adrian803

adrian803 / LingXi

Public

LingXi: multi-agent CTF and pentest framework originated from Tencent Security Hackathon

ctf cybersecurity docker fastapi gplv3
13
1
69% credibility
Found Apr 18, 2026 at 13 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

An open-source framework using AI agents to automate penetration testing for CTF challenges, with integrated tools, knowledge bases, and a web dashboard.

How It Works

1
🔍 Discover LingXi

You hear about LingXi, a smart helper that automates solving security challenges like in CTF games, making pentesting easier and faster.

2
📦 Get it ready

Download and set up LingXi on your computer with simple steps, like creating a safe space for it to run.

3
🔗 Link smart thinkers

Connect AI services so LingXi can plan, explore, and learn from past successes like a clever teammate.

4
🛠️ Power up tools

Attach helpful tools like scanners and command runners, so it can safely test targets without limits.

5
📊 Open the dashboard

Launch the web view to watch everything happen live, like a control room for your missions.

6
🎯 Start a challenge

Pick a security puzzle, and LingXi begins scouting, attacking, and grabbing hidden flags automatically.

🏆 Flags captured!

Sit back as LingXi solves challenges, collects rewards, and learns for next time, turning hard work into wins.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 13 to 13 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is LingXi?

LingXi is a Python-based multi-agent framework for automating CTF challenges and pentests, originated from the Tencent Security Hackathon. It pulls tasks from competition platforms, runs recon, executes tools in Dockerized Kali environments, corrects strategies via LLM agents, submits flags, and builds a knowledge base from writeups. Users get a CLI-driven system with web dashboard for monitoring runs, supporting main battlefields, forum tracks, and custom extensions like Sliver for lateral movement.

Why is it gaining traction?

It stands out by closing the pentest loop—recon to flag submission—with multi-agent roles (main attacker, advisor, reflector) that learn from failures and CTF writeups via RAG. Developers dig the robust failover for APIs/LLMs, Kali tool integration, and modes like `--all` for dual-track runs or `--web` for live dashboards. No more manual tool chaining; it handles concurrency, timeouts, and progress tracking out of the box.

Who should use this?

CTF competitors automating Tencent-style hackathons, red teamers scripting pentests with LLMs, and security engineers testing multi-stage challenges like AD pivots or CVE exploits. Ideal for those grinding repetitive recon/exploitation in Docker-safe environments without building agent orchestration from scratch.

Verdict

Worth forking for CTF automation—strong docs, .env config, and hackathon polish make it runnable fast—but at 13 stars and 0.7% credibility score, it's early-stage with room for broader tests and community PoCs. Prototype it on your next lingxi du or lingxi tang challenge before production pentests.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.