`n

RiftbornAI Documentation

The first AI that builds your game for you. Directly inside Unreal Engine. Not a chatbot. Not code autocomplete. A real in-editor AI that generates levels, blueprints, abilities, UI, AI trees, and entire game systems from plain English.

320K
Lines of Code
702
Editor Tools
12
Cognitive Systems
UE 5.7
Native Integration
🧠

The NPC Brain: 12 Cognitive Systems

Not scripted behavior trees. Not GPT wrappers. 10,000 lines of Python implementing real cognitive architecture: causal world modeling, intrinsic motivation (curiosity-driven behavior), goal hierarchies, self-modeling, adversarial competition, and continuous learning. NPCs that actually think.

πŸ”’

Your IP Stays Yours

No code leaves your machine. No project files shared. No secrets leaked. AES-256 encryption on all communications. Your assets, your game, your intellectual property β€” protected.

The NPC Brain Architecture

RiftbornAI isn't just another LLM wrapper. It includes a complete cognitive architecture for NPCs β€” 12 systems that give characters perception, memory, goals, curiosity, and self-awareness.

What This Actually Is

Let's be completely honest about what RiftbornAI is and isn't:

What It IS:

  • A production-quality HTTP bridge server β€” 228K lines of C++ that runs inside Unreal Editor
  • 702 editor tools β€” Spawn actors, create blueprints, generate materials, configure AI, and more
  • An LLM integration layer β€” Claude API (recommended) or Ollama (local)
  • 12 NPC cognitive systems β€” Real perception, memory, goals, curiosity, self-modeling
  • Voice chat NPCs β€” Whisper STT + XTTS neural TTS = real voice conversations
  • A security-first design β€” Rate limiting, RBAC, authentication, audit logging built in
  • A self-repairing system β€” Detects failing tests, generates patches, rewrites C++, rebuilds

What It Is NOT:

  • Not AGI β€” The brain is a cognitive architecture for NPCs, not general intelligence
  • Not magic β€” It executes tools based on LLM interpretation. Quality depends on the model.
  • Not a replacement for knowing UE β€” It accelerates experts. Beginners still need to learn.

The 12 Cognitive Systems

SystemWhat It Does
Causal World ModelNPCs learn cause-effect relationships from observation
Intrinsic MotivationCuriosity-driven behavior β€” NPCs explore novel situations
Epistemic PunishmentLearning from prediction errors β€” wrong guesses hurt
Multi-Drive SystemCompeting needs: hunger, safety, social, curiosity
Lossy CompressionMemory consolidation β€” compress experiences into rules
Living WorldTime of day, weather, location awareness
Goal HierarchyDays β†’ Hours β†’ Minutes β†’ Seconds goal decomposition
Self-ModelNPCs know their own skills, weaknesses, limits
Adversarial CompetitionScarce resources, NPC vs NPC competition
Continuous LearningPhysics intuition β€” predict object behavior
Permanent DamageInjuries persist, affect capabilities
Cognition APIUnified interface to all cognitive state

Self-Repair: The Brain Rewrites Itself

πŸ”§

This Is Real Self-Modifying Code

When tests fail, the system doesn't just report errors β€” it fixes them. It reads C++ source files, replaces broken code with working patches, triggers Unreal Build Tool, and validates the fix. No human intervention required.

