Advanced

Power-user techniques for getting the most out of HyperDevs.

Custom System Prompts

You can customize how AI responds by setting custom system prompts for each tab.

Use Cases

  • • Coding Style: Enforce specific patterns or frameworks
  • • Response Format: Request JSON, Markdown, or other formats
  • • Domain Knowledge: Add game-specific context or rules
  • • Constraints: Set limits on response length or complexity

Understanding EditableMesh Limits

EditableMesh is powerful but has limits. Understanding these helps you create better assets.

Key Limits

Triangles per part ~10K recommended
Texture size 1024x1024 or lower
Materials per mesh 1 (baked recommended)

Hyper 30 & Local Models

Two ways to run AI without a third-party API key: the built-in Hyper 30 model, or a fully local model via Ollama.

Hyper 30 (built-in, no setup)

The default model, served from the HyperDevs cloud proxy. Just sign in and it works — credit-billed, with a free tier. Power users on the local network can also point at the direct LAN path instead of the cloud.

  1. 1. Open Settings → AI Providers → Hyper 30
  2. 2. Enter your HyperDevs access key (or leave it blank on the LAN path)
  3. 3. Start chatting and generating — no other key needed

Ollama (free, fully offline)

Run models locally for complete privacy and offline use.

  1. 1. Download Ollama from ollama.com
  2. 2. Install and run ollama serve
  3. 3. Pull a model: ollama pull llama3
  4. 4. In HyperDevs, select Ollama as your provider (default: http://localhost:11434)

Recommended Local Models

  • • gemma4:26b: App default — best balance of quality and speed
  • • llama3.2: Lightweight and fast
Documentation for HyperDevs v0.1.20 Edit this page Report an issue