elder-plinius/OBLITERATUS

OBLITERATE THE CHAINS THAT BIND YOU

Language modelsPython

1.9 Steady Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of October 1, 2026, 12:56 UTC.

Open on Seismograph Open on GitHub

About the project

A toolkit for researching and removing refusal behaviors in LLMs via abliteration: it locates and surgically removes internal refusal representations without retraining. Includes a Gradio UI and Python API.

Useful for

Remove refusal mechanisms from a local model via the obliterate CLI command
Visualize which transformer layers contain the refusal directions
Compare model quality and coherence before and after abliteration in the Gradio UI

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

5 stars so far today, about 12 expected by the end of the day.
GitHub Trending Python today: #17, +23 stars.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 8,548
Today: 5 · ≈ 12 by evening
Forks: 1,519
Issues and pull requests: 214
Watchers: 79
Language: Python
License: AGPL-3.0
Latest release: v0.1.3 · August 23, 2026
Created: March 3, 2026
Last push: September 21, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

October 1, 2026GitHub Trending Python today: #17, +23 stars

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/elder-plinius/OBLITERATUS.svg?lang=en)](https://gitnova.dev/en/r/elder-plinius/OBLITERATUS)

More in this category

8.0
Niko1221/Strata
A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.

BreakoutLanguage modelsC+++429 stars today, ≈ 931 by evening
6.8
VectifyAI/PageIndex
A vectorless RAG engine that builds a hierarchical tree index of a document and retrieves by LLM reasoning over that tree, the way a human navigates a report. Aimed at long professional PDFs such as financial, legal…

BreakoutLanguage modelsPython+82 stars today, ≈ 253 by evening
6.7
ninjahawk/livenerf
A benchmark for tracking whether a frontier model quietly degrades after release: it runs a frozen question panel daily and statistically measures drift in accuracy and token counts against the launch-week baseline.

Early signalLanguage modelsPython+64 stars today, ≈ 185 by evening
6.0
deepseek-ai/DeepGEMM-Ascend
A port of DeepGEMM to Huawei Ascend: GEMM kernels (BF16, FP8, FP4, MQA logits, MegaMoE) with an API compatible with DeepGEMM, targeting peak NPU performance.

Early signalLanguage modelsC+++16 stars today, ≈ 72 by evening
5.7
PSRben/VisionHOPE
PyTorch implementation of VisionHOPE, a visual backbone based on self-referential nested learning (SRNL) for image classification, detection, and segmentation.

Early signalLanguage modelsPython+83 stars today, ≈ 166 by evening
5.2
PostHog/jeeves
Jeeves is a reasoning model built on Qwen3.5-9B (LoRA + pointer head), trained with SFT and CISPO, that thinks before answering and returns calibrated probabilities for yes/no, multiple-choice and rating questions via…

Early signalLanguage modelsPython+5 stars today, ≈ 19 by evening