The Self-Repair Loop

Autonomous Repair Pipeline
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                    TEST GATE FAILS                          β”‚
β”‚         "Project.TDM.Logic.ApplyKillLogic FAILED"           β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                      β”‚
                                      β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚              BUG PATTERN DETECTION                          β”‚
β”‚    Analyze failure signature β†’ Match known bug patterns     β”‚
β”‚    Result: "score_not_updated" detected                     β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                      β”‚
                    β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
                    β–Ό                                   β–Ό
        β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”               β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
        β”‚   PATCH CACHE     β”‚               β”‚   LLM REPAIR      β”‚
        β”‚ (Trusted Fixes)   β”‚               β”‚ (Generate New)    β”‚
        β”‚                   β”‚               β”‚                   β”‚
        β”‚ 3+ successful     β”‚               β”‚ Claude analyzes   β”‚
        β”‚ uses = promoted   β”‚               β”‚ code, generates   β”‚
        β”‚ to "trusted"      β”‚               β”‚ fix, adds to      β”‚
        β”‚                   β”‚               β”‚ cache             β”‚
        β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜               β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                  β”‚                                   β”‚
                  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                    β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                 APPLY PATCH TO C++                          β”‚
β”‚                                                             β”‚
β”‚  TeamDeathmatchLogic.cpp:                                   β”‚
β”‚  - // BUG: GameState->AddTeamScore(KillerPS->GetTeam(), 1); β”‚
β”‚  + GameState->AddTeamScore(KillerPS->GetTeam(), 1);         β”‚
β”‚                                                             β”‚
β”‚  path.write_text(new_content, encoding='utf-8')             β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                      β”‚
                                      β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚              REBUILD VIA UBT                                β”‚
β”‚         Build.bat testEditor Win64 Development              β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                      β”‚
                                      β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚              RE-RUN TEST GATE                               β”‚
β”‚         All tests pass β†’ Patch promoted to "trusted"        β”‚
β”‚         Tests still fail β†’ Revert, try different strategy   β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Bandit Learning

The system uses a multi-armed bandit algorithm (UCB1) to learn which repair strategies work best. Each strategy is scored based on success rate, and the system explores vs. exploits intelligently. Patches that succeed 3+ times are promoted to "trusted" status.

The Architecture

System Overview
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                    NPC COGNITIVE BRAIN                       β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”‚
β”‚  β”‚ World Model β”‚  β”‚   Goals     β”‚  β”‚  Learning Systems   β”‚  β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                              β”‚
                              β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                   RIFTBORN AI (320K lines)                  β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”‚
β”‚  β”‚ HTTP Bridge │──│ Tool System │──│ Design Systems (16) β”‚  β”‚
β”‚  β”‚ (228K C++)  β”‚  β”‚ (702 tools) β”‚  β”‚  GAS/AI/VFX/UI/etc  β”‚  β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β”‚
β”‚                         β”‚                                   β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”   β”‚
β”‚  β”‚              NPC Brain (10K lines Python)            β”‚   β”‚
β”‚  β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”‚   β”‚
β”‚  β”‚  β”‚  World  β”‚ β”‚   Self    β”‚ β”‚  Goal   β”‚ β”‚  Drive  β”‚  β”‚   β”‚
β”‚  β”‚  β”‚  Model  β”‚ β”‚   Model   β”‚ β”‚ Hierarchβ”‚ β”‚  System β”‚  β”‚   β”‚
β”‚  β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β”‚   β”‚
β”‚  β”‚  12 Cognitive Systems - See, Hear, Think, Speak     β”‚   β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜   β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                              β”‚
                              β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                    UNREAL ENGINE 5.7                        β”‚
β”‚         Blueprints Β· Actors Β· Materials Β· Levels            β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Honest Numbers

No inflated metrics. No marketing BS. Here's exactly what exists in the codebase right now. Every number verified by direct file counts.

320K
Total Lines
702
Editor Tools
472
C++ Classes
12
NPC Cognitive Systems

Code Breakdown

ComponentCountStatus
Total Codebase320,186 linesProduction
Plugin C++ Source227,798 linesProduction
Bridge (Python)92,388 linesWorking
NPC Cognitive Systems9,907 linesLearning

Architecture Metrics

MetricCountWhat It Means
C++ Header Files239Public interfaces
C++ Source Files233Implementation
Python Modules104Bridge & cognitive systems
NPC Cognitive Files12npc_*.py brain systems
βœ…

All Numbers Verified

Every stat on this page was counted by grep/find on the actual codebase. No estimates. No rounding up. This is what exists.

