Quick Start Guide
This guide takes you from a fresh OmniIDE installation to running your first autonomous coding session in under 5 minutes.
Step 1: Configure Your API Key
OmniIDE uses Google Gemini API for cloud-powered AI. You will need a free API key:
- Visit Google AI Studio
- Create a new API key (free tier available)
- In OmniIDE, open Settings (
Ctrl+,) and paste your key in the Gemini API Key field
Prefer offline? Skip the API key and set up Ollama for fully local AI execution.
Step 2: Create a Project
- Open OmniIDE and click File → Open Folder
- Create a new folder for your project (e.g.,
my-first-project) - The Omni-Agent will automatically detect the workspace
Step 3: Start an Autonomous Session
Open the Omni-Agent panel and type a natural language instruction:
Create a Node.js Express API with a /health endpoint
and a /users endpoint that returns sample data.
The Omni-Agent will:
- Generate the project structure
- Create all necessary files (
package.json,server.js, routes) - Install dependencies via
npm install - Start the development server
- If any errors occur, automatically debug and fix them
Step 4: Watch the Self-Healing Loop
If the agent encounters an error during execution — say, a missing dependency or a syntax mistake — it will:
- Catch the error from the terminal output
- Analyze the root cause using Gemini
- Generate the corrective code
- Re-execute automatically
This is the self-healing agentic loop — no manual intervention required.
Next Steps
- Learn about the Omni-Agent — how the autonomous agent works under the hood
- Multi-File Refactoring — handle complex cross-file changes
- Autonomous Workflows — advanced agent patterns