NeuroSploit v3.2 - Autonomous AI Penetration Testing Platform

116 modules | 100 vuln types | 18 API routes | 18 frontend pages

Major features:
- VulnEngine: 100 vuln types, 526+ payloads, 12 testers, anti-hallucination prompts
- Autonomous Agent: 3-stream auto pentest, multi-session (5 concurrent), pause/resume/stop
- CLI Agent: Claude Code / Gemini CLI / Codex CLI inside Kali containers
- Validation Pipeline: negative controls, proof of execution, confidence scoring, judge
- AI Reasoning: ReACT engine, token budget, endpoint classifier, CVE hunter, deep recon
- Multi-Agent: 5 specialists + orchestrator + researcher AI + vuln type agents
- RAG System: BM25/TF-IDF/ChromaDB vectorstore, few-shot, reasoning templates
- Smart Router: 20 providers (8 CLI OAuth + 12 API), tier failover, token refresh
- Kali Sandbox: container-per-scan, 56 tools, VPN support, on-demand install
- Full IA Testing: methodology-driven comprehensive pentest sessions
- Notifications: Discord, Telegram, WhatsApp/Twilio multi-channel alerts
- Frontend: React/TypeScript with 18 pages, real-time WebSocket updates

backend/requirements.txt

@@ -0,0 +1,40 @@
+# NeuroSploit v3 - Backend Requirements
+fastapi>=0.109.0
+uvicorn[standard]>=0.27.0
+pydantic>=2.5.0
+pydantic-settings>=2.1.0
+
+# Database
+sqlalchemy[asyncio]>=2.0.0
+aiosqlite>=0.19.0
+
+# HTTP Client
+aiohttp>=3.9.0
+
+# LLM APIs
+anthropic>=0.18.0
+openai>=1.10.0
+
+# Docker SDK (Kali Sandbox)
+docker>=7.0.0
+
+# Utilities
+python-multipart>=0.0.6
+python-jose[cryptography]>=3.3.0
+
+# Report Generation
+jinja2>=3.1.0
+weasyprint>=60.0; platform_system != "Windows"
+
+# Scheduling
+apscheduler>=3.10.0
+
+# RAG - Semantic Search (optional, enhances knowledge retrieval)
+# pip install chromadb sentence-transformers  # Best: semantic embeddings
+# pip install scikit-learn numpy              # Good: TF-IDF statistical similarity
+# No install needed for BM25 (default, zero deps, works out of box)
+
+# Development
+httpx>=0.26.0
+pytest>=7.4.0
+pytest-asyncio>=0.23.0