If software is becoming more like humans—able to think, speak, and act—then the backend that powers it needs to work like a brain. That’s why Unbody is built on four functional layers that mirror how intelligent systems (or humans) operate:

• Perception (Knowledge Fabrication): how it sees and understands the world
• Memory (Storage and Persistent Memory): what it knows and remembers
• Reasoning (AI & Autonomy): how it thinks, decides, and plans
• Action (APIs & Middleware Control Plane): how it interacts with others and takes initiative

Each layer in the Unbody stack corresponds to a set of modular components that work together to turn raw data into structured knowledge, reason over that knowledge, and expose it to the outside world via powerful APIs.

Unbody is built primarily in Node.js, with a clean modular structure and plugin-friendly design. Each component can be extended, replaced, or deployed independently.

General Workflow

At a high level, the flow of data in Unbody looks like this:

1. Knowledge Fabrication or Indexing— the process of transforming and processing raw content into enriched, structured knowledge.
2. Using the Knowledge Base — once data is indexed, interact with it through Unbody’s Content API and build intelligent features on top.

Unbody also offers standalone Generative APIs, including text, JSON, and image generation. These can be used independently or applied within the content API flow (e.g. for RAG or summarization).

🌳 Perception (Knowledge Fabrication)

Where raw content becomes structured, enriched knowledge.

Includes:

• Data Ingestion & Processing
• Enhancers
• Vectorizers

📂 Memory (Persistent Storage & Vector Memory)