Native Agent Language

Graph-based intermediate representation optimized for AI comprehension.
Verifiable semantics, native performance, and human-in-the-loop validation.

The Fundamental Shift

Traditional development: AI assists humans in writing human-readable code
NAL: Humans describe intent, AI agents write machine-optimized graphs

Traditional Workflow NAL Workflow
Human writes C++/C# code Human writes natural language intent
Compiler reads text → AST AI agents generate semantic graphs
Manual debugging & testing Human verifies intent in semantic IDE
Code must be human-readable Graphs optimized for AI & compiler
Hours to days iteration Faster iteration cycles

What NAL Is (and Isn't)

Graph IR

Graph-Based IR

JSON/JSONL serialized graphs representing game logic. First-class support for ECS, physics, and shaders.

Semantic

Semantic Model

Core primitives: Entity, Component, System, PhysicsDomain, MaterialGraph. Declarative rather than imperative.

Multi-Agent

Multi-Agent System

Specialist fine-tuned SLMs collaborate: ECS Architect, Physics Agent, Shader Agent, Orchestrator.

Verify

Verification Framework

Every node includes metadata: created_by_agent, source_intent_id, type annotations. Full lineage tracking.

Bytecode VM

Bytecode VM

Stack-based virtual machine for hot reload support. Executes NAL in <1 second iterations. JIT compilation via LLVM/Cranelift planned for Phase 4.

Production

Production Tool

Designed for real games, not demos. Planned UE5 integration for AAA workflows.

Not Text

Not a Text Language

NAL is NOT human-readable code. It's intentionally opaque to maximize semantic density.

Human

Not Replacing Humans

Humans become "semantic engineers" verifying intent, not debugging code. Different role, not eliminated.

Specialized

Not General Purpose

NAL is game-dev specialized. Optimized for ECS patterns, not web apps or databases.

Core Concepts

Entity

Unique node ID representing a game object. Lightweight identifier with no data itself.

{
  "entity_id": "player_001",
  "archetype": "PlayerCharacter"
}

Component

Pure data structures attached to entities. No logic, only state.

{
  "Position": {
    "x": "float",
    "y": "float"
  }
}

System

Pure functions querying and transforming component data. Auto-parallelizable.

{
  "system": "ApplyVelocity",
  "query": ["Position", "Velocity"],
  "transform": "..."
}

PhysicsDomain

Declarative physics properties: constraints, materials, collision rules.

{
  "physics": {
    "gravity": -9.8,
    "friction": 0.3
  }
}

MaterialGraph

Shader graph definitions compiled to HLSL/MSL/SPIR-V.

{
  "material": "PBR",
  "nodes": [...]
}

Metadata

Every node tracks creation agent, source intent, and type information.

{
  "created_by_agent": "ECS_Architect",
  "source_intent_id": "player_v1"
}

NAL Example: Player Movement

A simple player controller in NAL graph format

{
  "metadata": {
    "name": "PlayerController",
    "version": "1.0.0",
    "created_by_agent": "ECS_Architect",
    "source_intent_id": "player_movement_basic",
    "timestamp": "2025-12-28T00:00:00Z"
  },
  "components": {
    "Position": {
      "x": { "type": "float", "default": 0.0 },
      "y": { "type": "float", "default": 0.0 }
    },
    "Velocity": {
      "dx": { "type": "float", "default": 0.0 },
      "dy": { "type": "float", "default": 0.0 }
    },
    "Player": {
      "speed": { "type": "float", "default": 200.0 },
      "jump_force": { "type": "float", "default": 400.0 }
    }
  },
  "systems": {
    "ApplyVelocity": {
      "query": ["Position", "Velocity"],
      "execution_order": 10,
      "transform": {
        "Position.x": "Position.x + Velocity.dx * DeltaTime",
        "Position.y": "Position.y + Velocity.dy * DeltaTime"
      },
      "metadata": {
        "created_by_agent": "ECS_Architect",
        "source_intent_id": "basic_movement"
      }
    },
    "PlayerInput": {
      "query": ["Player", "Velocity"],
      "execution_order": 5,
      "inputs": ["keyboard"],
      "transform": {
        "Velocity.dx": "if KeyPressed(Left) then -Player.speed else if KeyPressed(Right) then Player.speed else 0",
        "Velocity.dy": "if KeyPressed(Jump) and OnGround then Player.jump_force else Velocity.dy"
      },
      "metadata": {
        "created_by_agent": "ECS_Architect",
        "source_intent_id": "player_input_handling"
      }
    }
  },
  "entities": [
    {
      "id": "player_001",
      "components": ["Position", "Velocity", "Player"],
      "metadata": {
        "archetype": "PlayerCharacter",
        "created_by_agent": "ECS_Architect"
      }
    }
  ]
}

Why NAL Works

Semantic

Semantic Density

Every token carries maximal semantic information. AI agents can reason about entire game systems within LLM context windows.

Verify

Formal Verification

Type systems and constraint checking at compile time. Catch bugs before runtime through static analysis.

Agents

Specialist Agents

Fine-tuned SLMs excel in their domain. ECS Architect understands entity patterns. Physics Agent knows constraints.

