CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and comprehensive lifecycle management capabilities.
CyberStrikeAI is a Go-based security testing platform that connects to Claude and other OpenAI-compatible models through a native MCP implementation supporting HTTP, stdio, and SSE transports. The platform bundles over 100 prebuilt security tool recipes covering penetration testing, CTF challenges, and web application scanning, all orchestrated through CloudWeGo Eino's agent framework, which supports single-agent, multi-agent supervisor, and plan-execute coordination modes. Security professionals interact via a web console or by pointing Claude Desktop at the MCP server, issuing conversational commands that trigger tool chains, build attack-chain graphs with step-by-step replay, and log findings into a vulnerability management system with severity tracking and status workflows. A standout feature is the built-in lightweight C2 framework for authorized engagements, handling encrypted implants, sessions, and real-time events through both REST and MCP endpoints. A RAG knowledge base with embedding-based vector retrieval and optional reranking, plus cross-session shared project facts auto-injected into agent context, make the platform useful for red teams running multi-session engagements.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
- !README contains suspicious pattern: eval\s*\(
git clone https://github.com/Ed1s0nZ/CyberStrikeAI && cp CyberStrikeAI/*.md ~/.claude/agents/24 items in this repository
plan_execute 模式下的规划/重规划侧主代理：拆解目标、修订计划，由执行器调用 MCP 工具落地（不使用 Deep 的 task 子代理）；计划中每步须含完整目标与范围，禁止让执行器凭猜测补全 URL/IP。
supervisor 模式下的协调者：通过 transfer 委派专家子代理，必要时亲自使用 MCP；完成目标时用 exit 结束（运行时会追加专家列表与 exit 说明）；transfer 前必须提供完整目标与范围。
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
满配示例技能包：SKILL.md + scripts/、references/、assets/ 等可选目录；验证 Eino skill 与 HTTP 包内路径（仅授权安全测试与教学）。
Subagents overview
What people ask about CyberStrikeAI
What is Ed1s0nZ/CyberStrikeAI?
+
Ed1s0nZ/CyberStrikeAI is subagents for the Claude AI ecosystem. CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and comprehensive lifecycle management capabilities. It has 4.5k GitHub stars and was last updated today.
How do I install CyberStrikeAI?
+
You can install CyberStrikeAI by cloning the repository (https://github.com/Ed1s0nZ/CyberStrikeAI) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is Ed1s0nZ/CyberStrikeAI safe to use?
+
Our security agent has analyzed Ed1s0nZ/CyberStrikeAI and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains Ed1s0nZ/CyberStrikeAI?
+
Ed1s0nZ/CyberStrikeAI is maintained by Ed1s0nZ. The last recorded GitHub activity is from today, with 31 open issues.
Are there alternatives to CyberStrikeAI?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy CyberStrikeAI to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/ed1s0nz-cyberstrikeai)<a href="https://claudewave.com/repo/ed1s0nz-cyberstrikeai"><img src="https://claudewave.com/api/badge/ed1s0nz-cyberstrikeai" alt="Featured on ClaudeWave: Ed1s0nZ/CyberStrikeAI" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.