⚠️

Early Access Reality Check

This is pre-release software. Some tools work flawlessly. Others need polish. We ship fast and iterate based on real feedback. If you want perfect, wait. If you want powerful, join now.

Installation

Get RiftbornAI running in your Unreal Engine project in under 5 minutes.

Prerequisites

  • Unreal Engine 5.5+ (5.7 recommended for full feature support)
  • Python 3.10+ for bridge scripts
  • Claude API key (recommended) β€” enables cloud brain learning, gets cheaper over time
  • Ollama (alternative) β€” fully local, no cloud dependency, but no learning benefits
  • 16GB RAM minimum, 32GB recommended
  • 8GB+ VRAM for local model inference

Step 1: Download the Plugin

Download the latest release when available (Q1 2026), or join the waitlist for early access:

Download Location
# Join the waitlist at:
https://riftborn-ai.vercel.app

# Early access members receive direct download links

Step 2: Install to Your Project

Copy the RiftbornAI folder to your project's Plugins directory:

Directory Structure
YourProject/
β”œβ”€β”€ Content/
β”œβ”€β”€ Config/
β”œβ”€β”€ Plugins/
β”‚   └── RiftbornAI/           ← Copy here
β”‚       β”œβ”€β”€ RiftbornAI.uplugin
β”‚       β”œβ”€β”€ Source/
β”‚       β”‚   └── RiftbornAI/
β”‚       β”‚       β”œβ”€β”€ Private/
β”‚       β”‚       β”‚   β”œβ”€β”€ DebugBridgeServer.cpp  (214K lines)
β”‚       β”‚       β”‚   β”œβ”€β”€ ClaudeToolUse.cpp
β”‚       β”‚       β”‚   └── Providers/
β”‚       β”‚       └── Public/
β”‚       β”œβ”€β”€ Bridge/
β”‚       └── Content/
└── YourProject.uproject

Step 3: Enable the Plugin

  1. Open your project in Unreal Editor
  2. Go to Edit β†’ Plugins
  3. Search for "RiftbornAI"
  4. Check the box to enable it
  5. Restart the editor when prompted

Step 4: Configure LLM Provider

Option A: Claude API (Recommended)

Claude enables the cloud brain β€” every task teaches the system, building patterns that reduce future LLM calls. Your costs decrease over time.

Environment Variable
# Set your Claude API key
set ANTHROPIC_API_KEY=sk-ant-your-key-here

# Or add to system environment variables for persistence

Option B: Ollama (Local, No Learning)

Fully offline. Your data never leaves your machine. But no cloud brain learning β€” costs stay flat.

Terminal
# Start the Ollama server
ollama serve

# Pull a recommended model
ollama pull qwen2.5-coder:7b
βœ…

You're Ready!

The bridge server starts automatically when Unreal Editor opens. Check the Output Log for "RiftbornAI Debug Bridge active on port 8766".

Quick Start

Send your first command to RiftbornAI and watch it build something in your level.

Verify the Bridge is Running

Terminal
curl http://localhost:8766/riftborn/ping

# Response:
{"ok":true,"message":"RiftbornAI Debug Bridge active"}

Send Your First Command

Terminal
curl -X POST http://localhost:8766/riftborn/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "Spawn a point light at position 0, 0, 200"}'

Response

JSON Response
{
  "ok": true,
  "message": "Spawn a point light at position 0, 0, 200",
  "duration_ms": 1247.5,
  "response": "I've spawned a PointLight actor at location (0, 0, 200).",
  "tool_calls": [
    {
      "name": "spawn_actor",
      "success": true,
      "result": "Spawned PointLight at (0, 0, 200)",
      "arguments": {
        "actor_class": "PointLight",
        "location": "{\"x\":0,\"y\":0,\"z\":200}"
      }
    }
  ]
}

Try These Commands

CommandWhat It Does
"Spawn a cube at the origin"Creates a static mesh actor
"Create a floor 2000x2000 units"Generates level geometry
"Add 4 point lights in a square pattern"Batch spawns with positioning
"Set the directional light intensity to 5"Modifies existing actors
"List all actors in the level"Queries the scene

Configuration

Customize RiftbornAI for your workflow and security requirements.

