novaglide
Defines a Cursor-powered AI development environment with LLM integration, web scraping, search, and screenshot verification tools.
What this file does
Defines a Cursor-powered AI development environment with LLM integration, web scraping, search, and screenshot verification tools.
When to use it
- Setting up an AI-assisted coding environment with Cursor
- Needing built-in tools for LLM queries, web scraping, and search
- Wanting a preconfigured dev container and CI/CD workflows
- Starting a project that uses multiple LLM providers
Assumes this stack
novaglide
A Cursor-powered AI development environment with advanced agentic capabilities.
Quick Start
-
Activate the virtual environment:
# On Windows venv\Scripts\activate # On macOS/Linux source venv/bin/activate -
Configure your environment:
- Copy
.env.exampleto.envif you haven't already - Add your API keys in
.env(optional)
- Copy
Available Tools
Your project includes several powerful tools in the tools/ directory:
LLM Integration
from tools.llm_api import query_llm
# Use LLM for assistance
response = query_llm(
"Your question here",
provider="anthropic" # Options: openai, anthropic, azure_openai, deepseek, gemini
)
print(response)
Web Scraping
from tools.web_scraper import scrape_urls
# Scrape web content
results = scrape_urls(["https://example.com"], max_concurrent=3)
Search Engine
from tools.search_engine import search
# Search the web
results = search("your search keywords")
Screenshot Verification
from tools.screenshot_utils import take_screenshot_sync
from tools.llm_api import query_llm
# Take and analyze screenshots
screenshot_path = take_screenshot_sync('https://example.com', 'screenshot.png')
analysis = query_llm(
"Describe this webpage",
provider="openai",
image_path=screenshot_path
)
Note: When you first use the screenshot verification feature, Playwright browsers will be installed automatically.
AI Assistant Configuration
This project uses .cursorrules to configure the AI assistant. The assistant can:
- Help with coding tasks
- Verify screenshots
- Perform web searches
- Analyze images and code
Environment Variables
Configure these in your .env file:
LLM_API_KEY: Your LLM API key (optional)AZURE_OPENAI_API_KEY: Azure OpenAI API key (optional)AZURE_OPENAI_ENDPOINT: Azure OpenAI endpoint (optional)AZURE_OPENAI_MODEL_DEPLOYMENT: Azure OpenAI model deployment name (optional)SILICONFLOW_API_KEY: Siliconflow API key (optional) Note: Basic functionality works without API keys. Advanced features (like multimodal analysis) require appropriate API keys.
Development Tools
.devcontainer/: VS Code development container configuration.vscode.example/: Recommended VS Code settings.github/: CI/CD workflows
License
MIT License
What's inside
7 sections, 4 tool examples, 1 environment variable list, 1 license
Change this for your project
- Replace
infinature/novaglidewith your own repository name - Replace
.env.examplewith your own environment variable template - Replace
tools/directory contents with your own tool implementations
Where it goes
Keep it in your repository where the agent or team that needs it will read it.
Related Documents
dbt Core
Defines a complete dbt project setup with layered architecture, SQL style, Jinja best practices, and CI/CD workflow guidance.
HarmonyOS 主题与样式 - Cursor Rules
Defines HarmonyOS theming rules for dark/light mode, page brightness, and screen-on control with code examples.
Cursor Development Environment
Documents a Docker-based dev container setup with test commands and OpenClaw agent configuration for the ClawDrive project.
Journey from Concept to Code: Transforming Cursor into a Devin-like AI Assistant
Documents the creation of aicode.cursorrules, a set of rules that turns Cursor/Windsurf into a Devin-like AI assistant with automated planning and self-evolution.