Kumiko Enterprise

Enterprise These features ship in the commercial Kumiko Enterprise offering, layered on top of the open framework. Want access? See kumiko.rocks.

Each feature below has a generated reference page (config keys, dependencies, secrets) — the same drift-free tables as the bundled features, introspected from the booted registry.

AI feature-builder

Generate, refine, and draft with LLMs — the engine behind the visual Designer and the AI authoring flow.

ai-foundation The LLM platform layer — per-tenant provider resolution, prompt assembly, system-prompt config.

ai-generate Generate a whole feature from a prompt, with a compile-validation loop.

ai-patch Suggest a targeted patch to an existing feature.

ai-draft Draft a reply message from a source message and a stated purpose.

ai-triage Triage and route incoming items with an LLM.

ai-conversation Persistent, event-sourced multi-turn conversations on top of ai-foundation.

prompt-store Event-sourced, versioned prompt templates with edit/revert handlers.

designer Visual feature builder backed by pattern storage.

AI providers

Pluggable LLM backends — pick per tenant via config. Each declares its own API-key secret.

ai-provider-anthropic Anthropic Claude provider.

ai-provider-openai-compat OpenAI-compatible provider (OpenAI, Azure, local).

ai-provider-mock Scriptable mock provider for tests and demos.

transcribe-provider-openai-compat Speech-to-text via an OpenAI-compatible transcription API.

Pattern storage & publishing

Store, version, and publish the feature patterns the Designer and AI builder produce.

pattern-storage Versioned storage for feature patterns.

publish Publish stored patterns into a running app.

Advanced renderers

Richer notification rendering than the open renderer-simple.

renderer-mail-html HTML email rendering via the template resolver.

renderer-puppeteer-client PDF / image rendering via a Puppeteer service.