Sovereign Command Center
A local-first AI development platform — multi-model orchestration on your own hardware, behind a six-gate safety pipeline.
Closed-source by design — the license and ecosystem are the moat. Architecture shown here; a technical write-up on the safety pipeline is in the works.
The problem
AI coding assistants lock teams into cloud SaaS with per-token costs, vendor lock-in, and data-privacy risk — a non-starter for proprietary codebases that can't be shipped to a third party.
What I built
- An orchestrator that routes between local Ollama models and optional cloud escalation, with per-org spend caps and cost estimation
- A six-stage code-safety pipeline: Crucible (Docker sandbox test) → Burn Book anti-pattern detection → review agent → approval token → commit
- A vector-backed Vault that indexes the whole workspace via AST analysis (ts-morph) for repo-wide context
- Ed25519 org-bound licensing and a privacy-first referral engine (HMAC contact matching), covered by 88 tests
- An MCP tool server that exposes the platform's capabilities to agents
Architecture
An npm-workspaces monorepo. A React 18 + Vite operator UI talks to an Express + Mongoose API. Local services are orchestrated with Docker — MongoDB, Ollama for LLM inference, ComfyUI for image generation, and an MCP server. The UI uses a Monaco editor and Graphology + Sigma for graph visualization; Zod validates throughout.
Scale & metrics
Outcome
Modern LLM tooling that never leaves the developer's machine — sold as a one-time license rather than a subscription. Demonstrates AI-era depth: multi-model orchestration, safety-gated code generation, and licensing, all built rather than bought.
Want something like this built for your business?
Fractional & project engagements for small, growing teams — now booking.