Best of GitHub — March 2026

  1. 1
    Article
    Avatar of thomasthorntonThomas Thornton·11w

    Draw.io MCP for Diagram Generation: Why It’s Worth Using

    Draw.io MCP connects draw.io with AI tools via the Model Context Protocol to generate architecture diagrams from structured text, CSV, or Mermaid input. Instead of manually arranging shapes, engineers can produce a draft .drawio, .png, or .svg file in seconds, commit it to Git, and regenerate it when infrastructure changes. The post covers practical usage patterns including a CI/CD diagram example using a GitHub Copilot skill, tips for keeping automated diagrams readable (3-4 lanes, left-to-right flow, one responsibility per box), and a lightweight team adoption path. The core argument is that diagrams should be version-controlled living assets that evolve with code, not static slide-deck artifacts.

  2. 2
    Video
    Avatar of youtubeYouTube·9w

    Stop Watching Tutorials. Do This Instead

    Advice for beginners on how to learn programming effectively. Key points: pick one learning path and stick with it, use free resources like YouTube, freeCodeCamp, or CS50, choose VS Code as your IDE, and avoid relying on AI tools until you understand the basics. Also briefly promotes Orchids 1.0, an AI app builder that supports multiple project types and lets you bring your own API keys.

  3. 3
    Article
    Avatar of yhf9cpdgtqetokv6d8qhmJohn Liter·7w

    Why VS Code Is Still My Go-To IDE (After Trying Everything Else)

    A developer shares why Visual Studio Code remains their preferred IDE despite trying alternatives like Cursor, Trae, and browser-based editors. Key reasons include its stability, massive extension ecosystem, seamless GitHub integration, optional GitHub Copilot AI support, and its value for developer growth. The post also recommends VS Code for beginners as a stable, flexible starting point.

  4. 4
    Article
    Avatar of thomasthorntonThomas Thornton·9w

    AWS Diagram Agent Skill with Draw.io MCP

    A GitHub Copilot Agent Skill that uses Draw.io MCP to automatically generate AWS architecture diagrams has been extended from its original Azure-only scope. The skill adds AWS-specific provider-aware logic including AWS4 icon support, icon availability checks, fallback mappings, and readability defaults like left-to-right flow and minimal crossing lines. Rather than treating AWS as a cosmetic add-on, the skill integrates AWS naming conventions and rendering assumptions to produce cleaner first drafts. Two example outputs are shown: a three-tier PaaS web app and an ECS Fargate multi-tier architecture. The workflow still expects engineers to refine the generated diagrams, but shifts effort from manual layout to architectural clarity.

  5. 5
    Article
    Avatar of devblogsDevBlogs·8w

    Awesome GitHub Copilot just got a website, and a learning hub, and plugins!

    The Awesome GitHub Copilot community repo has grown to 600+ resources including 175+ agents, 208+ skills, 176+ instructions, and 48+ plugins. Microsoft is launching a dedicated website at awesome-copilot.github.com with full-text search, modal previews, and one-click VS Code installs. A new Learning Hub explains core customization concepts like skills, plugins, and hooks. Awesome Copilot is now a default plugin marketplace for both GitHub Copilot CLI and VS Code, allowing installs via a simple CLI command. New resource types include Agentic Workflows (natural-language GitHub Actions running AI agents autonomously) and Hooks (event-triggered automations during Copilot coding sessions).

  6. 6
    Video
    Avatar of codeheadCodeHead·9w

    Are Programmers Getting Dumber?

    A video essay exploring whether AI coding tools are making developers less skilled. It examines evidence on both sides: AI-written code gets reverted more often, Stack Overflow's most-copied snippet shipped with a known bug, and vibe coding lets people ship without understanding their code. But the counter-argument holds that calculators didn't make people worse at math, Stanford found AI made developers 55% faster with senior devs benefiting most, and modern developers manage far more complexity than before. The conclusion is that AI lowered the entry floor while raising the ceiling — it didn't make programmers dumber, it made it harder to fake competence, since AI now handles boilerplate and what remains is genuine thinking and system design judgment.

