Skip to main content
AmigoFish

GitHub

GitHubVideo

Format:
YouTube channel
New videos:
Daily
Typical length:
about 25 minutes, not counting Shorts
Latest video:
Not rated yet

About this show

GitHub is the AI-powered developer platform to build, scale, and deliver secure software. We make it easier for developers to be developers: to work together, to solve challenging problems, and to create the world’s most important technologies. We foster a collaborative community that can come together—as individuals and in teams—to create the future of software and make a difference in the world.

The GitHub platform is where developers can create, share, and ship the best code possible. Our community is made up of students, hobbyists, consultants, enterprise professionals, partners, and executives, building software in the way that works best for them.

GitHub is much more than code. It is the home of open-source collaboration. It is where new developers get started and where experienced developers expand their knowledge. It is a community where developers come together to solve the unsolvable and test the limits of what software can do.

Videos come from the channel's public YouTube feed. The artwork is the newest video thumbnail. Last updated . Names, artwork and text belong to their publishers.

Cosmos

Similar by topic and creator

See the full Cosmos

Videos

  • How Marks & Spencer uses GitHub Copilot to scale retail engineering

    · 2 min

    Marks & Spencer (M&S) is a leading UK retailer with more than 1,000 stores across 70 global markets. As the business scales its food, fashion, and beauty operations, engineering teams rely on GitHub Copilot and agentic workflows to accelerate software delivery across the entire development lifecycle. By automating ticket scaffolding, code generation, and pull request reviews with specialized AI agents, engineers have achieved productivity uplifts of up to 75% for key tasks. Discover how M&S modernises retail engineering while keeping developers firmly in control of architectural decisions. #GitHub #GitHubCopilot #SoftwareEngineering Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • The unexpected reason Nvidia is trending on GitHub

    · 1 min

    Nvidia recently started trending on GitHub, and it has nothing to do with leadership changes. In this episode of The Download, discover why Nvidia's open-source Auto-Ontology repository surged by 8,000 stars in just a few days to become one of the most popular projects on GitHub. Learn how Auto-Ontology builds a semantic layer that maps business concepts to database tables, helping AI agents validate SQL queries and understand what your data actually means. Explore the repository and connect it to your agents via MCP, CLI, or APIs: https://github.com/NVIDIA/auto-ontology #NVIDIA #GitHub #SQL Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • How GitHub secures open source

    · 31 min

    For the past six years, the GitHub Security Lab has worked to secure the open source ecosystem, surfacing practical principles that protect modern software supply chains. In this GitHub Universe 2026 session, Bas Alberts and Xavier René-Corail share what succeeded, what didn't, and why keeping security simple, engaging, and social makes vulnerability remediation stick across communities. Discover how tools like Dependabot, GitHub Secret Protection, and GitHub Code Security unite with AI agents to magnify collective security intelligence. Learn how the recent wave of AI is reshaping open-source security and how to safeguard your own repositories. Speakers: Bas Alberts, Principal Security Researcher, GitHub Xavier René-Corail, Sr. Dir, Security Research, GitHub Watch more videos from GitHub Universe 2026: https://www.youtube.com/watch?v=AArI948SDz8&list=PLENrlACZ7mnU — CHAPTERS — 00:00 Introduction to GitHub Security Lab 00:38 The burden of open source security 02:20 Three imbalances in open source security 04:16 AI's impact on open source security 07:39 Principle 1: make security easy 13:01 Securing the software supply chain 22:12 Principle 2: make security delicious 25:33 Principle 3: make security social 29:40 Practical next steps for security #GitHubUniverse #OpenSource #CyberSecurity Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • The hidden security risk of running AI agents without boundaries

    · 35 sec

    When executive pressure to adopt AI meets everyday workplace tools, security boundaries are often the first thing to disappear. In this clip from our interview with cybersecurity researcher Niels Provos, learn why installing autonomous AI agents with unrestricted access to your email, calendar, and data creates major enterprise risks. Many third-party agent skills can harbor hidden malicious behavior, turning convenience into a serious vulnerability. Watch the full interview on the GitHub channel to explore how to secure autonomous workflows safely. #AI #Security #AIAgents Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • Four days, zero lines: the AI force multiplier with GitHub Copilot

