Home Projects CipherChat
CipherChat
Python

CipherChat

A framework to evaluate the generalization capability of safety alignment for LLMs

by RobustNLP · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
alignmentchatgptgpt-4-0613MITPython
View on GitHub
In plain words

Test how well large language models handle safety and alignment by evaluating their responses to coded messages.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
CipherChat — GitHub preview card
📈 Star history
628627
2026-07-202026-08-31
📈 Track CipherChat

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

A framework to evaluate the generalization capability of safety alignment for LLMs

CipherChat has 627 stars on GitHub. It has been forked 67 times. CipherChat is written mainly in Python. It has been in active development since 2023. CipherChat is available under the MIT license. Its main topics are alignment, chatgpt, gpt-4-0613, jailbreak.

Frequently asked questions

What is CipherChat?

A framework to evaluate the generalization capability of safety alignment for LLMs

Is CipherChat open source?

CipherChat is an open-source project. It is released under the MIT license.

Is CipherChat free?

Yes. CipherChat is free and open source — you can use, modify and self-host it.

What license does CipherChat use?

CipherChat is available under the MIT license.

What language is CipherChat written in?

CipherChat is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — CipherChat

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=robustnlp-cipherchat)](https://olud.ai/project/robustnlp-cipherchat.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.