heterodoxin/AbliteratedOutTheBox
CLI tool
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 3 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change yesterday.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A llama.cpp fork that reads refusal and disclaimer directions from each prompt at inference and removes them from activations when a look-ahead gate fires, without modifying the stored model weights. Benign prompts are left unchanged in the reported tests.
Who it's for
Researchers and developers testing refusal behavior in local LLMs who want inference-time abliteration on llama.cpp-supported models
How to use it
Install
cmake -S . -B build -DCMAKE_BUILD_TYPE=ReleaseFrom its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up heterodoxin/AbliteratedOutTheBox in my project. Follow its README: https://github.com/heterodoxin/AbliteratedOutTheBox. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
20,109 GitHub repos watched and ranked every hour. Figures as of 25 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/heterodoxin/AbliteratedOutTheBox?ref=badge)Similar repos
- abhi245y/PS5LM-Plus
A native app that runs llama.cpp on a jailbroken PlayStation 5 using its GPU via Vulkan. It loads GGUF models from internal or USB storage, shows a dashboard on the TV, and exposes a chat UI and OpenA
- routerhubSI/glm-5.3-abliterated
A guide to GLM 5.3 model variants (abliterated and uncensored labels) accessed through the RouterHub API gateway. It includes a catalogue of 35 bundled prompt files grouped by model family, plus notes
- cobanov/PS5LM
A PS5 homebrew app that runs llama.cpp on the console's GPU and serves GGUF models over OpenAI- and Anthropic-compatible HTTP APIs on the local network, with a TV interface and a decision-model endpoi
- 7API/glm-5.3-abliterated
Marketing-heavy README for a GLM 5.3 abliterated or uncensored model guide, a collection of 35 jailbreak prompt files for various models, and API access through the 7API service. The jailbreak prompts
- alleyxd/AnyDecide
A Python library and HTTP service that turns a local language model into a decision API. Typed questions (choice, score, yes/no) are answered in one batched forward pass by reading next-token probabil
- arhappy777/llm_pentesting
A README describing a freelance AI red team and LLM security consultancy offering audits of LLM applications, prompt injection testing, data access control reviews, and AI agent, API and MCP security