heretic-llm is an open-source command-line tool that automatically removes censorship mechanisms from transformer-based language models. It is designed for AI researchers who need unrestricted access to model outputs for research or experimentation. The tool is AGPL-licensed and runs locally.
In the AI security & guardrails space, heretic-llm takes a focused approach. It focuses on removing automated censorship restrictions from language models for unrestricted text generation. heretic-llm is an open-source project aimed at AI researchers. The project is open source (AGPL-3.0). It runs on the web and the command line, and it can be self-hosted.
p-e-w builds and maintains heretic-llm, and it first shipped in 2025. Development happens publicly on GitHub with 25.1k stars and 55 commits in the last 90 days. Among its 5 catalogued features are censorship removal, LLM patching, and command-line interface.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do