v0.2 — open source platform

IoT +
GenAI
EdgeAI

One stack. Three layers. Zero compromise.

p4n4 is a Docker Compose platform that wires together Node-RED, InfluxDB, Grafana, Ollama, Letta, n8n, and Edge Impulse into a single self-hosted stack — from Raspberry Pi to GPU server.

↓ Get Started View on GitHub

bash — p4n4 init

$ p4n4 init my-factory-stack

─── Configuration ──────────────────────────

? InfluxDB organisation: ming

? Timezone: UTC

? InfluxDB admin password: (auto-generated)

? Grafana admin password: (auto-generated)

─── Generating secrets ─────────────────────

✓ InfluxDB token ✓ Grafana password

✓ Project scaffolded at ./my-factory-stack

$ p4n4 up

✓ mosquitto healthy :1883

✓ influxdb healthy :8086

✓ node-red healthy :1880

✓ grafana healthy :3000

Architecture

Three stacks.
One network.

Built on the proven MING stack — Mosquitto, InfluxDB, Node-RED, Grafana — and extended with a GenAI layer and Edge AI inference. All services share a Docker bridge network, with Node-RED at the intersection wiring sensors, databases, and AI together.

Mosquitto :1883

Node-RED :1880

InfluxDB :8086

Grafana :3000

⟷

Ollama :11434

Letta :8283

n8n :5678

⟷

ei-runner :8080

Visual Flow Orchestration

Visual flow engine with bidirectional data movement, conditional logic, 400+ community nodes, and direct AI call-outs. Everything Telegraf does, and then some.

flow-based programming

Persistent AI Agents

Letta agents maintain core, archival, and recall memory across sessions. Your Site Monitor agent remembers every anomaly, every maintenance event, every operator conversation.

letta / memgpt

TinyML at the Sensor

Edge Impulse inference runs as a Docker container with an HTTP API. Classify vibration, audio, and images in <5ms before data ever reaches the broker.

edge impulse / tflite

Fully Self-Hosted

Zero cloud dependency at runtime. Models are pre-downloaded. Secrets stay local. Works air-gapped. Runs on a Raspberry Pi 5 or a rack-mount GPU server equally well.

on-premise

Composable by Design

Deploy only the IoT stack today. Add GenAI next month. Slot in Edge Impulse models as sensors are deployed. Each stack is independently manageable.

docker compose

Template Registry

Pull industry-specific configurations from Git. Publish your own. Short-name resolution through org indexes. OTA template upgrades with merge safety.

git-backed

Built on MING

The proven IoT foundation.
Now AI-native.

MING — Mosquitto, InfluxDB, Node-RED, Grafana — is a battle-tested open-source IoT stack used across industrial, agricultural, and smart-building deployments worldwide. p4n4 takes MING as its core and extends it with a complete GenAI layer and on-device Edge AI.

Mosquitto

MQTT Broker

Eclipse Mosquitto handles all device messaging. Publish/subscribe at scale, TLS-encrypted, ACL-controlled topic namespaces per site and device type.

InfluxDB

Time-Series Store

Purpose-built for sensor telemetry. Flux query language, data retention policies, and a REST API consumed by Grafana, Node-RED, and the full AI layer.

Node-RED

Flow Orchestrator

Visual, bidirectional flow engine. 400+ community nodes. Replaces Telegraf with full conditional logic, device actuation, and direct AI call-outs — all in a browser.

Grafana

Dashboards & Alerts

Real-time dashboards and unified alerting. Alert webhooks feed into n8n for AI-enriched notifications — plain-English anomaly summaries before they hit your inbox.

IoTStack vs p4n4

Why p4n4 over TIGUITTO?

TIGUITTO is a solid starting point. p4n4 is where IoT projects go when they need intelligence, not just telemetry. The IoT stack is identical — what changes is everything on top of it.

