CyberStrikeAI
The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the
What is CyberStrikeAI?
The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.
Overview of CyberStrikeAI
What it is
CyberStrikeAI is a system of action for AI-native cybersecurity. It connects planning, execution, human oversight, evidence, and replay in one auditable workspace. Built in Go, it combines Eino-powered agents, MCP-native tools, RAG knowledge, visual workflows, and attack-chain modeling and analysis for authorized security operations.
Key features
- Agentic execution translates natural-language intent into governed, auditable security actions.
- Eino orchestration supports single-agent execution plus Deep, Plan-Execute, and Supervisor multi-agent modes.
- Graph workflows combine agents, tools, conditions, approvals, and outputs into reusable flows.
- Includes 100+ curated YAML security tool recipes with custom extensions and role-scoped access.
- MCP integration supports HTTP, stdio, SSE, external federation, and dynamic tool discovery.
- Human-in-the-loop approval modes, tool allowlists, audit-agent review, and traceable decisions.
- Built-in WebShell management and C2 capabilities for authorized testing.
Use cases
Authorized security testing, penetration testing, vulnerability assessment, red teaming, capture the flag (CTF) challenges, and security auditing.
Getting started
Prerequisites: Go 1.25+ and Python 3.10+. bash git clone https://github.com/Ed1s0nZ/CyberStrikeAI.git cd CyberStrikeAI chmod +x run.sh && ./run.sh The script automatically checks environments, installs dependencies, builds the project, and starts the server.
License and pricing
Licensed under Apache-2.0. Open source.
Based on the project's public README and repository metadata.