Engineering Documentation

System Manual & CLI Specification

Configuration specifications for the Specter Go daemon, SQLite memory schema definitions, and local Ollama initialization protocols.

1. Specter Daemon Configuration
CLI Reference

The Specter daemon (compiled static Go binary) collects local deterministic telemetry. It is strictly configured via CLI flags or a config.yaml manifest.

$ specterd --help
Usage of specterd:
  -config string
        Path to config.yaml (default "/etc/axiom/specter.yaml")
  -db string
        SQLite database path (default "~/.axiomos/telemetry.db")
  -poll-interval duration
        Telemetry polling interval (default 1s)
  -module-browser bool
        Enable browser history tracking (default true)
  -module-shell bool
        Enable bash/zsh command parsing (default true)
  -module-screen bool
        Enable periodic screen OCR [HEAVY] (default false)
  -log-level string
        Log level: debug, info, warn, error (default "info")
Performance NoticeEnabling -module-screen invokes the local Tesseract binary and consumes noticeable CPU cycles. Use with caution during battery-operated laptop sessions.
2. Memory Layer (SQLite Schema)
SQL Spec

AXIOM relies on a deterministic memory layer to store context before AI evaluation. The schema ensures strict typing for telemetry events and audit trails.

// memory.sql
CREATE TABLE telemetry_events (
    id TEXT PRIMARY KEY,
    timestamp DATETIME DEFAULT CURRENT_TIMESTAMP,
    source TEXT NOT NULL, -- e.g., 'browser', 'shell', 'window_manager'
    payload JSON NOT NULL,
    processed BOOLEAN DEFAULT 0
);

CREATE TABLE behavior_evaluations (
    id TEXT PRIMARY KEY,
    event_id TEXT,
    axis_1_score REAL, -- Current Role Duties
    axis_2_score REAL, -- Personal Goal Alignment
    axis_3_score REAL, -- General Wellbeing
    intent_label TEXT,
    roast_generated BOOLEAN DEFAULT 0,
    FOREIGN KEY(event_id) REFERENCES telemetry_events(id)
);

CREATE INDEX idx_unprocessed_events ON telemetry_events(timestamp) WHERE processed = 0;
3. Local Ollama Initialization & Model Pull
Ollama Setup

AXIOM is powered by local quantized models via Ollama. We use a 3-billion parameter Qwen 2.5 model for rapid, low-thermal background evaluation.

Pulling the Model

$ ollama pull qwen2.5:3b
pulling manifest
pulling 8a3423... 100% ▕████████████████████████████████████████▏ 1.7 GB
pulling 4a1323... 100% ▕████████████████████████████████████████▏ 12 KB
verifying sha256 digest
writing manifest
removing any unused layers
success

Starting the Local Inference Server

# start-inference.sh
#!/bin/bash
export OLLAMA_HOST="127.0.0.1:11434"
export OLLAMA_MAX_VRAM="4G"

echo "[*] Starting Ollama server daemon..."
systemctl start ollama

echo "[*] Pre-loading Qwen 2.5 context..."
curl -X POST http://$OLLAMA_HOST/api/generate -d '{
  "model": "qwen2.5:3b",
  "prompt": "SYSTEM: Initialize AXIOM evaluation protocol.",
  "stream": false
}'

echo "[+] Inference layer online."