Capability	TIGUITTO / IoTStack	p4n4
Data ingestion	Telegraf metrics-scraping agent only	Node-RED visual, bidirectional flow engine
MQTT broker	Eclipse Mosquitto	Eclipse Mosquitto
Time-series DB	InfluxDB	InfluxDB
Visualisation	Grafana	Grafana
Conditional logic	Limited Telegraf processors only	Full Node-RED function nodes + JS
Device actuation	✗	✓ MQTT out, HTTP out
Protocol bridging	MQTT only	MQTT, HTTP, WebSocket, Modbus, OPC-UA…
AI integration	✗	✓ Ollama, Letta, n8n
Workflow automation	✗	✓ n8n — webhook, cron, AI chains
Agent memory	✗	✓ Letta / MemGPT — persistent across sessions
Local LLM inference	✗	✓ Ollama — phi3, mistral, llama3
Visual programming	✗	✓ Node-RED browser editor
Edge ML inference	✗	✓ Edge Impulse — <5ms, Docker container
Edge deployment	✓ Pi compatible	✓ Pi 5 + optional GPU acceleration

CLI Tool

p4n4 init.
That's it.

One interactive wizard scaffolds your entire project — compose files, configs, secrets, base flows, dashboards, and EI model wiring. All version-controlled, all idempotent.

p4n4 init

Interactive wizard. Scaffolds a complete project directory with secrets, configs, and base flows.

p4n4 template

Pull templates from Git or org indexes. Push your own. Upgrade with merge safety.

p4n4 up

Start the IoT stack. Add --ai or --edge to bring up additional stacks.

p4n4 status

Unified health view across all stacks and services with uptime and port listing.

p4n4 ei

Deploy an Edge Impulse model and run inference. Publishes results to MQTT.

p4n4 secret

Rotate secrets in .env with new random values. Shows a confirmation table before writing.

p4n4 validate

Pre-flight checks: Docker version, secrets, YAML validity, port conflicts, EI model presence.

p4n4 init — interactive wizard

$ p4n4 init
──────────────────────────────────
? Project name: my-factory-stack
? Site ID: factory-floor-1

─── Stacks ──────────────────────
? IoT stack? Y
? GenAI stack? y
? Edge stack? y

─── Secrets ─────────────────────
✓ MQTT password generated
✓ InfluxDB token generated
✓ n8n encryption key generated

✓ Scaffolded at ./my-factory-stack

Template Registry

Pull. Customise.
Deploy. Share.

Templates are Git repositories with a p4n4-template.toml manifest. Any Git host works. Org indexes add short-name resolution for teams.

01 — FIND

Discover a template

Search the community index or your organisation's private index.

p4n4 template search manufacturing

02 — APPLY

Apply to your project

Scaffolds a project directory with pre-configured stacks, flows, and dashboards.

p4n4 template apply factory-baseline

03 — RUN

Validate and start

Pre-flight checks, then bring up the stack.

p4n4 validate && p4n4 up

04 — SHARE

Publish your own

Secrets are scrubbed automatically. Tag a version. Register in your org index.

p4n4 template push origin --tag 1.0.0

Name Resolution

Short name (org-scoped)

acme/factory-baseline

Resolved via the acme org index registered in ~/.p4n4/config.toml. Version defaults to latest.

Full Git URL

github.com/acme/[email protected]

Pulls directly from any Git host. Supports HTTPS and SSH. Pin to any branch, tag, or commit.

Local path

./my-local-template

Use a local directory as a template. Ideal for developing and testing templates before publishing.

Edge AI

Two AI layers.
One data fabric.

Edge Impulse handles raw-signal TinyML at sub-100ms latency. Ollama and Letta handle natural language reasoning on aggregated context. They're complementary, not redundant.

Edge Impulse Inference

Raw signal → DSP → TFLite classifier → label + anomaly score

<5ms

Mosquitto + Node-RED

MQTT broker + flow engine bridges raw telemetry and EI results

<50ms

InfluxDB

Time-series store for raw telemetry and EI classification labels

persistent

Ollama LLM

Explain anomalies in plain English. phi3:mini to llama3:8b.

~2–8s

Letta Agents

Persistent agent memory. Accumulates fault history. Operator-facing chatbot.

stateful

MQTT inference flow

# Publish sensor data → sensors/raw
{
"device": "motor-m003",
"values": [0.12, -0.05, 1.01, 0.33]
}
─────────────────────────────────
# Result on → inference/results
{
"label": "normal",
"confidence": 0.964,
"anomaly_score": 0.18,
"latency_ms": 4.2,
"mode": "model"
}

Node-RED: if fault > 0.7 → Ollama
─────────────────────────────────
→ "Motor M003 shows early-stage bearing fault signature at 3.2 kHz. Last maintenance: 47 days ago. Recommend inspection within 72h."