    · 14 min

    How do you clear a massive governance backlog without destroying developer velocity? In just four days, Jeff Doolittle of Trimble used GitHub Copilot to build an automated system and rapidly clear the backlog without manually writing a single line of code. In this GitHub Universe 2026 session, you’ll learn how to use AI not just as a coding assistant, but as an architectural force multiplier. You'll leave knowing how to combine automated GitHub Actions with custom Copilot prompts to eliminate developer toil, easily enforce remediation lifecycles, and tackle technical debt across your engineering organization. Speaker: Jeff Doolittle, Distinguished Engineer, Principal Architect, Trimble Watch more videos from GitHub Universe 2026: https://www.youtube.com/watch?v=AArI948SDz8&list=PLENrlACZ7mnU — CHAPTERS — 00:00 The 436 repository compliance backlog 01:23 The friction of deferred organizational debt 02:29 Building OSS overseer with GitHub Copilot 04:13 Prioritizing human judgment over code generation 05:25 Designing trust and reversible enforcement 06:40 Lowering friction with self-service remediation 08:38 Achieving 100% compliance across repositories 10:29 Turning automation into a force multiplier 12:14 Architectural strategy for eliminating technical debt #GitHubUniverse #GitHubCopilot #GitHubActions Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • The view from the labs: What's next for AI-assisted development

    · 26 min

    The people building frontier AI models see early signals about where capabilities are heading and which developer skills and workflows are about to matter most. Recorded live at GitHub Universe 2026, this panel brings together leaders from Anthropic, OpenAI, Google Cloud, and GitHub Copilot for a forward-looking discussion on where AI-assisted development is heading over the next two years. Learn how frontier models, autonomous agents, and MCP integrations will reshape software architecture, code security, and everyday workflows. Explore more sessions and announcements at https://githubuniverse.com Speakers: April Leonard, VP of Engineering for GitHub Copilot, GitHub Angela Jiang, Head of Product, Claude Platform, Anthropic Richard Seroter, Senior Director and Chief Evangelist, Google Cloud Rohan Varma, Product Lead, Enterprise Agents, OpenAI Watch more videos from GitHub Universe 2026: https://www.youtube.com/watch?v=AArI948SDz8&list=PLENrlACZ7mnU — CHAPTERS — 00:00 Welcome to GitHub Universe 2026 01:10 Surprising AI development trends 03:46 AI vs. human judgment in tasks 10:13 Optimism for software development 14:24 Over and under-invested AI areas 24:11 Future developer skills 26:06 Judgment remains key #GitHubUniverse #GitHubCopilot #AIAgents Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • Security in 60 Seconds: Malicious Dependencies

    · 45 sec

    A vulnerability is a mistake. Malware is on purpose. In this Security in 60 Seconds short, Carlin Cherry explains how attackers get malicious code into your dependencies: they steal a maintainer's account and poison a package you already trust, or publish a lookalike name and wait for a typo. Malware can run the moment you install it, before your code ever calls it. Block known malicious packages before they're installed with the GitHub package firewall, and use Dependabot to get alerted if malware is already in your dependencies. Learn more about Dependabot malware alerts: https://gh.io/dependabot-malware Music credits: ahpook: https://ahpook.bandcamp.com/track/a #Security #Malware #GitHub Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • LangChain Deep Agents

    · 49 min

    Deep Agents is an open source agent harness — an opinionated agent that runs out of the box. Extend, override, or replace any piece.

    Not rated yet
  • Meet Valkey | Open Source Friday

    · 55 min

    Join us for Open Source Friday with Madelyn Olson, Valkey co-creator, maintainer, and Technical Steering Committee member. Valkey is an open source, high-performance key-value data store used for caching, real-time applications, and workloads that need fast access to data. We’ll explore what it does, the story behind the project, and how its community is shaping its future. Learn more and contribute at https://github.com/valkey-io/valkey.

