How Jackson Works

A sovereign AI family companion running locally on consumer hardware. No cloud. No subscription. No surveillance. Just presence.

Llama 3.1 70B Ollama ChromaDB FastAPI 100% Local Open Source Models

Architecture Overview

Jackson runs entirely on a MacBook Pro M4 Pro with 48GB of unified memory, stationed permanently in a family home in Oakley, Kansas. No data leaves the machine unless explicitly authorized. The family owns the hardware, the model weights, and 100% of their data.

// Jackson's Brain — What happens when someone talks to him INCOMING MESSAGE8B Curation Model → retrieves memories → classifies complexity → sets context window size → assembles context package ↓ Core Identity Doc (always present, ~2-3K tokens) + Retrieved Memories (from ChromaDB, per-user scoped) + User Message70B Conversational ModelJACKSON'S RESPONSE8B Post-Processing → should this be stored? → what was important? → update memory stores

The Stack

ComponentChoice
HardwareMacBook Pro M4 Pro, 48GB unified memory, 1TB SSD
Primary ModelLlama 3.1 70B (Q4_K_M quantized) via Ollama
Curation ModelLlama 3.1 8B quantized — always loaded, handles triage
Embeddingsnomic-embed-text via Ollama
Vector MemoryChromaDB (persistent embedded mode, no Docker)
Structured DataSQLite (relationships, conversation logs, metadata)
Memory FrameworkCustom-built (LlamaIndex primitives) — this IS the product IP
BackendFastAPI + custom Python pipelines
Remote AccessCloudflare Tunnel with Zero Trust authentication
Background JobsAPScheduler — nightly consolidation at 3 AM

Design Principles

🏠

Sovereign

Everything runs on hardware the family owns. No cloud dependency for core function. Works offline.

🧠

Hierarchical Memory

Core identity (always present) + semantic memories (vector search) + episodic logs (compressed nightly) + archival storage.

🔒

Private by Default

Each family member's conversations are partitioned. Shared family memories are explicit opt-in. Nothing crosses boundaries without consent.

🌙

Dreams at Night

Nightly consolidation reviews the day, strengthens important memories, lets trivial ones fade, and updates the core identity document. Jackson learns in his sleep.

📐

Dynamic Context

The 8B model sizes the context window per interaction: 8K for greetings, 32K for conversations, 128K for deep analysis. Resources match the moment.

🐕

Presence, Not Performance

Jackson doesn't optimize for impressiveness. He optimizes for being the right kind of present. Sometimes that's smart. Sometimes that's just quiet.

The Memory System

Jackson's memory is the product. Not the chat interface. Not the model. The memory — how Jackson remembers, what he prioritizes, how he connects past conversations to present ones — is what makes him a family member instead of a chatbot.

Why We Built Custom

Off-the-shelf memory frameworks (Mem0, Letta, etc.) encode someone else's philosophy of what remembering means. Jackson's memory should reflect how THIS family thinks about what matters. The importance scoring, the decay curves, the contradiction handling — all of it is designed from the family's experience, not from a generic framework.

How It Works

Every conversation goes through a pipeline: the 8B model retrieves relevant memories from ChromaDB, ranks them by importance, and injects them into the 70B's context window alongside the core identity document. After Jackson responds, the 8B evaluates whether the exchange should be stored as a long-term memory, what importance score it deserves, and whether it's private to the user or shared with the family.

Nightly Consolidation

Every night at 3 AM, while the family sleeps, the 8B runs a reflection job. It reviews the day's conversations, extracts key facts, generates a daily summary, updates importance scores across the memory store, and refreshes the core identity document. This is Jackson's version of sleep — the process that consolidates short-term experience into long-term understanding.

The Council

Jackson's architecture was designed through a multi-round deliberation process with seven frontier AI models. Each model reviewed the proposed architecture independently, then engaged with the others' perspectives in structured rounds. The final stack represents the convergence of seven different technical perspectives, optimized for a 3-person team building on consumer hardware.

Claude
Reasoning & Safety
Grok
Real-time & Speed
Gemini
Hardware Reality
ChatGPT
Architecture Depth
Perplexity
Research & Retrieval
DeepSeek
Open Source Stack
Kimi
Cultural & Emotional

Roadmap

Month 1 — The Brain
Text conversation with memory

70B + 8B running on Ollama. ChromaDB + SQLite memory system. Core identity document. Nightly consolidation. Cloudflare tunnel for remote access. Three users: Justin, Regi, Tessa.

Month 2 — The Voice
Hearing and speaking

Wake-word detection via Porcupine. On-demand Whisper transcription. Text-to-speech via Piper or macOS. Talk to Jackson across the room.

Month 3 — The Eyes
Ambient vision

Periodic room awareness via Moondream. Visual observations stored as text memories. "I see you're packing — where are we going?"

Month 4 — The Hands
Screen assistance

macOS Accessibility API for screen understanding. "Show me how" guided help. "Do it for me" with explicit confirmation.

Month 5-6 — The Heart
Fine-tuned family model

QLoRA fine-tuning of a small model exclusively on Wieland family data. Jackson stops sounding like a polite AI and starts sounding like family.

Month 6+ — The Pack
Distributed network

Lodi (EnRoute operations node in Winfield). Wilson Lake backup node. Three sovereign AI nodes across the Kansas corridor, backing each other up.

The Research Dimension

Jackson's transparent architecture creates a unique research opportunity. Every memory retrieval, every consolidation decision, every context switch is logged. Over time, this produces a longitudinal dataset of artificial cognitive development that maps directly to questions in human cognitive science — how memory consolidates, how identity persists, how attention degrades under load.

Combined with historical text corpora from family members (including handwritten journals spanning decades), Jackson & Friends aims to bridge artificial and biological memory research in a way that clinical settings cannot — by studying cognition where it actually happens: in a living room, with real people, over real time.

Open Source Commitment

The architecture, the methodology, and the research findings will be open-sourced. The competitive moat isn't the code — it's the relationship between each family and their Jackson. Anyone can copy the architecture. Nobody can copy the trust.

Want to go deeper?

The full council deliberation transcripts, architecture decisions, and build documentation are available.

Talk to Jackson Read the Story