-
Automattic
- Queensland, Australia
- in/darthhexx
Stars
Tensors and Dynamic neural networks in Python with strong GPU acceleration
PdfCraft: An open-source PDF reader and editor written from scratch in pure Rust
ARTEX - AI autonomous penetration testing system (English translation; upstream: Autumn-27/ARTEX, AGPL-3.0)
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
Reverse engineer anything with agents, from app behavior down to native binaries.
Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Agentic code review for the Linux kernel and other critical open-source systems software
Reprint — resumable, streaming WordPress site migration over HTTP
An open, programmable decision layer for models and compute.
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
[Anthropic research] We built automated alignment researchers to autonomously post-train other AIs to improve alignment
autonomous red teaming platform; multi-agent offensive-security meta-harness
State of the art inference performance with modern accelerators on Kubernetes
GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
A Call of Duty-quality FPS in Three.js, built from a single prompt.
The Little Book of Reinforcement Learning
Companion code for the global workspace interpretability paper
Train the smallest LM you can that fits in 16MB. Best model wins!
The runtime behind every E2B stack: Cloud, Enterprise, and your own machine.
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning.
Lean 4 programming language and theorem prover
Open source neural network chess engine with GPU acceleration and broad hardware support.
OpenStation is a WordPress plugin that turns /wp-admin into a desktop-style interface with movable windows and a dock menu. It’s opt-in per user, doesn’t change core, and fully reverts on deactivat…
Archived — ML Intern is no longer maintained. Continue with HuggingChat.