Open Source · AI-Powered · Free Forever

Stop Grinding.
Let AI Carry.

Record your gameplay. Train a neural network. AFK while the bot farms, fights, and loots for you 24/7. Battle-tested on Genshin, WoW, FFXIV, Lost Ark, GW2, and New World.

401Tests Passing
6MMORPGs
9Neural Nets
24/7Auto-Farm

Not a Macro. Not a Script. Pure AI.

This isn't your average auto-clicker. This is a full neural network that watches you play, learns your strats, and executes them at 30+ FPS while you sleep.

Record & Learn

Just play your game for 10-15 min. The AI watches every input you make — keyboard combos, controller sticks, mouse flicks — and records it all at 10+ FPS. Your gameplay is the training data.

Train Your AI Clone

Hit one command and grab a coffee. PyTorch trains a deep neural network on your recorded plays. It auto-detects your action space, picks the right model, and tunes everything to your game's profile.

GG, It Plays For You

Launch the bot and go AFK. It reads the screen, predicts your next move, and executes at 30+ FPS. Built-in anti-stuck tech means no more running into walls. Farm all night, wake up to full bags.

Every Input, Every Button

WASD, PS4/Xbox controller (sticks, triggers, bumpers, d-pad), and full mouse (aim, delta, velocity, LMB/RMB/MMB, scroll). If you can press it, the AI can learn it and reproduce it.

Game Launcher Vibes

A dark-themed gaming dashboard with one-click Record, Train, and Play. Looks like a Steam overlay, works like a pro tool. Game presets, model catalog, real-time logs. No terminal needed.

Raid-Tested, Ship-Ready

401 automated tests. Every game profile, every neural net, every action space — tested end-to-end with real PyTorch training. This isn't a prototype. It's production-grade.

Your Favorite MMOs. Day-One Support.

Each title ships with a hand-tuned game profile — resolution, action space, neural net, learning rate — all dialed in so you can jump straight into training.

⚔️Genshin Impact16 actions · 480p
🐉World of Warcraft73 actions · 640p
🔮Final Fantasy XIV73 actions · 640p
🛡️Guild Wars 248 actions · 480p
Lost Ark48 actions · 640p
🏹New World48 actions · 480p

Recommended Settings per Game

⚔️

Genshin Impact

efficientnet_lstm combat (48) 480x270 LR 0.001
🐉

World of Warcraft

efficientnet_lstm extended (73) 640x360 LR 0.0008
🔮

Final Fantasy XIV

efficientnet_lstm extended (73) 640x360 LR 0.0008
🛡️

Guild Wars 2

efficientnet_lstm combat (48) 480x270 LR 0.0006

Lost Ark

efficientnet_lstm combat (48) 640x360 LR 0.0005
🏹

New World

efficientnet_lstm combat (48) 480x270 LR 0.0006

The Tech Behind The Magic

Three stages: Capture your plays, train the AI on your data, then unleash it in-game. Mouse support is optional — toggle it on if your game needs it.

RECORD Screen 480x270 @ 10fps Keyboard (9) Gamepad (20) Mouse (10) pos + delta + vel + btn .npy dataset TRAIN EfficientNet-B0 Backbone Feature Extraction (5M params) LSTM Temporal Head Sequence Memory (4 frames) Actions 9-73 discrete Mouse 10 continuous BCEWithLogitsLoss Adam Optimizer INFERENCE Trained Model .pt checkpoint + metadata Action Weights Dynamic per action-space size Stuck Detection Escalating evasive maneuvers Keys Mouse GAME

Input Vector Anatomy

Keyboard (9 values)

W, S, A, D, WA, WD, SA, SD, NOKEY. One-hot directional encoding for 8-way movement.

Gamepad (20 values)

LT, RT, Lx, Ly, Rx, Ry, D-Pad (4), Face buttons (A/B/X/Y), Bumpers, Start/Select, Sticks.

Mouse (10 values) BETA

X, Y (position), dX, dY (delta), vX, vY (velocity), LMB, RMB, MMB (buttons), scroll.

9 Neural Nets. Pick Your Weapon.

From lightweight speed-runners to heavy-hitting transformer tanks — 9 architectures tested end-to-end across all 6 games. Every single one passed quality gates.

