sooryathejas/metatron

AI-powered penetration testing assistant using local LLM on linux (Parrot OS)

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 1 hour ago
Added to GitGenius on September 16th, 2026
Created on April 2nd, 2026
Open Issues & Pull Requests: 19 (+0)
GitHub issues: Enabled
Number of forks: 816
Total Stargazers: 4,154 (+0)
Total Subscribers: 31 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 7.4 hours
Mean response time: 9.1 hours
90th percentile: 19.2 hours
Tracked items: 20

Most active contributors

Sign in to see contributor activity.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 11
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 110 days
Stale 30+ days: 7
Stale 90+ days: 7

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Metatron is an AI-powered penetration testing assistant that runs a local large language model on Linux systems, specifically Parrot OS.

The tool addresses the need for intelligent guidance during security testing by integrating a locally-hosted language model into the penetration testing workflow. Rather than relying on external APIs or cloud-based services, Metatron keeps the LLM running on the user's own machine, which preserves privacy and avoids dependency on internet connectivity. The assistant can provide real-time recommendations, explanations, and tactical guidance as a penetration tester works through reconnaissance, exploitation, and post-exploitation phases.

Metatron is suited for security professionals and penetration testers who work on Parrot OS and want an AI assistant that operates entirely within their local environment. It is particularly valuable for those who prioritize data privacy, work in air-gapped or restricted network environments, or prefer not to send sensitive testing details to third-party services. The choice to use a local LLM rather than a cloud-based alternative means users maintain complete control over their prompts and responses, though this comes with the computational overhead of running the model locally.

The project shows active development with recent commits and ongoing refinement of its core functionality. The codebase is written in Python, making it accessible for modification and integration into existing security testing workflows. The tool remains focused on its specific use case of supporting penetration testing activities on Parrot OS rather than attempting to be a general-purpose security platform.