β¦ilsonnn/image-blaster1d ago
Converts an input image into 3D meshes, Gaussian splats, and audio files using Claude skills and external AI APIs.
Converts an input image into 3D meshes, Gaussian splats, and audio files using Claude skills and external AI APIs.
Archives experiments of AI agents autonomously tuning optimizers, schedules, and hyperparameters to reach target validation loss in fewest steps on a small LM benchmark.
Automates articulated 3D asset creation by prompting LLMs to generate executable Python code defining parts, geometry and joints.
Streams live traces of coding agent actions including tokens and tool calls to a local UI at localhost:5899.
Runs LLM inference server with continuous batching and tiered SSD KV caching for Apple Silicon, managed via macOS menu bar.
Examines GitHub user profiles and recent PR/issue activity to assess contribution review investment.
Serves PyPI download statistics via a Flask dashboard with Plotly charts and a JSON API.
Measures Python class cohesion by analyzing how methods share class and instance variables.
Reconstructs graphics-ready 3D scenes with PBR materials from RGB-D scans via AI-based segmentation and texturing.
Implements a minimal single-file LLM-driven loop that gathers context and executes coding tasks via human-approved shell commands.
Controls web interfaces via natural language using an in-page JavaScript GUI agent with text-based DOM manipulation.
Implements a Gymnasium environment where a circular agent pushes a T-shaped block into a goal zone with continuous position actions and optional image or state observations.
Displays staged and unstaged Git diffs in a desktop viewer supporting inline comments and Markdown export.
Creates customizable NetHack-based reinforcement learning environments via Gymnasium API and description files.
Implements a local-first relational database that syncs across browsers, React Native, and backends.
