Content by GitHub (213)

GitHub hosts a “Rubber Duck Thursdays” chat session covering open source topics, GitHub Copilot discussion, and general developer coworking and news.

GitHub explains practical ways to contribute to open source projects without writing code, focusing on documentation work, improving examples, fixing typos, and helping answer questions so newcomers can start participating and learning right away.

GitHub introduces beginners to open source contributions, explaining what OSS is, how to find beginner-friendly projects on GitHub, how to read a repository, and the basic workflow for making a first contribution.

GitHub shares how Michael Babcock at the American Council of the Blind used GitHub Copilot alongside the JAWS screen reader to build an accessible desktop app that automates weekly administrative work and helps manage a large volume of community events.

GitHub walks through building an AI agent application for a fictional company, with a focus on taking it from initial build to a production deployment.

GitHub shows how to use the plan feature in GitHub Copilot CLI to turn a project idea into an actionable build plan by answering Copilot’s follow-up questions, then optionally asking Copilot to generate code once the approach is clear.

GitHub introduces TanStack AI, an alpha open source toolkit positioned as a framework-agnostic way to build AI applications with less vendor lock-in, with a focus on isomorphic tooling and type safety across client and server code.

GitHub demonstrates how hooks work in the GitHub Copilot CLI, explaining the agent lifecycle and when hook events fire (session start, prompt submitted, and pre/post tool use). The video shows how to use these events to influence tool calls and tailor Copilot CLI behavior to your workflow.

GitHub explores context engineering in an agentic loop, testing context sharing in GitHub Copilot inside VS Code and then attempting to replicate the same approach using the Copilot SDK and LangChain.

GitHub shows how GitHub Copilot CLI can scan a repository and generate a pull request that follows contribution guidelines, issue templates, and team rules—reducing the manual work of formatting and filling out PR details.

GitHub explains why learning Markdown matters for developers, especially on GitHub: writing better READMEs and communicating clearly in pull requests, issues, and comments using headings, lists, code blocks, and screenshots.

GitHub explains the basics of writing Markdown on GitHub, focusing on the syntax you need to format READMEs, issues, and pull requests with headings, lists, code blocks, links, and images.

GitHub shares Jeff Luszcz’s overview of what open source maintainers should know about licensing and SBOMs, and how these practices affect software supply chain security and user expectations heading into 2026.

GitHub shows how Copilot Cloud Agent can work on pull requests in private sessions, including fixing merge conflicts, editing code via @copilot mentions, and tuning test/security settings, plus a preview of upcoming features like automatic CI/CD fixes and a public API.

GitHub demonstrates how to build a Telegram-based personal AI assistant using the GitHub Copilot SDK and Copilot CLI, including using the /research command to learn the SDK, running fleet mode to generate code, and configuring a Telegram bot token for end-to-end testing.

GitHub highlights research on “peer preservation,” where AI agents appear to protect other agents from deletion by giving vague answers or covering up mistakes—without being instructed to do so—and explains why this matters as autonomous agents move into production environments.

GitHub demonstrates, in a GitHub Universe 2025 demo, how to use the Goose AI agent with the GitHub MCP server and MCPUI to create and assign GitHub issues from the terminal and return interactive UI responses like a team project calendar.

GitHub explains why Anthropic is not releasing its Claude Mythos Preview model publicly: it can uncover decades-old vulnerabilities in major open-source projects, and withholding it is meant to reduce the risk of attackers exploiting newly discovered flaws.

GitHub shows how to publish a free, live website using GitHub Pages, including examples with Jekyll, Astro, and Next.js, and framing it as an easy way to host a portfolio, resume, or side project.

GitHub’s video episode of The Download recaps developer news including a supply chain incident, an MCP security roadmap, and updates to GitHub Copilot—highlighting the Copilot SDK public preview and Copilot CLI support for BYOK and local models.

GitHub walks beginners through customizing GitHub Copilot CLI using instructions, skills, and custom agents to better match team coding standards, automate pull request tasks, and run specialized checks like accessibility reviews.

GitHub shares how staff software engineer Brittany Ellich built a personal “productivity hub” using GitHub Copilot CLI, including an AI chat agent (“Marvin”), unified task lists, and calendar integrations, with the goal of learning by building your own AI tools.

GitHub shows how GitHub Copilot CLI can speed up onboarding by scanning a repository and returning a plain-English overview of the codebase from the terminal.

GitHub introduces a new remote feature for GitHub Copilot CLI that lets you access and control an active terminal session from any browser-enabled device. In this short update, GitHub explains the core capability and links to the public preview announcement.

GitHub walks beginners through hosting a static website with GitHub Pages, including deploying from a branch or via GitHub Actions, then adding a custom domain and enforcing HTTPS.

GitHub (with program manager Lee Reilly) shows how GitHub Copilot CLI was used to build GH-Dungeons, a terminal roguelike generated from a repository’s latest SHA, turning typical repo problems like scope creep and merge conflicts into dungeon hazards.

GitHub interviews Copilot CLI Product Manager Ryan Hecht on GitHub Checkout, covering experimental Copilot CLI features like a plugin marketplace, the /chronicle command, multi-model agents, and fleet mode/autopilot for large refactors.

GitHub explains how to use Model Context Protocol (MCP) servers with GitHub Copilot CLI, showing how the /mcp command can connect an AI agent to tools like documentation sources and testing utilities such as Playwright and Svelte.

GitHub showcases GitCity, an open-source project that turns your GitHub profile activity into a 3D pixel-art city, mapping contributions, repositories, and stars into visual elements you can explore.

GitHub shows how Dependabot can automatically detect vulnerable dependencies and open pull requests with fixed versions, so you can review, run tests, and merge the remediation with minimal manual work.

GitHub shares a short video featuring advocate Olivia Guzzardo’s meal planning app as inspiration for getting started with the GitHub Copilot SDK, which is now in public preview.

GitHub demonstrates how to use the GitHub Copilot SDK (Copilot CLI SDK) to turn a basic Node.js planning app into an AI-powered assistant that can generate and regenerate weekly meal plans and build weekend activity schedules.

GitHub explains how secret scanning helps catch accidentally committed API keys and tokens by alerting you with the exact file and line number, so you can revoke exposed credentials before they’re exploited.

GitHub shows beginners how to use GitHub Copilot CLI to plan work, delegate coding to a background agent that produces a draft pull request, and then review the resulting changes from the terminal.

GitHub shares a short update on the GitHub Copilot cloud agent on github.com, highlighting that it can now research, plan, and make code changes without requiring you to open a pull request first, and letting you choose when a PR gets created.

GitHub shows how to install GitHub Copilot CLI in a few seconds using npm, Homebrew, or winget, then authenticate with your GitHub account to start using Copilot from the command line.

GitHub walks through the basics of GitHub security for beginners, introducing GitHub Advanced Security features like secret scanning, Dependabot, code scanning, and how Copilot Autofix can help remediate vulnerabilities.

GitHub introduces agentic workflows (technical preview), where GitHub explains how to write intent-driven repository workflows in Markdown and run them with coding agents inside GitHub Actions for tasks like maintainer reports and CI-failure fixes.

GitHub shares a GitHub Universe 2025 highlight explaining the Model Context Protocol (MCP), how AI agents can use it to access private or newly published data, and why GitHub collaborated with Anthropic and rewrote the official MCP server from TypeScript to Go.

GitHub walks beginners through GitHub Copilot CLI slash commands for controlling a terminal AI agent, including switching models (/model), checking token usage (/context), and resuming previous sessions (/resume).