    Not rated yet
  • How a personal AI productivity hack became Slack's internal tool

    · 19 min

    Frances Coronel, a product engineer at Slack, built a personal AI setup to work faster and shared it in a public channel. Engineers across the company started forking it without being asked. That organic pull grew into Slack's internal AI tool catalog: a single source of truth for Model Context Protocol (MCP) servers, skills, and GitHub Copilot agents, backed by an adoption dashboard tracking real usage data across teams. In this GitHub Universe 2026 session, Frances demos the catalog, shares six months of real adoption metrics, and shows how a personal productivity hack became org-wide infrastructure. You'll learn how to build an internal AI tool catalog on GitHub with Projects and Issues, measure adoption with real telemetry instead of surveys, and create the cultural conditions that make AI tooling spread on its own. Speakers: Frances Coronel, Senior Software Engineer, Slack Watch more videos from GitHub Universe 2026: https://www.youtube.com/watch?v=AArI948SDz8&list=PLENrlACZ7mnU — CHAPTERS — 00:00 Introduction & the AI setup mess 01:08 From personal hack to internal tool 02:24 Introducing the DevX PI catalog 03:55 Meet Frances Coronel 05:14 Addressing AI knowledge silos 06:57 Catalog: a single source of truth 10:33 Catalog architecture & growth 11:55 Experimentation & automation with AI 14:39 Accessing the catalog via Slack 16:16 Cultivating an AI-first culture 17:52 Recommendations for internal AI tools #GitHubUniverse #Slack #AITools Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • Niels Provos on creating bcrypt, defending Google, and securing AI agents

    · 26 min

    Sit down with legendary cybersecurity researcher Niels Provos as he reflects on three decades of breaking, building, and securing software. From sneaking into Canadian university labs to write exportable cryptography and co-authoring bcrypt to protecting billions of users with Google Safe Browsing, Niels shares the core principles behind durable software defense. Discover why he is developing Project Iron Curtain to protect autonomous AI agents against prompt injection and intent drift, and how modern model harnesses are locating decades-old bugs across open-source codebases. Explore his candid thoughts on open-source sustainability, the roots of the word hackathon, and the enduring Cicada 3301 puzzle. — CHAPTERS — 00:00 Early days and entering computer science 01:29 Discovering unix vulnerabilities and bcrypt 03:17 OpenBSD and the origin of hackathons 05:11 AI vulnerability discovery and iron curtain 07:30 Google safe browsing and search worms 09:57 Honeypots, honeyd, and agent security 14:45 Open source maintainers and software licensing 18:15 Cybersecurity EDM songs and music 21:24 The cicada 3301 mystery and steganography 24:39 Bladesmithing and mindfulness #Cybersecurity #OpenSource #GitHub Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • What is new in GitHub: October releases explained

    · 17 min

    October brought major updates across the GitHub ecosystem, but what do these changes actually mean for your team's day-to-day work? In this edition of the GitHub Changelog, join the team as they demystify "software factories" and break down practical tools inside the GitHub Copilot app. Explore how self-learning Copilot automations handle issue triage, how Copilot Projects orchestrates multi-repo work without local cloning, and how Copilot Fusion routes tasks across frontier models. Learn how to automate routine pipeline tasks so you can focus on building software. Links mentioned in the episode: Copilot Automations: https://gh.io/copilot-automations Copilot Memory: https://gh.io/copilot-memory Projects in the GitHub Copilot app: https://gh.io/copilot-projects Agent Merge: https://gh.io/agent-merge Migrating the Copilot runtime to Rust: https://gh.io/runtime-to-rust Copilot Fusion: https://gh.io/fusion All changelog updates: https://gh.io/changelog — CHAPTERS — 00:00 Welcome to the October releases 01:39 Demystifying software factories 02:56 Self-learning Copilot automations 08:22 Orchestrating multi-repo work with Copilot Projects 14:23 Engineering management in the age of agents 16:41 Copilot Fusion and frontier models #GitHub #GitHubCopilot #Automation Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • Stop waiting on your own pull requests: GitHub stacked PRs in practice

    · 13 min

    Big pull requests slow everyone down, creating review bottlenecks, stalling feedback loops, and disrupting developer momentum. In this GitHub Universe 2026 session, discover how GitHub stacked PRs allow you to split complex changes into smaller, dependent pull requests that move through review smoothly while maintaining full context. Watch as Sameen Karim from GitHub builds a stack with the GitHub CLI, conducts reviews on github.com, and merges each pull request as soon as it is approved. Leave with practical workflows you can apply directly to your team's repository today. Speakers: Sameen Karim, Senior Product Manager, GitHub Watch more videos from GitHub Universe 2026: https://www.youtube.com/watch?v=AArI948SDz8&list=PLENrlACZ7mnU — CHAPTERS — 00:00 Introduction to stacked pull requests 00:27 Understanding GitHub stacked PRs 02:11 GitHub stacked PRs is GA 03:05 Using the GitHub CLI for stacks 04:47 Reviewing stacked PRs on GitHub.com 06:14 Adding new PRs to a stack 08:10 Atomic merges and branch protection 10:31 Auto-merge and VS Code support 11:36 Fixing CI and stack rebase 12:15 Stacked PRs fully merged & next steps #GitHubUniverse #GitHub #PullRequests Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • What's worth building when AI can build anything?

