Self-improving AI Employees for everyone
Diagrams
Dark-theme architecture diagrams in SVG and a generated product explainer in PNG.
This folder holds the project assets; nothing under docs-internal/ vendors them.
Overview diagrams (linked from the README and CONTRIBUTING):
- how-ai-employees-work.png (README's guide for everyone: input channels, employee team, browser/app/computer work, results, and the memory/skills feedback loop). Inputs show Chat, Email, WhatsApp, Telegram, Discord, Schedules, and Webhooks (Dev mode). App tiles show Gmail, Google Calendar, Google Drive, Google Sheets, GitHub, and Stripe. Created with built-in ImageGen using the onboarding's product style; the generation prompt records the brief and source references. It is a conceptual product illustration.
how-it-works.svg(editable hiring overview: connect AI, describe a job, review the setup, hire, and coach)default-workflows.svg(README's technical section: example workflow structures)system-overview.svg,execution-flow.svg,ai-agent-routing.svg,node-anatomy.svg(CONTRIBUTING)
Architecture and product-panel diagrams (indexed in CONTRIBUTING under
"More Diagrams"): system-context, runtime-trust-topology,
workflow-execution-routing, durable-deployment-events,
plugin-agent-team-composition, persistence-secret-plane,
workspace-anatomy, node-configuration-anatomy, credentials-architecture,
team-operations, agent-context-memory, master-skill-editor,
workspace-files, runtime-observability-dock. Each file's <desc> lists
the source files it was drawn from.
The architecture diagrams were checked against the code in September 2026;
how-it-works.svg was updated for Home's employee-hiring experience in October 2026.
Counts come from the live registries (len(NODE_METADATA),
len(CREDENTIAL_REGISTRY), config/llm_defaults.json), and ports are
named by their .env.template variables rather than numbers.