← Back to the map
The Core · CentraIn progress

The Brain

Local-first, event-driven core that every project plugs into.

Docker ComposeFastAPIPostgres + pgvectorTimescaleDBNATS JetStreamMQTT (Mosquitto)RedisMinIOOllamaTailscaleCaddyAuthentik
23%complete
Current phaseIn progressS1

Local AI stack

Prove the core premise: capable AI on your own hardware with no internet. This is the fastest motivating win and the model backend every project will call.

0%
View all phases →

The always-on brain: local AI, a durable event bus, a self-describing device registry, and a power-cut-aware health monitor. It runs on the laptop (Intel i7 + RTX 4060) today and migrates to a dedicated NAS later — and because every service is containerized, that migration is a copy-paste rather than a rebuild. Centra is not a project you finish; it is the ground every other project stands on.

01

Architecture

A modular brain: a small always-on core set up once, plus projects that attach as manifest-declared modules you add as you go. The core owns the brain-level work — coordination, memory, reasoning, anticipation, scheduling, notification — and delegates specialized capture/actuation to modules. It does most brain things, not everything. See docs/architecture.md.

Core — always onone-time setup; never a per-project rebuild
NATS JetStream event bus + storePostgres (pgvector + TimescaleDB)Redis cacheMinIO objectsDevice gateway (MQTT · registry · health)
Brain — the AIdoes most brain things; delegates the rest
Orchestrator (local LLM: Qwen3.5-9B / Qwen3-7B)MCP tool layer (modules expose tools)Memory + RAG (pgvector, evolving profiles)Anticipation engine (scheduled + event reasoning)Notifier
Module managermanifest-driven; add / upgrade / remove at runtime
Module manifest (capabilities, events, tools, data, UI, lifecycle)Capability registry (semantic action → connector)Lifecycle hooks (install / upgrade / uninstall)
Modules — the projectsattach as you go; own their domain
Blu · remindersAura · sensingSentry · visionAtlas · knowledgenew ideas → pipeline
Data flow
  1. A module registers via its manifest → capability registry, event subscriptions, and MCP tools are wired in; the core is unchanged.
  2. Devices and modules publish events (MQTT edge → gateway → NATS JetStream) — durable and replayable.
  3. The orchestrator reacts to events and, on a schedule, reasons over shared state (events, telemetry, memory) using module-provided MCP tools.
  4. The anticipation engine predicts likely needs and acts proactively — or asks — then notifies you.
  5. State is written back to the shared data plane so the next decision is better-informed.
02

Phase rail

S0Foundation & runtimeS1Local AI stackS2Data layerS3Event backbone & APIS4AI OrchestratorS5Secure remote accessS6IoT & Home AssistantS7ClientsS8Observability, backup & hardeningS9Expansion & NAS migration
03

Progress log

  • 2026-08-18

    Scaffolded the containerized brain (compose, gateway, edge agent, infra) and pushed to git. Added the power-cut-aware resilience architecture.

  • 2026-08-18

    Rebuilt the hub as a Next.js app (Vercel-ready, centra.krinc.in) with an animated project map, per-project overview pages, and engineered phase pages.

  • 2026-08-18

    Added CLAUDE.md operating manual + per-project folder convention so the AI works directly from this repo against the source of truth (web/content/centra.json).

  • 2026-08-18

    Redesigned the home as a revolving 3D atom (crisp, no hero text; hover pauses + zooms; orbs grow with progress) and added an animated atom logo. Documented Centra's feature set as a limited support assistant (docs/centra-features.md) and shipped a one-shot S1 local-AI bring-up script.

  • 2026-08-18

    S0 complete: Docker Desktop running and the RTX 4060 (driver 610.88, 8 GB) verified inside a container. Started S1 — bringing up the local AI stack (Ollama + Qwen + embeddings + Open WebUI) on the GPU. Home tuned to a clean 2D orbital rotation with 3D orbs; base page has no header/footer.