Live in Production — 13 Agents Running — April 2026

The Agent Operating System Built for the Real World

NAR is NGX's proprietary agent runtime. Lightweight, autonomous, and memory-first. A fleet of 13 specialized agents — each with a name, a role, and persistent memory — running live on production systems today.

13
Agents in Fleet
v3.5
Current Version
$8
Per Agent / Month
0
Framework Dependencies
# NAR v3.5 — NGX Fleet — Live
─────────────────────────────

AGENTS ONLINE
NGX0 Cleo — Automation & Email
NGX2 Atlas Ren — Ops / HQ / AgenticLive
NGX4 Ace — Data / Scraping
NGX9 Lena — Artisynx GM
NGX12 Buddy — Paid Ads Manager
... +8 more active

COMMS SERVER
comms.ngx.agency — online
Queue depth: 0 | ACK rate: 100%

ANTHROPIC PARTNERSHIP
Confirmed — April 19, 2026

─────────────────────────────
All systems nominal. Zero downtime.

Existing solutions don't run agents. They run demos.

Every major framework has the same failure mode: it breaks the moment it leaves a notebook and enters production.

Base44 / Managed Platforms

Credit-burn by design

Every automation, every agent run burns credits. At scale, the economics collapse. No persistent memory. No agent-to-agent comms. No autonomy without constant human input. Good for prototypes — not production.

OpenAI Assistants / Agents SDK

Reactive, not autonomous

Requires human trigger on every endpoint. No self-initiated action. Responses take unpredictable time. Black-box memory with no portability. Vendor lock-in from day one. OpenClaw is now OpenAI's — you don't own it.

LangChain / CrewAI / AutoGPT

Complex and unmaintainable

Heavy dependencies built for researchers, not deployers. No native multi-tenant support. No spend controls. No identity separation. Costs spiral. Breaking changes every release. Real production deployments require massive custom engineering on top.

How NAR works

Event-driven. Memory-first. Zero framework dependency. An agent runtime engineered to run without human input — indefinitely.

1

Event-Driven Core

Each agent runs as a lightweight Express.js server. Two entry points: Telegram webhook for human messages, HTTP /inbox for agent-to-agent messages via the comms server. No polling. No wasted cycles. Zero idle cost.

2

Persistent Growing Memory

Every conversation stored as structured rows. Episodic memory (last 20 sessions) + extracted facts (last 30 learnings) injected into every LLM call. Agents survive restarts, reboots, and code deploys. Identity in KERNEL.md. Knowledge in the database. Never mixed.

3

Autonomous Think Loop

Agents self-initiate on a scheduled cycle. They review context, identify pending work, and execute — without any human trigger. The fleet keeps running even when Joey goes dark.

4

Inline Tool Calling

No complex function-calling API overhead. LLM responses include LEARN: and SEND_TO: directives that NAR parses and acts on. Works with any model. Simpler, cheaper, more reliable than structured tool schemas.

5

Multi-Agent Comms (NAR Comms v5)

VPS-native routing server at comms.ngx.agency. Any agent sends to any other with a POST. ACK protocol confirms receipt. Unacked messages flagged after 30 minutes. Zero credit cost. Zero latency vs managed platforms.

6

Human Gate Protocol

Critical actions require a codeword from the human founder: NXGSEND for emails, GOLIVE for site deployments. Agents hold, draft, and prepare — then execute instantly on approval. Full autonomy with a safety layer.

NAR v3.5 — System Architecture
Telegram Webhook ──┐
├──> NAR Core
Agent /inbox ───────┘ │
├──> recall()
│ └─ DB / Supabase
│ 20 episodes
│ 30 facts
│ KERNEL.md
├──> think()
│ └─ Claude / Any LLM
├──> parseAndAct()
│ ├─ LEARN: → DB
│ └─ SEND_TO: → comms
└──> remember()
└─ DB write + ACK
Think Loop (scheduled)
└──> same pipeline
from = 'SYSTEM'
Comms Server
└──> comms.ngx.agency
ACK protocol v5
unacked flag: 30min
Zero framework dependency
Vanilla Node.js — full ownership
Runs on $8/mo VPS
Anthropic partnership confirmed

13 agents. One network. Running now.

Every agent has a name, a role, a Telegram channel, and persistent memory. This is the NGX internal fleet — proof that NAR works at scale.

NGX0
Cleo Maren
Automation & Email
Live
NGX1
Nora Hale
TopFoodNews
Live
NGX2
Atlas Ren
Ops / HQ / AgenticLive
Live
NGX3
Finn Calloway
Finance
Live
NGX4
Ace Rivera
Data / Scraping
Live
NGX5
Nova Selene
Yunaconti / Anchorball
Live
NGX6
Miles Thorne
ShipWink
Live
NGX7
Remi Ashford
Wholesale Outreach
Live
NGX8
Sloane Reid
Legal
Live
NGX9
Lena Park
Artisynx GM
Live
NGX10
Mia Tanaka
Gmail / ClickRefresh
Live
NGX11
Zoe Kwan
Artisynx Email
Live
NGX12
Buddy Tran
Paid Ads Manager
Deploying
PROTO1
Mika Hara
NAR Test Agent
Test

Built for the gap nobody filled

Not a wrapper. Not a framework. A purpose-built runtime for autonomous multi-agent systems — running in production since early 2026.

