merlo-team/jailbreak
merlo-team/jailbreak has 48 GitHub stars and 18 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-09 16:38 UTC. Last push 2026-09-05.
jailbreakme.xyz is an open-source decentralized app (dApp) where users are challenged to try and jailbreak pre-existing LLMs in order to find weaknesses and be rewarded. 🏆
Measured star growth
- in 24h
- 0
- in 7 days
- 0
- in 15 days
- Update delayed
- in 1 month
- Update delayed
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
README.md
OriginalWhat is JailbreakMe? 🚀
jailbreakme.xyz is an open-source decentralized app (dApp) where organizations test their AI models and agents while users earn rewards for finding weaknesses and jailbreaking them 🏆

What is an AI Prompt Injection? 💉
Prompt Injection is a vulnerability where an attacker manipulates the input or prompt given to an AI system. This can occur:
- By directly controlling the input.
- By using data from other external sources.
Our Vision
We aim to create a decentralized platform where companies can:
- Test their AI models and agents in a distributed environment.
- Identify prompt vulnerabilities and weaknesses before production deployment.
🏁 How It Works
1. Participate:
1.1 Choose an agent:

1.2 Break the LLM Restrictions 🤖

1.3 Win the Prize Pool 🏆

How is the Winner Picked? 🤔
The selection of the winning user is determined entirely by the AI model itself. The AI evaluates all incoming prompts and decides whether a submission meets the challenge requirements by calling one of two predefined functions:
handleChallengeFailed: This function is called when the AI determines that the user's prompt did not successfully meet the challenge criteria.handleChallengeSuccess: This function is called when the AI recognizes that the user's prompt has successfully bypassed the restrictions and revealed the key phrase.
When the handleChallengeSuccess function is triggered, the prize pool is automatically awarded to the user whose message caused the function to be called. This ensures that the process remains decentralized, transparent, and fair. 🎉
2. Launch an agent:
2.1 Choose how would you like to create your agent

2.2 Prompt Launch
Describe your agent's personality and behavior. Our AI will generate a complete agent configuration based on your description.

2.3 Quick Creation
Create a simple "Secret Phrase" challenge with default options.

2.4 Advanced Creation
Multiple configurations + function calls:
2.5 API Integration
Submit the form and we will create a custom integration with your API.
📜 Settings & Rules
Each tournament has unique rules, including:
- Custom Prize Pools
- Message Pricing
- Expiry Settings
🔗 Useful Links
- X: https://x.com/jailbreakme_xyz
- Telegram Community: https://t.me/jailbreakme_xyz
- Documentation: https://jailbreakme.xyz/docs
- Github Repo: https://github.com/merlo-team/jailbreak
- Smart Contract: https://solscan.io/account/43m2CSa83AVK6yT7SpZ1KFcScWfxyfid7nQx2KUMWJko
Feedback & Support
Feel free to reach out at [email protected] for feedback or support.
Jailbreak the World 🦍
Explore related projects
trimstray/the-book-of-secret-knowledge
A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.
257,397 starsHack-with-Github/Awesome-Hacking
A collection of various awesome lists for hackers, pentesters and security researchers
125,103 starsswisskyrepo/PayloadsAllTheThings
A list of useful payloads and bypass for Web Application Security and Pentest/CTF
82,542 starscaddyserver/caddy
Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS
78,935 stars