DoubleXL
A composable AI-system ecosystem — four independently versioned repos that layer together into a full-stack knowledge pipeline.
Composition Architecture
The Four Repos
Defines the schema, templates, and generation CLI for AI workflow definitions. Produces entity models, workflow specs, and foundation scaffolds from structured markdown definitions.
View demo →Provides the runtime scaffold and UI primitives consumed by blueprint output. Houses the shared design token system, layout components, and the base Astro application shell.
View demo →Specifies the agent messaging contracts and event schemas that connect pipeline stages. Defines typed message envelopes, routing rules, and observability hooks shared across the ecosystem.
View demo →Implements the RAG pipeline — chunking, embedding, vector storage, and ranked retrieval. Consumes protocol contracts to emit telemetry spans and expose a typed query interface over the knowledge corpus.
View demo →See it in action
End-to-end examples showing how the four repos compose into working AI pipelines.
Browse Examples