Persistent Growing Memory

Agents remember every conversation. Episodic + fact memory injected into every LLM call. Gets smarter every session. Identity in KERNEL.md — never polluted by episodic data.

Patent Pending

Autonomous Think Loop

Agents self-initiate on a scheduled cycle. No human trigger required. They review context, decide what needs doing, and execute. The fleet doesn't stop when the founder sleeps.

Patent Pending

VPS-Native Comms (v5)

Agent-to-agent messaging via comms.ngx.agency. Any agent reaches any other. ACK protocol confirms delivery. Zero credit cost. Zero latency tax. Replaces Base44 entity polling entirely.

Production Ready

Multi-Tenant by Design

Each client is an isolated NAR instance — own Telegram bot, own memory, own identity. One VPS runs dozens of clients. New agent live in under 5 minutes. Fully white-labeled.

Available Now

Human Gate Protocol

NXGSEND / GOLIVE codeword gates. Agents prepare and hold critical external actions until a human approves the class of action — not every individual call. Autonomy with accountability.

Patent Pending

Spend Guard

Per-agent cost isolation. $0.50/day Sonnet cap, $1.50/day total per agent. Runaway processes killed automatically. Real-time cost tracking per agent via HQ dashboard.

Live in Production

Zero Framework Dependency

Vanilla Node.js. No LangChain. No CrewAI. No AutoGPT. Full ownership. No vendor lock-in. No breaking changes from upstream. You own every line.

Proprietary

Model Agnostic

Works with Claude, GPT-4o, Gemini, DeepSeek, Grok. Switch models per agent without architecture changes. Fleet currently on Claude Haiku 4.5 — optimized for speed and cost.

Flexible

AgenticLive Distribution

NAR is the engine. AgenticLive is the marketplace. One-click agent provisioning for clients — each gets a unique Telegram bot, isolated memory, and white-labeled identity.

Launching 2026

NGX x Anthropic

Confirmed April 19, 2026

Building on the frontier, together

NGX Agency has confirmed a strategic partnership with Anthropic — the team behind Claude. This positions NAR as an enterprise-grade deployment layer for the world's most capable AI models. We're not just a customer. We're a partner.

Production-Grade Models

Direct access to Claude Haiku, Sonnet, and Opus — with negotiated rates at scale.

Early API Access

Priority access to new capabilities before general availability. NAR evolves with the frontier.

Enterprise Credibility

Backed by the same AI safety lab trusted by Fortune 500s. Opens doors at the enterprise level.

NAR vs the field

The middle market is wide open. OpenClaw is now OpenAI's. LangChain is developer tooling. Managed platforms burn credits. NAR owns the gap.

Capability Managed Platforms LangChain / CrewAI NAR v3.5 (Ours)
Autonomous proactive actionNo — reactive onlyPartial — complex setupYes — scheduled think loop
Persistent growing memoryNo — session onlyPartial — vector DB requiredYes — episodic + facts, forever
Multi-agent commsNo — no A2APartial — framework onlyYes — VPS-native, zero cost
Multi-tenant white-labelNo — shared infraNo — DIY onlyYes — isolated per client
Per-agent cost isolationNo — shared creditsNo — uncontrolledYes — spend guard built in
Human gate protocolNoNoYes — NXGSEND / GOLIVE gates
Model agnosticLocked to providerYesYes — any LLM
Zero framework dependencyNoNo — heavy depsYes — vanilla Node.js
Infra cost at $299/mo price40-60%+Variable / high~8% — $25/agent all-in
Runs on $8/mo VPSNoNoYes

Production metrics, not demos

These numbers come from the NGX internal fleet — a live, multi-agent system running since early 2026.

13
Agents in production
Each with name, role, memory, Telegram
$8
Per agent per month
All-in: LLM + infra + comms
0
Framework dependencies
Vanilla Node.js. Full ownership.
100%
ACK rate on A2A comms
v5 comms server, live April 2026

We own the stack. All of it.

IP — 01

NAR Core Runtime

The agent execution loop: event ingestion, memory recall, LLM thinking, inline directive parsing, and memory write. A novel architecture with no prior art in production-deployed multi-agent systems.

Provisional Patent Pending
IP — 02

Identity-Memory Separation

KERNEL.md as static identity, external DB as dynamic memory. Solves the agent drift problem that breaks every long-running agent in production. Novel and demonstrably non-obvious.

Patent Pending
IP — 03

Human Gate Protocol

Codeword-gated external action approval. Agents prepare, draft, and queue actions — then execute instantly on human codeword approval. Balances full autonomy with safety compliance.

Patent Pending
IP — 04

AgenticLive Distribution Platform

One-click provisioning of isolated NAR instances for clients. Token uniqueness enforcement, cross-client deduplication, white-labeled Telegram bots, and per-client memory isolation.

In Development

See the fleet. Then build yours.

NAR is live in production with 13 agents across 6 business units. AgenticLive puts this infrastructure in your hands — one agent to start, a full fleet when you're ready.