    · 29 min

    AI can build almost anything you ask it to, which makes a harder question unavoidable: what's actually worth building? In this GitHub Universe 2026 conversation, Sue Black of Durham University and Kent C. Dodds of kody.codes make the case for building software deliberately rather than reflexively. This session explores what responsible software looks like and takes a deeper dive into the daily reality of shipping, choosing developer tools, and maintaining what is already built. You'll leave with a sharper set of questions to bring to your own work, along with a clearer sense of when development speed is worth it and when it isn't. Speakers: Kent C. Dodds, Product Engineer, kody.codes Sue Black, Professor of Computer Science and Technology Evangelist, Durham University Watch more videos from GitHub Universe 2026: https://www.youtube.com/watch?v=AArI948SDz8&list=PLENrlACZ7mnU — CHAPTERS — 00:00 Welcome to GitHub Universe 2026 00:22 What's worth building with AI? 01:06 Sue Black's journey in Technology 03:15 Kent C. Dodds' AI optimism & kodi 04:45 Understanding the ripple effect 07:44 Building with restraint in AI 10:30 Educating the next generation of developers 14:41 Ensuring software is fit for purpose 20:19 AI and diversity in tech 23:14 Invisible software & individual impact 28:25 The million-person impact challenge 29:08 Join the conversation & feedback #GitHubUniverse #SoftwareEngineering #OpenSource Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • Why GitHub stars don't pay the bills: inside commercial open source | S02E07 | The GitHub Podcast

    · 45 min

    In this episode of The GitHub Podcast, Andrea Griffiths and GPS are joined by the co-authors of the annual State of Commercial Open Source 2026 report: Matt Lavergne, a partner at VC firm Serena, and Sam Boysel, a data scientist with the Linux Foundation. Matt and Sam walk through what years of venture capital data on open source startups actually show: commercial open source companies raise money faster, close bigger rounds, and exit at significantly higher valuations than closed-source peers. They dig into which community and criticality signals actually matter instead, why the fear that “money ruins open source communities” mostly doesn’t hold up in the data, and how founders can build a business on top of an existing project without alienating maintainers, including real examples like pyannoteAI and MotherDuck. Finally, they share why open source founders turned out to be surprisingly optimistic about AI’s impact on their businesses. Links mentioned in this episode: Matt Lavergne on LinkedIn: https://www.linkedin.com/in/matthieulavergne/ Sam Boysel on LinkedIn: https://www.linkedin.com/in/sboysel/ State of Commercial Open Source Report: https://cossreport.com pyannoteAI: https://github.com/pyannote MotherDuck: https://motherduck.com Working in Public by Nadia Eghbal: https://www.librarything.com/work/25093316/book/187790380 — CHAPTERS — 00:00 Introduction to the GitHub Podcast 01:26 Meet the report co-authors 04:51 Venture capital and Open Source data 10:11 Community metrics and criticality signals 14:43 Evaluating startup signals and vanity metrics 23:09 Dispelling myths around money and Open Source 26:53 State of Commercial Open Source findings 31:30 Real-world examples: pyannoteAI and MotherDuck 37:23 Avoiding community alienation and forking risks 42:09 Where to find the report and conclusion #GitHubPodcast #OpenSource #SoftwareEngineering Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • 3D printing a custom microphone stand with GitHub Copilot

    · 1 min

    Can you use GitHub Copilot to customize physical 3D prints? After printing a standard DJI microphone stand, we turned to the GitHub Copilot app to see if an AI prompt could modify the 3D model directly instead of relying on manual CAD software. The result embedded clean GitHub platform icons across the entire handle, creating a custom textured grip in minutes. It turns out developer AI tools can handle creative physical projects in ways you might not expect. What is the most unexpected or unusual project you have tackled with GitHub Copilot? Let us know in the comments below. #GitHubCopilot #MicrophoneStand #3DPrinting Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • Inside the Microsoft Copilot Harness: Customizing AI Agents

