EdgeGen is a powerful CLI tool designed to generate custom edging behaviors and funscripts using advanced AI models. It integrates seamlessly with OpenAI, Anthropic, and Google Gemini to turn your creative prompts into fully realized .edgy files.
Created by alston808.
- Plug-and-Play AI: Support for OpenAI (GPT-4o), Anthropic (Claude 3.5), Google Gemini, Groq, OpenRouter, DeepSeek, Mistral, and local Ollama.
- Free AI Access: Use OpenRouter's free models or local Ollama for zero-cost generation.
- Easy Setup: Interactive CLI setup for API keys and preferences.
- Prompt-Driven: Uses a sophisticated system prompt to ensure high-quality, technically accurate outputs.
- Custom Patterns: Built-in awareness of your custom behaviors like
@alston808-custom-v1.edgy. - Debug Mode: Automatically saves raw AI responses if JSON validation fails.
-
Option A: Download Standalone Binary (Recommended) Go to the Releases page and download the executable for your platform (
edgegen-linux,edgegen-windows.exe, oredgegen-macos).Move it to a folder in your PATH and rename it to
edgegenfor easy access. -
Option B: Install via Pip Clone the repository:
git clone https://github.com/alston808/EdgeGen.git cd EdgeGenInstall in editable mode:
pip install -e .Alternatively, if you don't want to install it globally, just install the requirements:
pip install -r requirements.txt
Configure your preferred AI provider. You can use the edgegen command (if installed via pip) or the provided scripts:
# Using the shortcut (Recommended)
edgegen setup
# Using the shell script (Unix)
./edgegen.sh setup
# Using the batch file (Windows)
edgegen.bat setupThis will create a .env file with your secret keys.
Generate a new behavior:
edgegen generate "Create a behavior called 'The Siren' that starts slow and builds up to a frantic finish"See which providers are configured:
edgegen statusTo get the most out of EdgeGen, your prompts should be descriptive and technically specific where it matters. The AI understands both narrative roleplay and technical requirements.
- Be Specific with Arousal: Instead of saying "get faster," say "increase velocity from 20% to 80% as arousal goes from 0 to 90."
- Define the Stroke Zone: Specify if you want deep strokes (0-100%), tip-teases (80-100%), or bottom-heavy movements (0-30%).
- Add Personality: Use words like "mechanical," "seductive," "erratic," or "relentless" to guide the AI's creative choices.
- Utilize Gestures: Ask for specific variations like "sudden pauses," "vibrating pulses," or "random speed bursts."
Copy and fill this template for consistent results:
Create a behavior called '[NAME]' with the icon [EMOJI].
The theme is [THEME/NARRATIVE].
**Arousal Logic:**
- At 0% arousal: [DESCRIPTION OF STARTING MOTION]
- At 50% arousal: [DESCRIPTION OF MID-POINT]
- At limit (100%): [DESCRIPTION OF PEAK MOTION]
**Technical Details:**
- Velocity: [e.g., 10% to 90%]
- Stroke: [e.g., Deep strokes early, shallow late]
- Hold: [e.g., No hold at start, 500ms hold at 90% arousal]
**Gestures:**
- Add a variation called '[GESTURE NAME]' that [DESCRIPTION OF MOVEMENT] with [X]% probability.
**Orgasm:**
- Duration: [X] seconds.
- Style: [e.g., Massive spike then slow fade]- System Prompt: edgegen/system_prompt.md - The core logic driving the AI.
- Custom Patterns: edgegen/alston808-custom-v1.edgy - Custom behaviors defined by alston808.
- Google Gem: Custom Gemini Link
- Example Prompts: edgegen/user_prompts.md
This file contains hand-crafted behaviors like "The Abyssal Plunge" and "The Deep Diver". These behaviors use complex velocity and stroke curves to create unique sensations. The EdgeGen CLI feeds these examples to the AI to maintain consistency and quality.
A collection of detailed example prompts that demonstrate how to talk to the EdgeGen AI. Use these as inspiration or as a base for your own custom behaviors. It includes a Prompting Structure Guide to help you craft effective requests.
This is the "Brain" of EdgeGen. It contains technical specifications for how behaviors should be structured, including LaTeX math for curves and specific XML tag requirements for AI responses.
EdgeGen uses GitHub Actions to automatically build and release binaries for Linux, Windows, and macOS.
To trigger a new release, simply push a new version tag to GitHub:
git tag v1.0.1
git push origin v1.0.1The workflow will automatically build the package and attach it to a new GitHub Release.
You can also trigger a release manually:
- Go to the Actions tab in your repository.
- Select the Release workflow.
- Click Run workflow.
MIT