📄️ Overview
ABI is the open-source AI operating system for enterprise knowledge work. Its architecture mirrors the approach Palantir took with Foundry and AIP, but built entirely in the open: MIT-licensed, self-hosted, and grounded in the same formal ontology standards (BFO/OWL/SPARQL) used in defense, healthcare, and intelligence.
📄️ The ABI Stack
ABI is organized as three open-source Python packages that together constitute an enterprise AI operating system. The runtime layer (naas-abi-core) provides the Engine, all service port interfaces, and the infrastructure adapters. The application layer (naas-abi) adds the built-in agents, the Nexus platform, the base ontologies, and the core module library. The module layer (naas-abi-marketplace) extends the system with community-contributed domain modules, all disabled by default and opted in per deployment. A fourth package, naas-abi-cli, orchestrates the whole stack. All four are MIT-licensed Python packages you install and run on your own infrastructure.
📄️ The Ontology System
The Ontology is the structural core of ABI. It integrates an organization's data, logic, and action capabilities into a formal, machine-readable representation that both humans and AI agents can reason over with precision.
📄️ The Data Plane
ABI's data architecture follows a single philosophy: any data, any compute, any model, on any infrastructure you own. It assembles best-in-class open-source services, each accessible through open protocols, with no proprietary storage format and no cloud dependency. You retain full ownership of every byte, at every layer.
📄️ Interoperability
ABI is built on open protocols at every integration point. Every interface uses a standard that exists independently of ABI: no proprietary SDK required, no lock-in to a particular cloud, identity provider, or model vendor.
📄️ The Runtime
ABI runs on Docker. Every service in the stack is a standard container orchestrated by Docker Compose, with no proprietary Kubernetes substrate and no managed infrastructure required. You operate it with tools you already know.
📄️ The Agent System
ABI's agent architecture is the capstone of the platform agents are Python classes, tools are SPARQL queries or Python functions, routing is vector similarity over registered intent strings, and every agent is exposed via REST, MCP, and CLI simultaneously.