Environment Variables

VariableDefaultDescription
ANTHROPIC_API_KEY-Recommended: Claude API key for brain learning
RIFTBORN_AUTH_ENABLEDfalseEnable API key authentication
RIFTBORN_API_KEY-API key for authentication (auto-enables auth)
RIFTBORN_RATE_LIMIT_ENABLEDtrueEnable rate limiting
RIFTBORN_RBAC_ENABLEDfalseEnable role-based access control
RIFTBORN_ENCRYPTION_KEY-Base64 encoded 32-byte key for AES-256
OLLAMA_HOSTlocalhost:11434Ollama server address (if using local)

Config File

Add to your project's Config/DefaultEditor.ini:

DefaultEditor.ini
[RiftbornAI.Security]
AuthEnabled=false
RateLimitEnabled=true
RBACEnabled=false
ToolTimeoutMs=30000
MaxRequestBodySize=10485760

[RiftbornAI.LLM]
Provider=claude  # Recommended: enables brain learning
# Provider=ollama  # Alternative: fully local
Model=qwen2.5-coder:7b
Temperature=0.7
MaxTokens=4096

API Reference

Complete reference for the RiftbornAI HTTP API. All endpoints return JSON.

Base URL

http://localhost:8766

Authentication

When auth is enabled, include your API key in requests:

Header Authentication
# Option 1: X-API-Key header
curl -H "X-API-Key: your_api_key_here" http://localhost:8766/riftborn/status

# Option 2: Bearer token
curl -H "Authorization: Bearer your_api_key_here" http://localhost:8766/riftborn/status

Endpoints

11 HTTP endpoints for full control over RiftbornAI.

GET /riftborn/ping

Simple health check. No rate limiting.

Response
{"ok": true, "message": "RiftbornAI Debug Bridge active"}

GET /riftborn/health

Detailed health check with component status.

Response
{
  "status": "healthy",
  "ok": true,
  "service": "RiftbornAI",
  "timestamp": "2025-12-06T15:30:00Z",
  "components": {
    "http_server": "healthy",
    "tool_registry": "healthy",
    "rate_limiter": {"enabled": true, "remaining_requests": 95}
  }
}

GET /riftborn/status

Server status including tool count and LLM provider connection.

GET /riftborn/tools

List all 415+ registered tools with descriptions and parameters.

GET /riftborn/metrics

Prometheus-compatible metrics for monitoring.

Response (text/plain)
riftborn_requests_total 1247
riftborn_requests_success_total 1198
riftborn_requests_failed_total 49
riftborn_uptime_seconds 3847.25
riftborn_tools_registered 415
riftborn_tool_executions_total{tool="spawn_actor"} 89

POST /riftborn/chat

Send natural language commands. The LLM interprets and executes tools.

Request
{
  "message": "Create a blueprint called BP_Enemy with a health component"
}

POST /riftborn/tool

Execute a specific tool directly (bypass LLM).

Request
{
  "tool": "spawn_actor",
  "args": {
    "actor_class": "PointLight",
    "location": {"x": 0, "y": 0, "z": 100}
  }
}

POST /riftborn/clear

Clear conversation history and operation context.

GET /riftborn/context

Get recent operations for error recovery.

GET /riftborn/logs

Get recent log entries from the bridge.

GET /riftborn/audit

Get audit log entries (requires authentication).

Tool Catalog

415+ tools organized into 16 design systems. Here are the key categories.

