security-agent

Open-Source autonomous security operations and red teaming agent built to help defenders investigate threats, analyze vulnerabilities, assess indicators of compromise, generate hardening guidance, and execute security research through an auditable agent workflow.

osint ai cybersecurity penetration-testing exploitation soc ethical-hacking red-team metasploit security-tools ai-agents readteaming security-agent ethical-hacking-tools redteam-tools ai-red-team security-red-team agentic-ai aisoc soc-agent

Updated Jun 25, 2026
TypeScript

namhop88 / AD-GEN

Star 32

Dataset for Training and Evaluating LLM-Based SOC Agents

security-agent security-dataset cybersecurity-dataset security-ai agentic-ai llm-dataset llm-for-cybersecurity ai-for-soc

Updated Jun 4, 2026
Python

audit

ali-master / audit

Star 24

An 8-stage AI vulnerability-discovery agent.

ai vulnerability vulnerability-detection ai-agents security-agent claude-agent-sdk

Updated Jun 19, 2026
TypeScript

argusappsec / argus

Star 14

An open-source AppSec agent that reasons like an analyst: real scanners, your org's context, and a conversation instead of 400 findings.

golang security mcp code-review application-security appsec devsecops sast ai-security security-agent ai-agent llm

Updated Aug 27, 2026
Go

Threat-Vector-Security / guardian-agent

Star 13

Local workstation and network security with ContextCypher diagrams, threat analysis and GRC. Use standalone or through scoped MCP, CLI and HTTP interfaces. Windows, macOS and Linux; optional AWS and Entra ID integrations.

windows macos linux aws typescript mcp self-hosted cybersecurity grc threat-modeling network-security endpoint-security security-agent local-first microsoft-entra-id contextcypher

Updated Sep 6, 2026
TypeScript

alex-chenc / aegis

Star 10

Open-source AI-native host security platform with vulnerability management, compliance auditing, eBPF runtime detection, attack investigation and automated remediation.

linux-security cloud-security security-agent ai-agent host-security llm

Updated Sep 1, 2026
Go

shamspias / dify-nmap

Star 2

A Dify plugin that integrates Nmap for powerful network scanning, mapping, and security auditing directly within Dify workflows.

agent automation nmap security-tools security-agent dify-plugins

Updated Aug 30, 2025
Python

og-mason / GhostSec

Star 1

SecMonLite (GhostSec)

linux open-source security log-analysis monitoring python3 cybersecurity intrusion-detection threading infosec hacking-tool ethical-hacking red-team system-monitoring malware-detection privacy-tools blue-team real-time-monitoring security-agent open-source-security

Updated Jul 21, 2025
Python

C00LN3T / Log4ShellAuditor

Star 1

An autonomous reflective Go agent for full-cycle security auditing, WAF evasion, OOB LDAP verification, self-remediation (auto-patching), and compliance reporting for CVE-2021-44228 (Log4Shell).

agent golang automation ai spring audit cybersecurity pentesting cyber-security remediation devsecops security-agent autonomous-agent ai-agent cve-2021-44228 log4shell cybersecurity-tools agentic auto-audit oob-verification

Updated Aug 17, 2026
Go

Mpurushotham / claude-security-agent

Star 1

An enterprise Claude security agent for GitHub, packaged as reusable org-level workflows. Drop a few lines into any repo in your org and every pull request and push is automatically reviewed for OWASP Top-10 issues, scanned with GitHub Advanced Security (CodeQL, Dependabot, secret push protection), gated by severity, and — for critical/high finding

security devsecops security-agent claude-ai-security

Updated Jul 27, 2026
Python

bj112233 / governor-edr

Star 1

Local-first threat detection agent for Windows. Runs a 4B-parameter LLM (Qwen3.5-4B) on-device via KoboldCpp. ReAct FSM, MITRE ATT&CK, YARA, OSINT, 15 skills, 4000+ tests.

python mitre-attack threat-detection security-agent local-llm agentic-ai

Updated Aug 17, 2026
Python

elicosilva / RouteWarden

Star 1

Diff-aware security scanner for GitHub PRs — flags mutable Express/NestJS/Next.js routes with no auth middleware and responses leaking sensitive fields. Deterministic, AST-based, human-in-the-loop.