JoasASantos/NeuroSploit

NeuroSploit is an advanced, AI-powered penetration testing framework designed to automate and augment various aspects of offensive security operations. Leveraging the capabilities of large language models (LLMs).

49
/ 100
Emerging

Built on a FastAPI backend with a 3-stream autonomous agent architecture (reconnaissance, junior tester, tool runner), NeuroSploit executes tests in isolated per-scan Kali Linux containers and validates findings through an anti-hallucination pipeline with negative controls and proof-of-execution checks. It chains exploits automatically (e.g., SSRF to internal access, SQLi to database-specific payloads), detects and bypasses 16 WAF signatures, and adapts strategy mid-scan based on endpoint responsiveness and diminishing returns. The React frontend provides real-time WebSocket monitoring of scan progress and container health, while the backend supports multiple LLM providers (Claude, GPT, Gemini, Ollama) and exposes 13 REST API routers for scan management, scheduling, and report generation (HTML/PDF/JSON).

942 stars. Actively maintained with 1 commit in the last 30 days.

No License No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 1 / 25
Community 25 / 25

How are scores calculated?

Stars

942

Forks

239

Language

Python

License

Last pushed

Feb 24, 2026

Commits (30d)

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/JoasASantos/NeuroSploit"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.