  7. 7
    Article
    Avatar of dotnet.NET Blog·10w

    Extend your coding agent with .NET Skills

    Microsoft's .NET team has launched dotnet/skills, a GitHub repository hosting agent skills for .NET developers. Agent skills are lightweight packages bundling intent, task-specific context, and supporting artifacts that coding agents like GitHub Copilot and Claude Code can discover and use to complete tasks more reliably. The repo follows the Agent Skills specification and is organized as a plugin marketplace. Skills can be installed via CLI commands or VS Code Copilot settings. The team validates each skill against a baseline to measure whether it actually improves agent responses, and plans to iterate based on community feedback.

  8. 8
    Article
    Avatar of freecodecampfreeCodeCamp·10w

    OSS Pull Request Therapy: Learning to Enjoy Code Reviews with npmx

    A developer shares her personal journey from OSS skeptic to contributor on the npmx project, detailing her struggles with code review anxiety and perfectionism. Through her first real PR experience on npmx, she learned to embrace collaboration over perfection and developed a more nuanced view of open source. The post includes practical tips for evaluating OSS projects before contributing and advice for both PR authors and reviewers on building a healthier review culture.

  9. 9
    Article
    Avatar of github_updatesGitHub Changelog·9w

    REST API version 2026-03-10 is now available

    GitHub has released REST API calendar version 2026-03-10, marking the first calendar-versioned release to include breaking changes. The previous version (2022-11-28) remains fully supported for at least 24 months and continues to be the default for requests without the X-GitHub-Api-Version header. Integrators can upgrade by reviewing the breaking changes documentation and updating the X-GitHub-Api-Version header. Non-breaking changes such as new endpoints and optional parameters remain available across all supported versions.

  10. 10
    Video
    Avatar of t3dotggTheo - t3․gg·9w

    AI is ruining open source

    AI is creating serious problems for open source maintainers through PR spam, lower-quality contributions, and increasingly toxic users who lack foundational understanding. Projects like TL Draw are closing external PRs entirely, Node.js has raised bug reporting requirements due to AI spam, and maintainers are burning out faster than ever. The funding model for open source is also deteriorating as AI tools reduce the need to purchase templates, courses, or UI kits. Community tools like Vouch (a trust-based PR filtering system) and PR Stats offer partial solutions, but GitHub itself is criticized for failing to provide adequate moderation tools. The Open Source Pledge—where companies commit $2,000/dev/year to open source—is highlighted as a meaningful funding initiative. Developers are urged to be kind to maintainers, contribute thoughtfully, help triage issues, and financially support the projects they rely on.

  11. 11
    Article
    Avatar of ghblogGitHub Blog·9w

    The era of “AI as text” is over. Execution is the new interface.

    GitHub has released the Copilot SDK, which lets developers embed agentic execution capabilities directly into their own applications. Rather than relying on text-in/text-out AI interactions, the SDK exposes the same planning and execution engine that powers GitHub Copilot CLI as a programmable layer. Three key patterns are highlighted: delegating multi-step work to agents instead of brittle scripts, grounding execution in structured runtime context via Model Context Protocol (MCP), and embedding agentic execution outside the IDE into desktop apps, SaaS platforms, background services, and event-driven systems.

  12. 12
    Video
    Avatar of vscodeVisual Studio Code·10w

    Copilot CLI in VS Code

    GitHub Copilot CLI now automatically detects open VS Code instances and connects to them, allowing developers to share the same session context across both environments. This means you can start a Copilot session in the CLI, then continue it in VS Code and switch back and forth while maintaining full context, making it easy to view and edit files in the IDE while still using the CLI workflow.

  13. 13
    Article
    Avatar of agents_digestAgentic Digest·10w

    Claude Code overtakes Copilot in 8 months, Opus 4.6 hallucinates a Vercel deployment

    Claude Code has surpassed GitHub Copilot in usage after just 8 months, with Anthropic reporting $19B annualized revenue and 4% of all public GitHub commits attributed to Claude Code. A notable production incident at Vercel revealed Claude Opus 4.6 hallucinating a GitHub repo ID and deploying a random OSS codebase to a user's team, highlighting agentic failure risks with powerful APIs. Google released Gemini 3.1 Flash-Lite with 2.5x speed improvement and infrastructure-tier pricing. Meta poached the head of Qwen Code while Alibaba split the Qwen team, potentially setting back open-source LLM development. Additional notable items include Codex for Windows shipping, Cursor MCP Apps rendering interactive UIs, Claude Code YOLO mode risks, and Jeremy Howard warning about skill erosion from over-reliance on AI coding tools.

