EXTENSIONS

Generate Ixen pages — self-narrated, mixed-media web pages in the tradition of 'I, Xen' (2005), where the technology itself speaks in first person while teaching real technical content. Self-contained HTML output with pop-up command windows, zoomable images, embedded video/audio/PDF, and inline cheatsheet/infographic embeds. Uses Claude or any OpenAI-compatible endpoint, or saves agent-written pages keylessly.

Generate browser-ready infographic pages using OpenAI image generation. Produces an image, reliable HTML text shell, and relative output suitable for embedding in @alvagante/content-ixen.

Generate images using the OpenAI Images API (gpt-image-1.5 by default). Supports transparent PNG output and 11 style presets: ixen-dark, ixen-light, pencil-bw, pencil-color-accents, blueprint, technical-diagram, cyberpunk-photo, educational, clean, editorial, none. Optional outputDir for composing multi-media mini-sites alongside content-ixen pages.

Generate 'I Am' biography minisites — self-narrated, editorial-style HTML pages where a real person, fictional character, or AI persona speaks in first person about their own life. Facets replace concepts; a Dateline replaces the cheatsheet; an Influence Map replaces the infographic. Wikipedia grounding for real subjects. Sticky sidebar navigation, side-drawer study popups, 3D-flip facet card grid, and an optional bottom audio player. Visual register: editorial magazine (Georgia serif, warm off-white palette, warm brown accent) — intentionally distinct from @alvagante/content-ixen.

Generate self-contained HTML timelines for any subject — biographical, historical, project, technology, or custom. Events are grouped into named phases; all content must be factually documented (no invented dates or events). Uses Claude or any OpenAI-compatible endpoint, or stores caller-written content via the save method.

OpenAI image generation and editing via gpt-image-1 and DALL-E 3 — text-to-image generation, image editing with reference images, model selection, and configurable size and quality. Vault-based API key.

OpenAI-powered document and webpage generation — analyze and enhance .pptx/.docx, design PDFs from natural language, compose decks from outlines using your own theme template, and generate self-contained HTML/CSS pages from reference designs via vision. Vault-based API key, headless Chromium for rendering.

Generate songs from topics using Claude for lyrics and 1min.ai (Suno or Lyria) for audio. Part of the @alvagante content-media suite.

Azure OpenAI / AI Services token usage monitoring — multi-subscription

GCP Vertex AI token usage monitoring — multi-project scanning of

AWS Bedrock token usage monitoring — multi-account fan-out scanning of

Unified cross-provider AI token usage monitoring — workflow, model, and

Generate playing-card shaped content images using OpenAI image generation. Adds card sequence, skill-level corner numbering, topic icons, optional logo hints, and expanded card-specific style presets.

Generate platform-shaped social media post drafts for Facebook, X, LinkedIn, TikTok, and Instagram. Supports persona-driven text, short posts, text plus image/card plans, provided media, and orchestration-friendly media requests for @alvagante/content-image and @alvagante/content-card.

Generate publication-ready blog posts on any topic using Claude or any OpenAI-compatible endpoint, or save agent-written posts keylessly. Configurable skill level (novice/intermediate/senior/guru), output length, writing persona presets, and model selection.

Generate dense, visually structured cheatsheets on any technical topic. Outputs print-to-PDF-ready HTML (Cmd-P → Save as PDF) or GitHub-flavoured Markdown. Configurable skill level (novice→guru), verbosity, and completeness. Uses Claude or any OpenAI-compatible endpoint, or stores agent-written content keylessly.

A sourced, versioned knowledge base of LLM-ops knowledge — NOT a control plane for running models, but the structured, CEL-queryable record that running extensions read to decide which model to run where, with what settings, at what cost. Six subject kinds (model, runtime, provider, hardware, technique, endpoint), all the same uniform `entry` shape (open kind + open facets, like @stateless/inventory); a model's run-options embed on the model in runsOn[] keyed by endpoint, and capacity/plan answer "what to run where" over them. The twist: it records external, decaying knowledge, so every volatile assertion carries a provenance envelope (asOf, source, versionPins, supersededBy) — "best vLLM version" is derived as the latest un-superseded claim, never a bare rotting field. Declarative: `apply` materialises one `entry` resource per id (re-run = versioned trend); `prune` soft-retires undeclared entries.

Chat completions and model catalog listing against the OpenRouter LLM gateway API

Ollama LLM integration (generate, batch generate, unload)

Generate text with Anthropic's Claude models via the Messages API from swamp workflows.