GitHub

This #OpenSourceFriday, we're spotlighting E2B, open source infrastructure runtime environment transforming how developers build AI-powered agents and autonomous applications. E2B makes it easier for developers to create, run, and manage sandboxed, long-running cloud processes for agents and AI-native apps. E2B is built to be secure, scalable, and developer-friendly, enabling new possibilities in LLM-powered products with “Cloud for AI Agents.” Website: https://e2b.dev/ GitHub Repository: https://github.com/e2b-dev

Stop repeating your instructions. 🛑 Copilot now supports Agent Skills, the open standard by Anthropic. Package your specialized expertise into skills once and use them everywhere. Try it in: ✅ agent mode in Visual Studio Code Insiders ✅ Copilot coding agent ✅ Copilot CLI Here's how to get started. 👇 https://lnkd.in/guvZ6ded

Cassidy on the GitHub dev advocacy team is here to chat with you about your questions, and maybe even build a thing or two!

Join us for Rubber Duck Thursdays! A lighthearted and informal stream where we live code on some projects. This will be our last European-timezone-friendly stream of 2025. So this week, we'll build something to help us to look forward to 2026!

Gemini 3 Flash is now rolling out in public preview in GitHub Copilot. This model is ideal for tasks where speed is crucial. Try it out in Visual Studio Code👇 https://lnkd.in/edreda5g

Have an app idea but don't know where to start? Stop staring at a blank screen. 💻 We put together a guide on vibe coding with GitHub Copilot. It’s more than just "vibes." It’s about clearly articulating what you want so Copilot can handle the how of implementation. Check out the tutorial. ⬇️ https://lnkd.in/gRVp2pYG

💡 A tip for GitHub Copilot: It works best when you treat it less like a search engine and more like a new teammate. It can likely figure out what you are doing, but it doesn't know why you do it that way—unless you tell it. That's why custom instructions are so important. They document the institutional knowledge that usually lives in your team's heads: • The stack: specific versions and frameworks • The rules: linter preferences and "unwritten" style guides • The goal: what you are actually trying to build Here are 5 tips to help you write better instructions so you can spend less time correcting Copilot and more time building. 🚀 Get the guide. ⬇️ https://lnkd.in/g-TkXcSZ

Have you tried GitHub Copilot coding agent? 🤖 It acts like a peer developer that runs independently in the background, handling the tasks that slow you down: 🐛 Bug fixes 🧪 Test coverage ♻️ Refactoring It takes you from Issue ➡️ PR while you focus on the code that interests you most. Here's how to get started with agentic workflows. 🚀 https://lnkd.in/gh_QUJ24

It started as a small idea to connect AI models to developer workflows. It turned into one of the fastest-growing open standards in the industry. 🚀 Now, the Model Context Protocol is officially joining The Linux Foundation. Hear from the engineers and maintainers of GitHub, Microsoft, Anthropic, and OpenAI on the journey from day zero to now. 👇 https://lnkd.in/gddWtqsK

Agentic security is a conflict: You are handling non-deterministic outputs in a deterministic execution environment. To balance capability with safety in GitHub Copilot, we enforce three architectural principles: • Maximize interpretability • Minimize autonomy (Principle of Least Privilege) • Reduce anomalous behavior Take a deep dive into our threat model for hosted agents. ⬇️ https://lnkd.in/g6iUT_bj