#77th of 9 in Security
cyberstrikeai
AI agent platform for authorized penetration testing
- Stars
- 7.9k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Go
Missed the latest GitHub check; these facts may be older.
Overview
CyberStrikeAI is a Go-based platform that turns natural-language intent into governed, audited security operations, using Eino-powered multi-agent orchestration, MCP-native tool integration, and RAG knowledge retrieval. It ships 100+ curated security tool recipes (nmap, sqlmap, nuclei, metasploit, etc.), plus asset and vulnerability management, attack-chain modeling, WebShell management, and a built-in C2 framework, with RBAC, approvals and audit logging for authorized engagements.
Who it is for: Authorized penetration testers and red teams running self-hosted engagements
Strengths
- 100+ curated tool recipes covering recon, exploitation, forensics and post-exploitation in one workspace
- RBAC, approval workflows, audit logs and regex-based call blocking for governed execution
- Attack-chain modeling with cross-session facts, risk scoring and step-by-step replay
- One-command deployment script and built-in self-update/rollback mechanism
Weaknesses
- Includes high-risk capabilities (WebShell, built-in C2) that require careful hardening before use
- No Docker/Compose support listed; deployment relies on local Go/Python setup via run.sh
- Requires external AI provider API keys (OpenAI-compatible) for agent functionality
- Many underlying security tools (nmap, metasploit, hashcat, etc.) must be installed separately
What it needs
- Needs Go 1.25+, Python 3.10+, OpenAI-compatible API, nmap, metasploit, sqlmap, nuclei, SQLite
- Models: OpenAI-compatible models (e.g. GPT-4o, DeepSeek, Qwen)
- port 8080
Also in Security
See all 9| Rank | Project | Score |
|---|---|---|
| 1 | shannonAutonomous pentester that exploits web apps and APIs using source code analysis | 79 out of 100 |
| 2 | StrixAutonomous AI pentesting agents that validate vulnerabilities with working exploits | 75 out of 100 |
| 3 | pentagiAutonomous multi-agent penetration testing system with sandboxed security tools | 75 out of 100 |
| #4 | ifixaiPython CLI that audits AI agents for policy, access and reliability failures | 65 out of 100 |
| #5 | guardrailsProgrammable input, output and dialog guardrails for LLM applications | 55 out of 100 |