Concept Modeling: Topic Modeling on Images and Text

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.

Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

A curated set of agent skills for Qdrant vector search, providing structured knowledge on scaling, optimization, monitoring, deployment, and SDK usage.

kapp is a simple deployment tool focused on the concept of "Kubernetes application" — a set of resources with the same label

A set of installable AI agent skills for evidence-driven design award research, evaluation, matching, entry writing, and submission readiness, supporting multiple agent runtimes.

A proof-of-concept jupyter extension which converts english queries into relevant python code

A pipeline of 7 agent skills to convert any novel into a playable web game, installable on Claude Code, Codex, and Kimi Code.

Gridgeist turns product intent into a rigorous visual system—without the generic AI SaaS aftertaste.

EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.