pentest regulatory intel.stub

---

id: pentest-regulatory-intel name: RegIntel (Penetration Testing Regulatory Intelligence) repo_path: ~/Documents/sw30labs/repos/pentest-regulatory-intel remote_url: https://github.com/sw30labs/pentest-regulatory-intel.git primary_language: Python framework: LangGraph + LangChain ingested: 2026-04-11 last_commit_date: 2026-07-06 category: ai-security stacks: [pentest, langgraph, compliance]

Purpose

AI-powered CLI tool that automatically researches, stores, and manages a global inventory of penetration testing regulations for financial services across 20+ jurisdictions. Uses agentic LLM workflows with mandatory reflection quality gates.

Architecture

Three layers: CLI (Click + Rich), LangGraph agent pipeline (Batch Orchestrator → Research Pipeline with 4 agents: Research, Validator, Reflection, Persister), and dual storage backend (SQLite for structured data, ChromaDB for semantic search). Research and Validator use cloud LLM (GPT-5.4-mini); Reflection and Persister use local MLX Qwen 3.5 122B. The CLI is now organized as a proper Python package, and a periodic regulation-monitoring mode re-checks jurisdictions on a schedule to catch newly published or amended pentest regulations.

Dependencies

langgraph, langchain, langchain-openai, langchain-community, tavily-python, sqlalchemy, chromadb, pymupdf, pdfplumber, click, rich, pydantic, python-dotenv, pyyaml, httpx.

CI/CD

No CI workflows. No Docker.

Entities and topics

• tslit (shared security testing domain)
• agentic-ai-pentesting (shared pentesting research)
• Tags: [python, langgraph, langchain, chromadb, mlx, security, pentesting, cli]