pentestagent and CyberStrike
About pentestagent
GH05TCREW/pentestagent
PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.
Built on LiteLLM for multi-model LLM support, PentestAgent features a hierarchical agent architecture where instances can spawn isolated child agents via stdio transport (`spawn_mcp_agent`), enabling parallel task delegation without external orchestration. It integrates MCP (Model Context Protocol) servers with automatic RAG-based tool optimization for large tool sets, includes prebuilt attack playbooks for structured assessments, and offers Docker isolation with both minimal and Kali Linux images containing pentesting tools like metasploit and sqlmap.
About CyberStrike
CyberStrikeus/CyberStrike
AI-powered offensive security agent. Autonomous pentesting with 4 specialized agents, 120+ OWASP test cases, and Kali Linux integration. Your AI red team operator.
Operates as a multi-agent framework with 13+ specialized security agents (web application, cloud, mobile, infrastructure) that inject domain-specific methodology—OWASP WSTG, CIS benchmarks, MASTG/MASVS—directly into LLM reasoning rather than relying on generic chat models. Supports 15+ LLM providers (Claude, GPT-4, Gemini, Bedrock, Groq, DeepSeek, Ollama, and OpenAI-compatible endpoints) with provider auto-detection and schema normalization, enabling offline-first deployments on air-gapped networks. Includes Bolt, a remote tool execution system for distributing security tools across infrastructure via Ed25519-authenticated servers, and integrates with the MCP ecosystem for extensible tool orchestration.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work