I tried to give an LLM ADHD by modifying its attention. Three interventions, three failure modes, one orchestration pattern that actually works.

AI governance guardrails for coding agents. Curated security and compliance patterns from NIST AI RMF, OWASP Top 10 for LLMs, and ISO/IEC 42001.

DeepScout is a fully optimized small-model research agent that distills frontier-level web reasoning into deployable 3B models using QLoRA, post-training quantization, and vLLM serving — powering a…

AI-powered offensive security testing using autonomous agents, directly in your terminal.

Fast, accurate & comprehensive text measurement & layout

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

An Anthropic Claude Skill for evidence-first startup idea evaluation, market research, competitor mapping, beachhead market selection, BHM TAM sizing, validation design, and GTM hypothesis generation.

🦕 A collection of Orpheus (Hack Club's mascot) drawings! Look at them at rawr.hackclub.com :)

Course Files for Complete Python 3 Bootcamp Course on Udemy