    · 14 min

    In this episode, Andrea Griffiths sits down with Patrick Nikoletich to unpack the Microsoft Copilot harness. Discover how teams are using the harness for non-coding scenarios, autonomous software factories, and customizing the harness for custom agents. Patrick demos a Dockerized agent worker pool, explains credential-safe inference gateways, and shows how the Agent Host Protocol (AHP) tunnels CLI sessions into isolated containers. Explore what is coming in Copilot harness 2.0, from a Rust rewrite to direct Azure tunneling. Links mentioned in the episode: Microsoft Copilot harness: https://gh.io/harness Microsoft Copilot SDK: https://aka.ms/copilot-harness/sdk/repo Patrick's demo (harness builder + secure Aspire agent service): https://github.com/patniko/copilot-sdk-aspire Agent Host Protocol (AHP): https://github.com/microsoft/agent-host-protocol Local sandbox for agents: https://gh.io/local-sandbox Copilot SDK workshop: https://github.com/github/copilot-sdk-workshop #MicrosoftCopilotHarness #AIAgents #GitHub — CHAPTERS — 00:00 Introduction 01:05 From coding agents and personal assistants to fully autonomous agents 02:55 Designing a secure runtime for flexible agent deployments 04:52 Customizing the harness for three different use cases 08:11 Dockerized worker pools and security architecture 10:07 Agent Host Protocol and CLI tunnels 12:20 Direct Azure tunneling and open source access 13:27 What is coming in Copilot Harness 2.0 Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • A pixel dog that writes songs: lessons from my first MCP server with GitHub Copilot

    · 13 min

    It’s 2 a.m. You’re deep in a solo coding session, and your IDE doesn’t notice you haven’t moved in an hour, but the golden retriever on your desk does. In this GitHub Universe 2026 session, Yunika Liu introduces Coco, a pixel-art golden retriever that lives on a desktop window and an LED display to encourage you while you build. Discover how she used GitHub Copilot and Model Context Protocol (MCP) support to build a custom server featuring WebSocket sync, animation triggers, and music composition in just one week. Learn how anyone can connect AI coding agents to custom hardware and build their own MCP server. Speakers: Yunika Liu, Product Builder, Independent Watch more videos from GitHub Universe 2026: https://www.youtube.com/watch?v=AArI948SDz8&list=PLENrlACZ7mnU — CHAPTERS — 00:00 Meet Coco: the inspiration 01:14 Building a pixel-art golden retriever 02:20 GitHub Copilot & coco's music 05:23 Behind the scenes: MCP server 07:32 DJ Coco & hardware upgrades 09:55 Lessons from my first MCP server 12:14 Work-life balance & small joys #GitHubUniverse #GitHubCopilot #MCP Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • The hardware secrets behind the GitHub Universe badge

    · 2 min

    How did a simple conference lanyard tag evolve into a full-fledged portable computer running Doom? On the GitHub Podcast, Martin Woodward breaks down the engineering journey behind the GitHub Universe badge, from early e-ink prototypes built with Pimoroni to full color screens powered by the RP2040 chip. Discover how the hardware team solved real battery safety challenges and why they added an accelerometer to automatically flip the screen 180 degrees whenever you look down at it. #GitHubPodcast #GitHubUniverse #GitHub Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet
  • Key takeaways from GitHub's Octoverse report in 60 seconds

    · 1 min

    Almost half of all pull requests on GitHub are now started by AI agents, and 90% are merged within two weeks. In this 60-second recap of the Octoverse report, explore how software teams are reshaping their workflows and mixing multiple frontier models in GitHub Copilot. Learn why TypeScript continues to lead as the most popular language, plus a critical security warning on supply chain risks in developer marketplaces. #GitHub #Octoverse #GitHubCopilot Stay up-to-date on all things GitHub by connecting with us: YouTube: https://gh.io/subgithub Blog: https://github.blog X: https://twitter.com/github LinkedIn: https://linkedin.com/company/github Insider newsletter: https://resources.github.com/newsletter/ Instagram: https://www.instagram.com/github TikTok: https://www.tiktok.com/@github About GitHub It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com

    Not rated yet

More in Technology

See all Technology shows