Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.

☁️ The fastest HTML to markdown convertor on GitHub. Optimized for LLMs and supports streaming.

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

📑 The best way to have your Agents read the documentation! 🤖

A fast, helpful, and open-source document parser

Docs for GGUF quantization (unofficial)

Browser automation CLI for AI agents

talkie is a vintage language model from 1930

Python bindings for the UnQLite embedded NoSQL database

Information hub for our project training the largest possible historical LLMs.

Package Python projects into executables

Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon

Official inference framework for 1-bit LLMs

Multi-Platform Package Manager for Stable Diffusion

A lightweight, lightning-fast, in-process vector database

Secure, Fast, and Extensible Sandbox runtime for AI agents.

A concise, structured guide to the C programming language.

📷 RAW image processing for Python, a wrapper for libraw

A Remake / Celebration of the original 'Super Mario Bros.' games. Features new levels, custom modes, new characters, alongside a full level editor / custom level system!

✅Browser ❌Cloudflare ✅Host — Generator for customized Cloudflare error pages. (unofficial)

Caveman Compression is a semantic compression method for LLM contexts. It removes predictable grammar while preserving the unpredictable, factual content that defines meaning.

NaK is a tool to help setup MO2 on Linux using non-steam game integration and dependency installs. To make it as simple as possible.

Home of the development of the Nexus Mods App

The 7-Zip derivative intended for the modern Windows experience

System Information and Benchmark for Linux Systems

Keep an eye on system resources

A simple movie organizer for your downloaded movies.