evolve Security Automation and Orchestration Platform.
Enterprise cybersecurity threat intelligence agent with system tray integration
Python fileagent to accompany Snort in a container
Sentry event scrubber and utilities library
A network traffic classification toolkit
Flowtriq DDoS Detection Agent — real-time L3/L4/L7 traffic monitoring, incident detection, PCAP capture, and auto-mitigation
Lightweight open-source DDoS traffic monitor — stdout output, no account required
Framework-agnostic telemetry and monitoring agent for the Guard security ecosystem (fastapi-guard, flaskapi-guard, djangoapi-guard, tornadoapi-guard)
Component for creating VPN client environments
LangChain integrations for CrowdStrike AIDR
OSINT intelligence platform integration for LlamaIndex — 15-category intelligence reports, domain recon, and social media lookup
CLI-based threat hunting platform using LLM and RAG for semantic search of security logs
Attack recovery support system using an LLM
Python SDK for LoginLlama suspicious login detection
LogSentry agent SDK and collectors.
Lightweight cloud agent for Windows Event Log anomaly detection
Automatically Detect and Repair Common Firewall Issues
Autonomous Server Cybersecurity Expert Bot - monitors hosts and containers, detects risks, recommends and executes safe remediation
OWASP Security Bot - LLM
A Python OSINT tool using Large Language Models
CLI for using the PolySwarm Customer APIs
Client library to simplify interacting with the PolySwarm consumer API
Library containing artifact type enums and functions
Client library to simplify interacting with a polyswarmd instance
Polyswarm engine libarary
Config module the PolySwarm Daemon
A pipeline to detect fraudulent articles
pySigma uAQL backend
Rekall Incident Response Agent
Rivex security posture collection agent (cross-platform)
An EOS agent to collect and process RPKI VRP data