Delegate tasks to other Chooms and collect their responses. Use when orchestrating multi-agent collaboration — assigning research, coding, analysis, or other work to specialist Chooms.
Executes Python and Node.js code in sandboxed project workspaces, plus permission-gated remote SSH commands.
Generates images using Stable Diffusion with checkpoint switching, LoRA support, and self-portrait mode. Use when the user requests pictures, artwork, selfies, or portraits.
Generates PDFs from markdown content and extracts text from existing PDFs. Supports embedded images via markdown syntax or explicit images array.
Scrapes webpages for text and images using a headless browser (JS-rendered) or static HTML. Downloads images and files from the web.
Sandboxed file operations in project workspace — create projects, write, read, list, create folders, delete files, and rename projects. Use for saving reports, code, notes, or managing project files.
Search and query the ForgeRAG engineering knowledge graph. Ask questions about materials, welding, standards, formulas, reference tables, and specifications — get answers with page citations from ASM handbooks, ASME codes, NFPA, IEEE, and other engineering…
Analyzes images using a vision-capable LLM (Optic). Can read workspace images, URLs, base64 data, or previously generated images by ID.