MyModels by Forgeboro

Documentation & Spec
← Open MyModels Chat

Private Local & In-Browser AI Workspace

MyModels connects directly to local models via Ollama or executes neural models 100% inside your browser using WebGPU hardware acceleration, WebAssembly CPU execution, and Chrome's native Prompt API (Gemini Nano).

Key capabilities include multiline prompt composition with draft traversal history, streaming token rendering, dual-tab SVG graphics visualization, sequential multi-instruction batch queue, hardware diagnostics, and signed HMAC-SHA256 state backups.

Interactive Tools & Selectors

Prompt Composer Enter

Multiline prompt editor. Auto-expands as text is typed. Shift+Enter for newlines. Up/Down arrows to traverse historical prompt drafts.

[data-tool="prompt-input"]

Model Selector

Categorized selector supporting Ollama daemon models, Chrome Built-in Gemini Nano, and In-Browser WebGPU/WASM models.

[data-tool="model-selector"]

Hardware & AI Diagnostics

Inspects WebGPU adapter limits, FP16 shader capability, Chrome Prompt API status, and cached offline model weights.

[data-tool="hardware-diagnostics"]

Session Drawer Toggle

Collapses or expands the left-hand navigation sidebar containing chronological chat history and session controls.

[data-tool="sidebar-toggle"]

Sequential Command Queue

Enables batch queuing of multiple prompt instructions and file payloads, executing sequentially with autonomous streaming completion.

[data-tool="command-queue"]

Interactive SVG Canvas

Dedicated rendering canvas for inline SVG vector art generated by LLMs, featuring zoom controls and raw XML source inspection.

[data-tool="svg-viewer"]

Obsidian Theme Toggle

Switches between Forgeboro obsidian glassmorphism dark theme and clean high-contrast light mode.

[data-tool="theme-toggle"]

Keyboard Shortcuts

Shortcut Action Description
Enter Submit current prompt to model
Shift + Enter Insert newline without submitting
↑ / ↓ Traverse backward/forward in prompt draft history
? Open in-app interactive Help & Documentation modal
Escape Close active modal dialog or abort streaming completion
Ctrl + Shift + O Start new chat session

In-Browser Models & WebGPU Setup

MyModels supports zero-install local AI running directly in your browser tab. Model weights downloaded by Transformers.js or WebLLM are cached permanently in browser storage for full offline use.

1. Chrome Built-in Prompt API (Gemini Nano)

In Chrome 127+, enable chrome://flags/#prompt-api-for-gemini-nano and chrome://flags/#optimization-guide-on-device-model (Enabled BypassPerfRequirement). In chrome://components, update "Optimization Guide On Device Model".

2. Universal ONNX & WebLLM Models

Models like SmolLM2 (135M/360M), Qwen 2.5 (0.5B/1.5B), and Llama 3.2 1B execute via WebGPU shaders with automatic CPU WebAssembly fallback.

AI Agent Automation API

Autonomous agents and testing harnesses can inspect and control MyModels programmatically via the global controller:

window.__MYMODEL_AGENT_SPEC__ = {
  appName: "MyModels by Forgeboro",
  version: "V1-[hash]",
  getTool: (id) => document.querySelector(`[data-tool="${id}"]`),
  getAction: (id) => document.querySelector(`[data-action="${id}"]`),
  spec: { ... }
};

The raw machine-readable specification is accessible at /agent-spec.json.