Model Params Temporal Speed Best For Tier
EfficientNet-LSTM ~5M LSTM (4 frames) ~8ms Best overall accuracy Recommended
EfficientNet-Simple ~5M None ~5ms Single-frame prediction Recommended
MobileNetV3 ~2M None ~3ms Low-end / real-time Recommended
ResNet18-LSTM ~12M LSTM (4 frames) ~10ms Speed / accuracy balance Recommended
EfficientNet-Transformer ~12M Transformer ~15ms Long action sequences Advanced
Multi-Head Action ~6M Multi-head ~8ms Simultaneous actions Advanced
Game Attention Net ~6M Spatial attn ~10ms Complex UIs Advanced
InceptionV3 ~7M None ~12ms Legacy support Legacy
AlexNet ~60M None ~5ms Legacy support Legacy

Recommendation

Use EfficientNet-LSTM for all MMORPGs. It delivers the best accuracy with temporal awareness across all 6 tested game profiles while maintaining >30 FPS inference on GPU. Use MobileNetV3 only on low-end hardware (<4GB VRAM).

From Zero to Auto-Farm in 5 Minutes

No PhD required. Just follow these steps and your AI will be farming while you sleep. Windows 10/11 for gameplay; training works on any OS.

1

Install Prerequisites

You need Python 3.10+, Git, and optionally Rust (for the Tauri desktop app).

# Check Python version
python --version   # Should be 3.10+

# Install Rust (optional, for Tauri desktop app)
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
2

Clone & Install

Clone the repository and install all dependencies with a single command.

git clone https://github.com/ruslanmv/BOT-MMORPG-AI.git
cd BOT-MMORPG-AI
make install          # Core + PyTorch
make install-launcher  # Desktop launcher (optional)
make install-tauri     # Tauri desktop app (optional)
3

Record Your Gameplay

Play your game normally for 10-15 minutes. The bot watches and records screen + inputs.

# Via command line
make collect-data

# Or use the Launcher / Tauri app GUI
# Controls: T = pause/resume, Q = stop and save
4

Train the Neural Network

One command trains the model. Auto-detects action space and hardware tier.

make train-model

# GPU: ~30-60 minutes  |  CPU: ~2-4 hours
# Default: efficientnet_lstm (recommended for all games)
5

Let the AI Play

Start the bot, switch to your game window, and watch the AI play using your learned strategy.

make test-model

# Controls: T = pause/resume, ESC = stop completely
# Built-in stuck detection + evasive maneuvers
6

Verify Everything Works

Run the full test suite to confirm all 401 tests pass on your system.

make test

# Expected: 401 passed, 1 skipped
# Covers: profiles, networks, mouse, training, inference

Pro Strats for Maximum Performance

These are the optimization tips the top players use. Follow them and your bot will perform like a speedrunner, not a noob.

Record Quality Data

Play consistently for 10-15 minutes. Repeat the same route 2-3 times. Set in-game time to noon for consistent lighting. Avoid AFK or idle moments during recording.

Use 480x270 Resolution

Lower capture resolution = faster training and inference. 480x270 captures all essential UI elements for most games. Only use 640x360 for complex UIs (WoW addons, FFXIV hotbars).

Start with EfficientNet-LSTM

It is the proven default for all 6 tested MMORPGs. Only switch to MobileNetV3 on low-end hardware (<4GB VRAM) or if you need maximum FPS. Advanced architectures are experimental.

Use Game Presets

Select your game in the launcher or Tauri app. Presets auto-configure resolution, action space, architecture, learning rate, and temporal frames for optimal results.

Mouse is Optional

Mouse recording is a beta feature, disabled by default. Enable it in the UI checkbox only if your game relies heavily on mouse aim (action combat, camera control). It is purely additive and non-destructive.

Hardware Tier Matters

Low (<4GB): MobileNetV3, batch 8, 160x160. Medium (4-8GB): EfficientNet-Simple, batch 16, 224x224. High (>8GB): EfficientNet-LSTM, batch 32, 224x224 with 4 temporal frames.

Enjoying the Bot? Drop a Star!

Help us reach more gamers. A GitHub star takes 1 second and means the world to our dev party. Let's hit the leaderboard together.

Star on GitHub

Open source · Apache 2.0 · Free forever · No strings attached