243 items indexed · AI tools, prompts, hooks & techniques
This is a free, comprehensive course from Microsoft that teaches the fundamentals of building AI agents. It provides a structured, 12-lesson curriculum in Jupyter Notebooks to get anyone started with creating automated AI systems that can reason and perform tasks.
This is a curated list of research papers and software frameworks for running advanced AI, like language and image models, directly on mobile phones and other small devices. This technique enables faster, more private AI applications that work without a constant internet connection.
This technique combines two different AI coding assistants to improve software development. Use the Claude AI for high-level planning and complex code refactoring, similar to a senior architect, and use the Codex AI for writing and debugging smaller, specific pieces of code. This 'hybrid' approach leverages the unique strengths of each AI to deliver better results faster.
This comparison outlines two distinct approaches to AI-powered coding. Claude Code acts as an interactive partner for developers, ideal for complex refactoring within large codebases, while OpenAI Codex is an autonomous agent that handles entire tasks independently, best for delegating production work.
Windsurf and Cursor are powerful AI tools that function as autonomous developers within a code editor. Cursor excels at rapid iteration and bug fixing for individual developers, while Windsurf is designed for large, complex enterprise projects, using its 'Cascade' agent to understand and modify the entire codebase.
OpenCLAW's latest update introduces a 'ContextEngine' for smarter, more customizable AI agents that can handle complex tasks and remember more information. It also adds automatic failover, ensuring the AI remains operational by switching between different AI models (like OpenAI or Google) if one fails, increasing reliability for business-critical applications.
This resource provides a professional blueprint for building robust AI agent systems that can handle real-world business demands. It outlines the seven essential layers—from security and data management to performance monitoring—ensuring your AI agents are reliable, scalable, and safe for production use.
This guide provides developers with concrete examples of how to build AI agents that are reliable enough for production use. It highlights specific open-source projects that focus on testing and handling unexpected scenarios, or 'edge cases', to ensure the AI doesn't break when faced with unusual user requests or data.
For complex coding tasks, using two specialized AI assistants is more effective than one. This technique uses an AI like OpenAI Codex to rapidly generate the initial functional code, and then uses a different AI, like Claude Code, to review, refactor, and improve the code's quality for production use.
This document compares two distinct approaches to AI-powered coding assistants. The 'Cursor' style prioritizes speed and rapid edits for individual developers and prototypes, while the 'Windsurf' style focuses on deep, project-wide understanding for large-scale changes and enterprise team collaboration.
OpenCLAW's latest update introduces a 'ContextEngine,' allowing developers to build more intelligent and customized AI agents for your business needs. It also improves reliability by automatically switching between AI providers like OpenAI and Anthropic if one fails, ensuring your AI tools remain consistently operational.
The OpenAI Codex CLI is a command-line tool that gives developers direct terminal access to powerful AI models for coding. Recent updates have made it more 'agentic,' allowing it to independently plan and execute complex tasks, understand image uploads like screenshots, and integrate directly with VS Code and GitHub to streamline workflows.