The capability Fleet for enterprise AI integration

An open-source, spec-driven integration platform that elevates any public or private API into governed, domain-driven capabilities usable by developers, copilots, and agents. Six components, all at v1.0.0-alpha3.
Land in the Shipyard
Naftiko fleet Naftiko fleet Naftiko fleet

One capability, many protocols

A single Naftiko spec is exposed simultaneously across REST, MCP, and Skill — and soon A2A — from one Ikanos deployment.
REST API
Clean REST endpoints with per-operation path, method, and parameter mapping.
MCP Server
Tools, resources, and prompts for AI copilots and agents via streamable HTTP or stdio.
Agent Skills
Downloadable skill folders with SKILL.md prompt integration for developer agents.
A2A Protocol
Roadmap
Google's Agent-to-Agent protocol for cross-agent tool discovery and execution. Landing Alpha 4 (mid-June 2026).

Surfaces for the tools your teams already use

Crafter (VS Code + AI IDEs)
IntelliSense for capability YAML, inline governance diagnostics with Quick Fix, live topology panel, one-click run/stop, JSONPath and Mustache linting.
Warden (Backstage)
Capability scaffolding from templates, auto-catalog from CRDs/Git, scorecards for Cost/Risk/Velocity pillars, fleet explorer with impact tracing.
Skipper (Kubernetes)
Fleet dashboard with health and uptime, visual spec viewer, structured log streaming with filters, secret injection, continuous compliance.