backend▌

newapi (new-api) is an open-source unified AI gateway platform. It aggregates multiple model providers behind OpenAI / Claude / Gemini compatible interfaces, and provides model, token, group, and balance management.

Use SerpApi via direct curl calls to scrape search engine results from Google, Bing, YouTube, and more.

33+ essential JavaScript concepts every developer should know, inspired by 33-js-concepts.

Generate complete, production-ready applications directly from OpenAPI specifications. \n \n Accepts OpenAPI specs via URL, local file, or direct content input; validates completeness and identifies endpoints, schemas, authentication requirements, and data relationships \n Generates full project structure with controllers, services, models, repositories, and configuration files following framework conventions and best practices \n Includes unit tests, README with setup instructions, environment

Comprehensive Rust testing patterns for writing reliable, maintainable tests following TDD methodology.

Standards and best practices for Python development. Follow these guidelines when writing or modifying Python code.

Persona: You are a Go engineer who treats caching as a system design decision. You choose eviction algorithms based on measured access patterns, size caches from working-set data, and always plan for expiration, loader failures, and monitoring.

Comprehensive pytest testing strategies with TDD, fixtures, mocking, and coverage best practices. \n \n Covers TDD methodology (red-green-refactor cycle), parametrization, fixtures with multiple scopes, and mocking patterns for unit and integration testing \n Includes pytest fundamentals: assertions, markers for test selection, exception testing, and async test support with pytest-asyncio \n Provides practical patterns for testing APIs, databases, file operations, and class methods with real cod

Web search and content scraping via DuckDuckGo with configurable result limits. \n \n Provides two core commands: search for querying the web with customizable result counts, and fetch_content for scraping full page content from URLs \n Integrates with the DuckDuckGo MCP Server for real-time search results and webpage extraction \n Useful for agents that need to gather current information, verify facts, or extract text from live web pages \n

Operation-aware node configuration with progressive discovery and property dependency management. \n \n Start with get_node({detail: \"standard\"}) for 95% of configuration needs; escalate to full detail or search_properties mode only when standard doesn't provide required information \n Resource and operation determine which fields are required; use validation iteratively to discover conditional dependencies controlled by displayOptions rules \n Common patterns include resource/operation nodes