Actor Tools

ToolDescription
spawn_actorSpawn any actor class at a location
delete_actorRemove an actor from the level
move_actorSet actor position/rotation/scale
get_actorsQuery actors in the level by class or tag
set_actor_propertyModify any exposed property
duplicate_actorClone an actor with offset

Blueprint Tools

ToolDescription
create_blueprintCreate a new Blueprint asset
add_componentAdd component to Blueprint
add_variableAdd a variable with type
add_functionAdd a function to the graph
add_nodeAdd a node to the event graph
connect_pinsConnect two pins together
compile_blueprintCompile and save Blueprint

Material Tools

ToolDescription
create_materialCreate a new Material asset
add_material_expressionAdd a node to material graph
set_material_paramSet scalar/vector parameters
create_material_instanceCreate a material instance
apply_materialApply material to actor/mesh

Level Design Tools

ToolDescription
create_floorGenerate floor geometry
create_wallGenerate wall segments
create_roomGenerate enclosed room
add_navmeshConfigure navigation mesh
set_lightingConfigure scene lighting

Design Systems

16 specialized systems for different game development domains.

SystemToolsWhat It Does
GAS (Abilities)45+Gameplay Ability System - abilities, effects, attributes
AI Behavior38+Behavior Trees, EQS queries, AI Controllers
VFX & Niagara52+Particle systems, effects, emitters
Materials34+Material graphs, parameters, instances
Blueprints67+Node creation, pin connections, compilation
C++ Generation28+Actor, Component, GameMode class generation
UI & Widgets36+UMG widgets, HUD layouts, bindings
Audio29+Sound cues, attenuation, mixing
Level Design41+Room generation, lighting, geometry
Input System24+Enhanced Input mappings and contexts
Networking31+Replication, RPCs, net relevancy
Animation27+Montages, blend spaces, state machines
Physics22+Physics materials, constraints, collision
Save System18+Save games, serialization
Localization15+Text localization, string tables
Streaming12+Level streaming, world partition

GAS (Gameplay Ability System)

Full integration with Unreal's Gameplay Ability System. Design abilities from descriptions.

Example: Create a Fireball Ability

Natural Language Command
"Create a fireball ability with 50 damage, 3 second cooldown, 
costs 20 mana, spawns a projectile with explosion VFX on impact"

Generated Assets:

  • GA_Fireball β€” Gameplay Ability Blueprint
  • GE_Fireball_Damage β€” 50 instant damage effect
  • GE_Fireball_Cost β€” -20 Mana modifier
  • GE_Fireball_Cooldown β€” 3s cooldown effect
  • BP_Fireball_Projectile β€” Projectile actor

GAS Tools

ToolDescription
design_abilityDesign complete ability from description
design_effectCreate gameplay effect (damage, buff, DOT)
design_attribute_setDefine attribute set (Health, Mana, etc.)
create_ability_blueprintGenerate GA_ Blueprint
create_effect_blueprintGenerate GE_ Blueprint
add_gameplay_tagRegister gameplay tags

AI & Behavior Trees

Generate complete AI behavior systems from descriptions.

Example: Patrol & Chase AI

Command
"Create patrol behavior that chases player when spotted, 
returns to patrol after losing sight for 5 seconds"

Generated Assets:

  • BT_EnemyPatrol β€” Behavior Tree
  • BB_Enemy β€” Blackboard with keys
  • BTTask_Patrol β€” Custom patrol task
  • BTTask_ChasePlayer β€” Chase behavior
  • BTService_CheckVisibility β€” Vision service
  • EQS_PatrolPoints β€” Environment query

VFX & Niagara

Create particle systems from descriptions.

Example Commands

"Blue magic explosion with lingering sparks"
"Fire trail that follows the player"
"Purple lightning arc between two points"
"Healing particles rising upward with glow"
"Shield bubble effect with hexagon pattern"

Materials

Generate material graphs with proper node connections.

Example Commands

"Glowing lava material with animated flow"
"Ice shader with subsurface scattering"
"Hologram material with scan lines and flicker"
"Worn metal with rust and scratches"
"Glass with refraction and color tint"

Blueprints

Create and modify Blueprint assets programmatically.

