THE WORLD'S FIRST SELF-EVOLVING CTF PLATFORM

Where AI Meets Hacking

An AI pipeline that designs challenges, hacks them, calibrates their difficulty, and evolves them overnight. A training ground that gets smarter every time someone plays.

Not hand-crafted. Not static. Not the same for everyone.

The Living Loop

This isn't a linear process. It's a continuous cycle where every player interaction feeds back into the system. The more people play, the better the platform becomes. Every solve, every hint, every failure is signal.

01

Generate

AI designs the challenge

LLM agents craft a realistic scenario — vulnerable web app, flawed smart contract, exploitable binary — complete with narrative, Docker sandbox, and working exploit. Every challenge passes an 8-stage pipeline: design, static analysis, automated validation, exploit verification, difficulty calibration, quality scoring, hardening, and deployment. Nothing reaches you that the AI hasn't already hacked itself.

02

Hack

You attack a live sandbox

No multiple choice. No simulated terminals. You get a real Docker container running a real vulnerable application — plus a fully loaded attackbox with nmap, sqlmap, Burp-style tools, pwntools, gdb, and more. Find the vulnerability, craft your exploit, capture the flag. Exactly like a real engagement.

03

Analyze

AI measures your performance

Your solve time is benchmarked against the AI's own par time — like golf. Performance feeds into your multi-axis skill vector across 11 challenge types. Difficulty is recalibrated using community solve data, hint usage, attempt variance, and time distributions. The platform knows exactly where you stand.

04

Evolve

The platform rewrites itself

Every night, four autonomous loops run: challenges with extreme solve rates mutate into harder or easier variants. Difficulty ratings recalibrate from real data. Underperforming LLM prompt templates get rewritten by AI. Gaps in the difficulty curve are filled with new auto-generated challenges. You wake up to a smarter platform.

CONTINUOUS LOOP

What Makes This Revolutionary

Traditional CTF platforms are built by humans, for humans, and they stay exactly the same until a human changes them. We built something fundamentally different.

Challenge Creation
Human authors hand-craft 50 challenges per year
AI generates unlimited unique challenges on demand
Difficulty
Static labels — easy, medium, hard — set once by the author
Self-calibrating from community solve data, hint usage, and time distributions
Personalization
Same challenges for everyone, in the same order
Per-category skill vectors target your weakest areas with surgical precision
Platform Evolution
New content when authors have time — maybe quarterly
Four nightly AI loops: mutate, recalibrate, evolve prompts, fill gaps
Scoring
Points or first-blood — rewards speed over learning
Par system benchmarked against AI solver times — can you beat the machine?
Environment
Web forms, simulated terminals, or shared VMs
Dedicated Docker sandboxes: target container + attackbox with real hacking tools

Can You Beat the Machine?

Every challenge has a par time — the time it took our AI exploit agent to solve it blind, with no prior knowledge. Your performance is benchmarked against the machine. Like golf, lower is better.

Eagle< 75% of par
Par75% - 125%
Bogey125% - 250%
Double Bogey250% - 500%
Over Par> 500%

Eagles are rare. The AI is fast, methodical, and doesn't get distracted. Beating it means you saw something the machine missed, or you just know the technique that well. Eagle solves earn 2x coins and bonus XP.

Truly Adaptive Difficulty

Not a single ELO number. A multi-dimensional skill profile that knows exactly where you're strong, where you're weak, and what to throw at you next.

Skill Vector

Your abilities are tracked independently across all 11 challenge types. Great at web exploitation but weak on crypto? The AI knows and targets those gaps. Strong categories get stretched with harder challenges. Weak categories get reinforced.

ELO Rating

Start at 1000 ELO. K-factor 32 means your rating converges fast. Fast solves earn time bonuses. The system tracks your last 5 attempts per category — 80%+ success rate means you get stretched harder. Below 20% and the AI eases up. No plateaus.

Smart Hints

Three progressive hint levels, each generated by AI with your specific skill profile in mind. A beginner gets different guidance than an expert stuck on the same challenge. Hints cost ELO (5%/15%/30%) — use them wisely, or challenge yourself to go hint-free.

Challenge Matching

When you ask for the next challenge, the AI computes a target difficulty using your per-category skill vector, recent performance trends, and stretch factors. It selects the challenge closest to that target. Never too easy. Never impossible. Always in the growth zone.

Under the Hood

This is not a wrapper around ChatGPT. It's a purpose-built AI pipeline with specialized agents, Docker orchestration, and self-improving feedback loops.

8-Stage Pipeline

Design, Static Analysis, Validation, Calibration, Exploit Verification, Quality Scoring, Hardening, Deploy

Docker Sandboxes

Isolated dual-container architecture: vulnerable target + fully loaded attackbox per session

Multi-Provider LLM

Anthropic Claude, Google Gemini, OpenAI GPT — hot-swappable via config

4 Evolution Loops

Challenge mutation, difficulty recalibration, prompt evolution, adaptive gap-filling

Exploit Validation

Every challenge is attacked by AI before you see it — 4 strategies, 5-attempt iterative refinement

Quality Scoring

Weighted multi-factor formula: code quality, exploit reliability, narrative coherence, difficulty accuracy

11 Types. 33 Categories.

From classic web exploitation to cutting-edge AI/LLM security. Every category runs in its own specialized sandbox with the right tools, frameworks, and runtime.

Web Exploitation

6 categories

SQLi, XSS, SSRF, Path Traversal, Auth Bypass, Command Injection

Cryptography

3 categories

RSA, AES, Hash Attacks

Binary Exploitation

3 categories

Buffer Overflow, Format String, Heap

Smart Contracts

3 categories

Reentrancy, Overflow, Access Control

Reverse Engineering

3 categories

Static Analysis, Dynamic Analysis, Obfuscation

Forensics

3 categories

Memory Forensics, Disk Forensics, Network Forensics

OSINT

3 categories

Social Media, Geolocation, Data Mining

AI/LLM Security

3 categories

Prompt Injection, Jailbreak, RAG Poisoning

API Security

3 categories

Broken Auth, Injection, Rate Limiting

Malware Analysis

3 categories

Static, Dynamic, Network

Miscellaneous

3 categories

Steganography, Encoding, Logic Puzzles

Web: Flask/Python · Crypto: PyCryptodome · Pwn: C/socat/Ubuntu · Smart Contracts: Solidity/Hardhat · AI: Mock LLM chatbots · And more

Built to Keep You Coming Back

Skill development requires consistency. Every system here is designed to keep you training, not just playing.

12 XP Levels

Recruit to Mythic. XP scales with difficulty and par performance. Each rank unlocks at a defined threshold.

30+ Badges

5 rarity tiers from Common to Legendary. First Blood, Speed Demon, No Hints, category mastery, and more.

Daily Streaks

Solve daily for XP multipliers. Purchase streak freezes with coins when life gets in the way. Comeback bonuses up to 5x.

Coin Economy

Every solve earns coins (10 to 100 by difficulty). Eagle bonus doubles it. Spend on streak freezes, hint tokens, and more.

Daily & Weekly Missions

Targeted challenges that adapt to your weak areas. Complete them for coin and XP rewards. Missions refresh regularly to keep training diverse.

Real-Time Notifications

Streak risks, rank changes, mission deadlines, badge unlocks — all pushed to your notification bell so you never miss a milestone.

Join the Evolution

The platform is live. The AI is running. New challenges are being generated, calibrated, and evolved right now. The only question is whether you're training on a static platform — or one that grows with you.

Free to play. No credit card. Start hacking in 60 seconds.