Graph

Graph Visualization

Semantic IDE shows intent graphs, not text. Humans verify "why" not "how". See which agent created each node.

Performance

Native Performance

Optimized interpreter runs games at 60fps. LLVM compilation in development for maximum throughput.

Iterate

Rapid Iteration

Intent → Graph → Compile → Play. Streamlined workflow with no manual coding or boilerplate.

Trail

Audit Trail

Full lineage tracking from human intent to compiled code. Every decision traceable to its origin.

ECS

ECS-Native

First-class ECS support. Compiler guarantees system purity, data access correctness, and automatic parallelization.

Physics

Declarative Physics

Describe physics properties, not implementation. Compiler chooses optimal physics engine and settings.

Multi-Agent Architecture

Specialist agents collaborate through A2A protocol

Orchestrator

Orchestrator Agent

Role: Workflow management, task decomposition, agent coordination

Status: Planned for Phase 3 (fine-tuned SLM)

ECS

ECS Architect Agent

Role: Entity-Component-System design, archetype optimization

Status: Prototype complete (92% success on test cases)

Physics

Physics Agent

Role: Physics simulation, constraint solving, material properties

Status: Planned for Phase 3 (fine-tuned SLM)

Shader

Shader Agent

Role: Material graphs, shader compilation, visual effects

Status: Planned for Phase 3 (fine-tuned SLM)

Verify

Static Analyzer

Role: Game design validation, balance analysis, performance prediction

Status: Planned for Phase 3 (integrated in Harmonic IDE)

RAG

Example Library

Role: Retrieval system for NAL patterns and game templates

Status: 93 examples indexed, expanding in Phase 2-3

NAL vs Traditional Approaches

Feature Traditional C++ AI Copilot NAL
Code Format Text files (.cpp) Text files (.cpp) JSON graphs (.nal.json)
Readability Human-readable Human-readable AI-optimized (opaque)
Authoring Humans write code AI assists humans AI generates from intent
Debugging Manual code debugging Manual code debugging Semantic verification
Performance Native (C++ compiler) Native (C++ compiler) Native (Rust/LLVM)
Type Safety Compile-time Compile-time Compile-time + metadata
Lineage Tracking None Comments only Full metadata trail
ECS Support Library-based Library-based Language primitive

NAL + Harmonic IDE Roadmap

From JSON graphs to production-ready development environment

✅ Phase 1: Foundation (Months 1-4)

Focus: Stable Resonance Engine

  • ✓ JSON/JSONL NAL parser
  • ✓ Runtime execution in engine
  • ⏳ Example gallery (5+ games)
  • ⏳ Documentation & open source launch

📋 Phase 2: ANL Revolution (Months 5-8)

Focus: NAL v2 Compiler + Harmonic Alpha

  • ○ NAL v2 syntax (entity, component, system keywords)
  • ○ Lexer, parser, AST generation
  • ○ Graph IR with optimization passes
  • ○ Stack-based VM + bytecode
  • ○ Harmonic IDE alpha (Tauri + Monaco)
  • ○ Visual node editor (Blueprint-style)
  • ○ Hot reload in <1 second

📋 Phase 3: AI-Native Features (Months 9-12)

Focus: Fine-tuned SLMs + Harmonic Beta

  • ○ Natural language → NAL (fine-tuned SLM)
  • ○ Local AI agents (runs offline, privacy-first)
  • ○ Static analyzer (catches design bugs)
  • ○ Visual debugger & entity inspector
  • ○ Behavior tree DSL & visual editor
  • ○ NAL standard library (20+ modules)
  • ○ Harmonic Beta launch ($19-49/mo)

📋 Phase 4: Escape Velocity (Months 13-16)

Focus: Production-ready + Marketplace

  • ○ NAL VM JIT compilation (LLVM/Cranelift)
  • ○ Performance optimization (≥ Bevy speeds)
  • ○ Plugin API & marketplace
  • ○ Asset store (sprites, sounds, templates)
  • ○ Educational content & certification
  • ○ Conference talks & press coverage

Harmonic IDE: The Future of Game Development

Purpose-built IDE launching in Phase 2 (Months 5-8)

Local AI Agents

Fine-tuned SLMs run on your machine (no cloud, no API costs). Privacy-first, offline-capable. Generate NAL from natural language descriptions.

Hot Reload

Edit NAL code, save, see changes in <1 second. No game restart. State preserved across reloads. 10x faster than Unity/Godot.

Visual Node Editor

Blueprint-style visual scripting that generates NAL code. Drag-and-drop entities, components, systems. Round-trip: visual ↔ NAL.

Game-Aware Compiler

Catches game design bugs ("Boss HP too high for player DPS"), not just code bugs. Balance analysis, pacing suggestions, performance predictions.

Pricing (Beta Launch)

Indie: $19/mo (1 seat, basic AI)
Studio: $49/mo/seat (5+ seats, advanced AI)
Enterprise: Custom pricing

14-Day Free Trial

Try Harmonic IDE risk-free. No credit card required. Full feature access during trial period. Alpha users get lifetime discounts.

Explore the Future of Game Development

NAL represents a fundamental shift in how games are created.

Contact Us Explore the Engine Meet Rezzy