Example Commands

"Add double jump to my character"
"Create a door that opens when player approaches"
"Add sprint with stamina drain"
"Create a pickup that restores 25 health"
"Add a dash ability with 2 second cooldown"

C++ Generation

Generate C++ classes with proper UE macros and patterns.

Supported Class Types

  • AActor β€” Base actors
  • ACharacter β€” Characters with movement
  • APawn β€” Controllable pawns
  • AGameModeBase β€” Game modes
  • APlayerController β€” Player controllers
  • UActorComponent β€” Components
  • UObject β€” Data objects

Generated Code Features

  • Proper header guards and includes
  • UCLASS/UPROPERTY/UFUNCTION macros
  • Replication setup (if needed)
  • BlueprintCallable/BlueprintReadWrite specifiers
  • Event dispatchers

UI & Widgets

Create UMG widgets and HUD layouts.

Example Commands

"Create a health bar with damage flash effect"
"Create a radial menu with 8 ability slots"
"Create an inventory grid 6x4"
"Create main menu with Play, Settings, Quit"
"Create dialogue box with character portrait"

Security & Authentication

Production-grade security features built into the core.

Security Features

FeatureDescription
Rate LimitingPer-IP, per-route, and global rate limits. Configurable windows and burst handling.
AuthenticationAPI key authentication via X-API-Key header or Bearer token.
RBACRole-based access control. Roles: None, ReadOnly, Execute, Admin, System.
Audit LoggingAll requests logged with timestamp, IP, endpoint, tool, success/fail, duration.
EncryptionAES-256-CBC encryption for sensitive data. PKCS7 padding.
Request SigningHMAC signature verification for tamper-proof requests.
Timeout ProtectionTool execution timeouts prevent runaway operations.

Rate Limit Configuration

Default Limits (per minute)
/riftborn/chat    β†’ 20 requests
/riftborn/tool    β†’ 30 requests
/riftborn/ping    β†’ 120 requests
/riftborn/status  β†’ 60 requests
/riftborn/health  β†’ 120 requests
/riftborn/audit   β†’ 30 requests (admin only)

Troubleshooting

Common issues and how to fix them.

Bridge Won't Start

⚠️

Port 8766 already in use

Another process is using the port. Check with netstat -ano | findstr 8766 and kill the process, or change the port in config.

LLM Not Responding

⚠️

LLM Connection Issues

Claude: Verify your ANTHROPIC_API_KEY is set correctly. Check API status at anthropic.com.

Ollama: Ensure it's running: ollama serve. Check it's accessible at http://localhost:11434.

Tools Timing Out

⚠️

Tool execution timed out after 30000 ms

Some tools take time. Increase timeout in config: ToolTimeoutMs=60000. Or the tool might be stuck β€” check UE Output Log.

Rate Limited

ℹ️

Rate limit exceeded

Wait for the window to reset (usually 60 seconds), or disable rate limiting for development: RIFTBORN_RATE_LIMIT_ENABLED=false

Check Server Status

Diagnostic Commands
# Check if server is running
curl http://localhost:8766/riftborn/ping

# Get detailed status
curl http://localhost:8766/riftborn/health

# Check metrics
curl http://localhost:8766/riftborn/metrics

# View recent logs
curl http://localhost:8766/riftborn/logs

Requirements

System requirements and dependencies.

Unreal Engine5.5+ (5.7 recommended)
Operating SystemWindows 10/11, macOS 12+, Linux
Python3.10 or later (for bridge scripts)
RAM16GB minimum, 32GB recommended
GPU VRAM8GB+ for local LLM inference
Claude APIRecommended β€” enables cloud brain learning
OllamaAlternative β€” qwen2.5-coder:7b for fully local operation

Ready to Build Games at the Speed of Thought?

Stop building everything manually. Join the waitlist and be among the first to experience AI-powered game development.

Join the Waitlist β†’