Supported Devices

Runs on the hardware
you already have.

p4n4 targets ARM64 and x86-64. If it runs Docker and Docker Compose, it runs p4n4. The IoT stack runs comfortably on 1 GB RAM devices. Add the GenAI stack on 4 GB+ boards or any GPU server.

Raspberry Pi

Raspberry Pi 5

ARM Cortex-A76 · 4–8 GB RAM · PCIe 2.0

IoT GenAI Edge

Recommended. Runs all three stacks. PCIe slot supports NVMe storage.

Raspberry Pi 4

ARM Cortex-A72 · 2–8 GB RAM · USB 3.0

IoT GenAI Edge

4 GB+ model recommended for GenAI stack with lightweight models (phi3:mini).

Raspberry Pi 3B+

ARM Cortex-A53 · 1 GB RAM

IoT Edge

IoT + Edge stacks only. GenAI stack requires 4 GB+.

Raspberry Pi Zero 2 W

ARM Cortex-A53 · 512 MB RAM · Wi-Fi

Edge

Edge Impulse runner only. Ideal as a dedicated TinyML inference node.

NVIDIA Jetson

Jetson Orin NX / AGX

ARM Cortex-A78 · 8–64 GB · CUDA Ampere

IoT GenAI Edge

GPU-accelerated Ollama inference. Run 13B+ models on the edge. Best-in-class for Edge AI.

Jetson Nano (4 GB)

ARM Cortex-A57 · 4 GB · 128-core Maxwell GPU

IoT GenAI Edge

Use NVIDIA L4T base images. Ollama runs on CPU; GPU-accelerated EI inference works natively.

Jetson Xavier NX

ARM Carmel · 8 GB · 384-core Volta GPU

IoT GenAI Edge

Tensor Cores enable fast LLM inference. Strong choice for industrial vision pipelines.

Banana Pi & Rockchip

Banana Pi BPI-M7

RK3588 · 8–32 GB · NPU 6 TOPS

IoT GenAI Edge

Onboard NPU accelerates Edge Impulse models. PCIe 3.0 for NVMe storage.

Banana Pi BPI-M5 Pro

RK3576 · 4–16 GB · NPU 6 TOPS

IoT GenAI Edge

Cost-effective RK3576 board. Runs all stacks. Good Pi 5 alternative.

Rock 5B / Orange Pi 5 Plus

RK3588 · 4–32 GB · NPU 6 TOPS

IoT GenAI Edge

RK3588 NPU can run RKLLM for local LLM inference. Use arm64 Docker images.

x86-64 Servers & Mini PCs

GPU Workstation / Server

x86-64 · NVIDIA RTX / A-series GPU

IoT GenAI Edge

Run 70B+ models with Ollama GPU offloading. Central hub for multi-site deployments.

Intel NUC / Beelink Mini PC

x86-64 · 8–32 GB RAM · Intel iGPU

IoT GenAI Edge

Compact, low-power on-premise hub. 16 GB+ recommended for GenAI stack.

Any Linux VPS / VM

x86-64 · 4 GB+ RAM · Ubuntu / Debian

IoT GenAI

Ideal for remote deployments and CI/CD staging. Edge stack requires hardware sensor access.

ARM64 & x86-64 — all Docker images are multi-arch

1 GB minimum for IoT-only stack · 4 GB+ for GenAI stack

Docker 24+ and Docker Compose v2 required

Air-gapped operation supported — no cloud dependency at runtime

IoT + GenAI EdgeAI

Three stacks.One network.

The proven IoT foundation.Now AI-native.

Why p4n4 over TIGUITTO?

p4n4 init.That's it.

Pull. Customise.Deploy. Share.

Two AI layers.One data fabric.

Runs on the hardwareyou already have.

Up in five minutes.

IoT +
GenAI
EdgeAI

Three stacks.
One network.

The proven IoT foundation.
Now AI-native.

p4n4 init.
That's it.

Pull. Customise.
Deploy. Share.

Two AI layers.
One data fabric.

Runs on the hardware
you already have.