Christopher Smith ran a mini hackathon in Albany New York at the weekend around uses of my LLM - the first in-person event I'm aware of dedicated to that project! …

VS Code AI Customization: Learn to use custom instructions, prompt files, and custom chat modes to personalize AI code generation, reviews, and chat responses.

The solution to agentic flows was code all along.

Customize and extend Claude Code's behavior by registering shell commands

6 tactics for fixing your context and shipping better agents. As Karpathy says, building LLM-powered apps means learning to ‘pack the context windows just right’—smartly deploying tools, managing information, and maintaining context hygiene.

A pragmatic take on AI coding with practical insights

A detailed walkthrough of using Claude Code AI assistant for software development, including workflow tips, testing practices, and practical examples from real projects. Covers defensive coding strategies, TDD, and team implementation.

A curated list of commands, files, and workflows for Claude Code - vincenthopf/claude-code

This guide is intended to help you provide better context for GitHub Copilot when working on programming-related tasks. Use this template to define your goals, preferences, and any specific guideli...

Working with GitHub Copilot in VS Code amps out your efficiency as a programmer - but did you know that adding a simple markdown file can boost this efficiency even more, while *also* decreasing the size of your prompt? Custom Instructions can help you and your team do so much more with GitHub Copilot, and @rconery will show you how in this video. 🔎 Chapters: 00:12 Simple, automatic instructions 02:07 Custom Git commit messages 03:26 Customizing Copilot functionality in VS Code 05:00 Going all in with markdown files as instructions 🔗 Links: Get Copilot: https://aka.ms/get-copilot Instruction Snippets for JSONC: https://gist.github.com/robconery/f93d016ace16feb7156f9b7905f3f499 🎙️ Featuring:‪ @rconery‬ #vscode #copilot #githubcopilot

✅ Learn how to build robust and scalable software architecture: https://arjan.codes/checklist. Want your AI tools to actually *do* something? In this video, I’ll show you how to integrate external tools with language models using **MCP (Model Context Protocol)**. You’ll learn two common architecture patterns, see real code examples, and get tips on keeping your setup clean and scalable. Whether you’re building for Claude, ChatGPT, or any other LLM—this is how you connect your backend to AI. 🔥 GitHub Repository: https://git.arjan.codes/2025/mcp-server. 🎓 ArjanCodes Courses: https://www.arjancodes.com/courses. 🔖 Chapters: 0:00 Intro 0:46 What is MCP? 3:14 YouTube MCP Version 1 7:58 YouTube MCP Version 2 12:18 Final Thoughts #arjancodes #softwaredesign #python

In my previous article , we explored Model Context Protocol (MCP) — a standardized way for LLMs to invoke tools or APIs with structured…

The original promise of personal computing was a new kind of clay. Instead, we got appliances: built far away, sealed, unchangeable. In this essay, we envision malleable software: tools that users can reshape with minimal friction to suit their unique needs.

OCR package using Ollama vision language models.

My current theory of agentic programming: people are amazing at adapting the tools they're given and totally underestimate the extent to which they do it, and the amount of skill we build doing that is an incidental consequence of how badly the tools are designed.

Your open source AI agent, automating engineering tasks seamlessly.

Turn your blind AI into a visual debugger with instant screenshot capture and analysis

Contribute to cognitivecomputations/dolphin-mcp development by creating an account on GitHub.

Personal Blog

A comprehensive guide outlining best practices for building reliable, user-friendly Model Context Protocol (MCP) tools with proper configuration, testing, and release management.

Check out our deep dive on the latest meta prompting methods, like DSPy and TEXTGRAD, and the best prompt generator tools out there.

System prompt for a Raycast chat preset, acting as a Todoist assistant using the new AI Extension. - raycast_chat_preset_instructions.md

LLM 0.26 is out with the biggest new feature since I started the project: support for tools. You can now use the LLM CLI tool—and Python library—to grant LLMs from …

Task management inside Cursor that makes it 10x betterGet Complete AI Agents playbook: https://clickhubspot.com/i2uy🔗 Links- Join AI builder club & access 1...

OpenMemory is a passport powered by Mem0 that lets you carry your memory across any AI app. It provides a unified memory layer that stays with you, enabling agents and assistants to remember what matters across applications.

Minimal AI agent framework that just works with only seven tools. - aperoc/toolkami

Therapeutics Commons (TDC): Multimodal Foundation for Therapeutic Science - mims-harvard/TDC