Verified project record
Ed1s0nZ/CyberStrikeAI
cyberstrikeai is an AI-native cybersecurity system of action that combines Eino-powered agents, MCP-native tools, RAG knowledge, visual workflows, and attack-chain modeling for authorized security operations. It provides a unified, governed, and auditable workspace connecting planning, execution, oversight, evidence, and replay for security testing.
Project overview
The project addresses the lack of a governed and auditable workspace for AI-driven security testing by turning natural-language intent into traceable security actions with human-in-the-loop oversight, multi-agent orchestration via Eino, and built-in role-scoped RBAC across the kill chain.
- Project type
- MCP · AI Agent · RAG
- Use cases
- Knowledge Q&A · Automation
- Deployment
- Refer to project documentation
- License
- Apache-2.0
Best for
- Operations teams conducting educational and authorized security testing who need governed, auditable agent orchestration across the kill chain.
- Teams that require human-in-the-loop approval modes and traceable decision records for every security action.
Key capabilities
- Translates natural-language intent into governed, auditable security actions, supporting single-agent execution plus Deep, Plan-Execute, and Supervisor multi-agent modes via Eino orchestration.
- Combines agents, tools, conditions, approvals, and outputs into reusable flows.
- Includes 100+ curated YAML recipes for the whole kill chain, with custom extensions and role-scoped access.
- Combines query rewriting, vector retrieval, reranking, and result post-processing.
- Normalizes and deduplicates assets, tracks scan coverage and risk state, and provides vulnerability severity classification and lifecycle tracking.
- Provides approval modes, tool allowlists, audit-agent review, and traceable decisions.
- Supports multiple users, system and custom roles, scoped permissions, ownership, and explicit assignments.
- Provides WebShell connection management, virtual terminal, file operations, AI-assisted workflows, listeners, encrypted beacons, sessions, task queues, payload helpers, and live events.
Limitations and risks
- The project is intended for educational and authorized testing purposes only.
- WebShell, C2, and other high-risk capabilities require strict adherence to security models to prevent misuse.
Getting started
- Setup is rated easy and requires only Go and Python prerequisites. The first success path begins with cloning the repository. An OpenAI-compatible model must be configured via AI Channel Configuration.
Evidence and sources
- GitHub project description: The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.
- README: CyberStrikeAI connects planning, execution, human oversight, evidence, and replay in one auditable workspace. Built in Go, it combines Eino-powered agents, MCP-native tools, RAG k…
- README: - Go 1.25+ ([Install](https://go.dev/dl/); required by `go.mod`) - Python 3.10+ ([Install](https://www.python.org/downloads/))
- README: - 🤖 **Agentic execution** translates natural-language intent into governed, auditable security actions. - 🧩 **Eino orchestration** supports single-agent execution plus Deep, Plan-…
- README: - 🧰 **Security tools** include 100+ curated YAML recipes with custom extensions and role-scoped access. - 🔌 **MCP integration** supports HTTP, stdio, SSE, external federation, and…
AI Search
Find projects, verify facts, compare options, or turn a complex need into an actionable plan