Automatically remove censorship from language models to retain their original capabilities without complex training.
pip install -U heretic-llm heretic Qwen/Qwen3-4B-Instruct-2507
Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeFully automatic censorship removal for language models
heretic has 29.1k stars on GitHub. It has been forked 3.2k times. heretic is written mainly in Python. It has been in active development since 2025. heretic is available under the AGPL-3.0 license. Its main topics are abliteration, llm, transformer.
Fully automatic censorship removal for language models
heretic is an open-source project. It is released under the AGPL-3.0 license.
Yes. heretic is free and open source — you can use, modify and self-host it. Its AGPL-3.0 license is a strong copyleft: if you distribute a modified version — including offering it as a network service — your changes must be released under the same license.
heretic is available under the AGPL-3.0 license.
heretic is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/p-e-w-heretic.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.