Cybersecurity radar: agents and agent frameworks

Momentum based on available 7-day snapshots for Cybersecurity: measured with two snapshots, estimated otherwise. Each value shows its own source window. This page reads stored snapshots only.

Radar filters

Tool ranking

Mixed ranking: measured growth takes priority; entries without two snapshots are estimated. Raw values keep their source-specific window, shown under each tool; a change requires at least two snapshots from the last 7 days.

  1. 1

    Agent
    Active

    Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.

    PythonLicense: Apache-2.0
    • ai-agent
    • appsec
    • bug-bounty
    • cvss-v3
    • cybersecurity

    githubmeasured growthOpen source ↗

    676GitHub stars+120 (+21.6 %)
  2. 2

    Agent
    Active

    PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous operations.

    TypeScriptLicense: MIT
    • ai-agents
    • ai-security
    • ai-security-tool
    • anthropic
    • autonomous-agents

    githubmeasured growthOpen source ↗

    583GitHub stars+106 (+22.2 %)
  3. 3

    Agent
    Active

    Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

    PythonLicense: Apache-2.0
    • agents
    • ai-hacking
    • ai-penetration-testing
    • ai-pentesting
    • ai-security

    githubmeasured growthOpen source ↗

    59 759GitHub stars+1 509 (+2.6 %)
  4. 4

    Agent
    Active

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    JavaScriptLicense: MIT
    • ai-agents
    • anthropic
    • claude
    • claude-code
    • developer-tools

    githubmeasured growthOpen source ↗

    245 322GitHub stars+2 085 (+0.86 %)
  5. 5

    Agent
    Active

    Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.

    PythonLicense: AGPL-3.0
    • agent
    • ai-security
    • code-audit
    • cve
    • fastapi

    githubmeasured growthOpen source ↗

    1 387GitHub stars+110 (+8.6 %)
  6. 6

    Agent
    Active

    DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from…

    PythonLicense: MIT
    • agent
    • ai
    • ai-agents
    • aisecurity
    • cybersecurity

    githubmeasured growthOpen source ↗

    371GitHub stars+34 (+10.1 %)
  7. 7

    Agent
    Active

    基于 AI Agent + MCP 工具链 + 渗透 Skill 编排， 配合大语言模型， 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。

    PythonLicense: MIT
    • ai
    • ai-agent
    • ai-tools
    • ctf
    • cybersecurity

    githubmeasured growthOpen source ↗

    3 026GitHub stars+50 (+1.7 %)
  8. 8

    Agent
    Active

    Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with ReAct reasoning — supports bug bounty, continuous monitoring, and CTF modes. Built with Go, Claude…

    GoLicense: AGPL-3.0
    • ai-agents
    • bug-bounty
    • cybersecurity
    • offensive-security
    • penetration-testing

    githubmeasured growthOpen source ↗

    2 408GitHub stars+41 (+1.7 %)
  9. 9

    Agent
    Active

    SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

    PythonLicense: MIT
    • agent
    • agent-based-model
    • ai
    • cybersecurity
    • developer-tools

    githubmeasured growthOpen source ↗

    20 180GitHub stars+41 (+0.20 %)
  10. 10

    Agent
    Active

    An AI-powered agentic red team framework that automates offensive security operations, from reconnaissance to exploitation to post-exploitation, with zero human intervention.

    PythonLicense: MIT
    • agentic-ai
    • ai
    • cybersecurity
    • ethical-hacking
    • ethical-hacking-tools

    githubmeasured growthOpen source ↗

    2 371GitHub stars+18 (+0.76 %)
  11. 11

    Agent
    Active

    Supervised, Hermes-native penetration testing profile with 35 routed playbooks, guarded target execution, persistent engagement state, evidence-backed findings, and release-gated reporting.

    PythonLicense: MIT
    • agentic-ai
    • ai-agents
    • cybersecurity
    • hermes-agent
    • hermes-profile

    githubmeasured growthOpen source ↗

    84GitHub stars+4 (+5.0 %)
  12. 12

    Agent
    Active

    Agentic offensive-security in your terminal

    TypeScriptLicense: Apache-2.0
    • ai
    • ai-agents
    • bugbounty
    • penetration-testing
    • security-audit

    githubmeasured growthOpen source ↗

    1 313GitHub stars+7 (+0.54 %)
  13. 13

    Agent
    Active

    Bypass all api restraints within Kimi-CLI

    PythonLicense: MIT
    • ai-agents
    • bypassing
    • exploit
    • kimi-cli
    • kimi-k2

    githubmeasured growthOpen source ↗

    138GitHub starsstable
  14. 14

    Agent
    Active

    The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

    GoLicense: Apache-2.0
    • ai
    • ai-agents
    • ai-cybersecurity
    • ai-hacking
    • ai-penetration-testing

    githubestimated momentumOpen source ↗

    6 067GitHub stars—
  15. 15

    Agent
    Active

    Autonomous Hacking Agent for Red Team

    PythonLicense: Apache-2.0
    • agent
    • ai
    • cybersecurity
    • generative-ai
    • hacking

    githubestimated momentumOpen source ↗

    5 365GitHub stars—
  16. 16

    Agent
    Active

    AI red-team platform. Autonomous LLM agents run a penetration test end to end inside a Kali container and write the report. LangGraph plan/act engine, provider-agnostic models via LiteLLM, PDF/JSON/SARIF output. FastAPI + React.

    PythonLicense: MIT
    • ai-agents
    • autonomous-agents
    • cybersecurity
    • fastapi
    • langgraph

    githubestimated momentumOpen source ↗

    73GitHub stars—

Learning resources

Ranked by measured growth, normalized across sources. These resources remain available separately and do not take part in the main tool ranking.

  1. 1

    awesome-cyber-ai-arsenal

    Agent
    ActiveOpen source ↗

    A curated collection of offensive, defensive and AI/LLM security tools.

    License: MIT
    • ai
    • ai-agents
    • ai-security
    • blue-team
    • bug-bounty
    githubResourcemeasured growth
    166GitHub starsstable

Page 1 of 1 · 17 entries