AI Integration
Connect AI assistants to your systems through capabilities, so they can access trusted business data and actions without custom glue code.
Take Me to the Repo
Declare upstream systems in your capability spec with namespace, base URI, authentication, and operation contracts. Expose the same domain as MCP tools and REST resources, so both AI agents and traditional clients use one integration layer.
Use call, steps, and JSONPath mapping in output parameters to return normalized, task-ready payloads instead of raw provider responses. One capability serves both AI and API consumers.
The Naftiko Fleet — six components, all at v1.0.0-alpha3
Spec-Driven Integration (SDI) ties every component to a single declarative YAML spec — authored once, linted by Polychro, executed by Ikanos, authored in Crafter, governed by Warden, orchestrated by Skipper, and documented in Shipyard.
Shipyard
The documentation hub and public front door for the Fleet. Tutorials, concepts, editions. Soon: a hosted Playground and AI-assisted Ask Navi search across the corpus.
Ikanos
The OSS capability engine. Runs a Naftiko spec as a multi-protocol server — REST, MCP, and Skill from the same definition. Apache 2.0.
Polychro
The OSS deterministic AI-era linter for YAML, JSON, and Markdown specs. The new Spectral for SDI. Apache 2.0.
Crafter
The capability builder for VS Code and most AI IDEs. Visual + spec-driven authoring with inline governance and live topology.
Warden
Capability governance and policy enforcement for Backstage. Scorecards, scaffolding, fleet explorer, impact tracing.
Skipper
Fleet-wide orchestration for Kubernetes — across teams, regions, and compliance domains. Continuous compliance and FinOps tagging.
Start small, scale smart
AI integration without the glue code.
Chart your next course
Rightsize AI Context