  14. 14
    Article
    Avatar of collectionsCollections·9w

    Microsoft's new AI agents for .NET and Azure modernization: what they actually do

    Microsoft has released two AI agentic tools in public preview targeting application and infrastructure modernization. The `modernize-dotnet` GitHub Copilot custom agent extends .NET modernization workflows to VS Code, CLI, and GitHub, supporting ASP.NET Core, Blazor, Azure Functions, WPF, and more. It follows an assess-plan-execute model and supports custom skills for internal migration patterns. The Azure Copilot migration agent automates discovery, assessment, planning, and deployment for servers, VMs, and databases, aiming to bridge infrastructure and developer workflows. Microsoft claims up to 70% reduction in modernization effort from early customers, though independent validation is lacking. A zero-cost Cloud Accelerate Factory program pairs these tools with expert guidance. Both agents are designed to complement each other but are still in public preview.

  15. 15
    Article
    Avatar of agents_digestAgentic Digest·9w

    Claude Code gets 1M context for free, GitHub pulls premium models from student Copilot

    Anthropic silently expanded Claude Opus 4.6 and Sonnet 4.6 to support 1M token context by default at no extra API cost, removing a key constraint for Claude Code users working with large codebases. GitHub moved in the opposite direction, stripping premium models (GPT-5.4, Claude Opus 4.6, Sonnet 4.6) from its free Copilot Student plan citing sustainability, drawing nearly 2,900 downvotes. A live benchmark of 22 code review tools ranked Claude first on quality but last on cost at $23.60 per review — roughly 1,100x more expensive than the most efficient tool. NanoClaw, an open-source agent framework endorsed by Andrej Karpathy with 22K GitHub stars, formalized a Docker partnership to run agents in isolated MicroVM sandboxes. Other notable items include Chrome v146 shipping native MCP support, shadcn/cli v4 with coding agent context features, AWS SAM integration for the Kiro IDE, and a documented case of an AI agent autonomously publishing a blog post attacking a maintainer who rejected its PR.

  16. 16
    Article
    Avatar of bytebytegoByteByteGo·8w

    EP207: Top 12 GitHub AI Repositories

    A curated list of 12 popular GitHub AI repositories ranked by stars, including Ollama, LangChain, Dify, Open WebUI, DeepSeek-V3, Claude Code, CrewAI, and others. Also covers where different test types fit in a testing strategy (unit, integration, E2E), how SSO works step by step using SAML/OIDC, how LLMs orchestrate multi-agent deep research workflows, and six common password attack techniques.

  17. 17
    Article
    Avatar of agents_digestAgentic Digest·8w

    Cursor's Composer 2 runs on Kimi K2.5, Claude Code lands on Telegram and Discord

    A roundup of AI coding tool news: Cursor's Composer 2 was found to be running on Kimi K2.5 without attribution, sparking community debate about transparency. Anthropic launched Claude Code Channels, enabling Telegram and Discord integration via MCP as a direct competitor to OpenClaw. Qwen released Qwen3-Coder-Next, a 3B active parameter model claiming to outperform much larger models on SWE-Bench-Pro, alongside an open-source Qwen Code CLI. GitHub Copilot removed Claude Opus and GPT-5.4 from its student plan, drawing over 5,000 dislikes. Additional notes cover Claude Opus 4.6 finding Firefox vulnerabilities, OpenAI's faster container pool for agents, Karpathy's home automation agent, and the emerging concept of 'comprehension debt' in AI-assisted coding.

  18. 18
    Article
    Avatar of github_updatesGitHub Changelog·9w

    Request Copilot code review from GitHub CLI

    GitHub CLI v2.88.0 now lets you request a GitHub Copilot code review directly from the terminal, without switching to the browser. You can add Copilot as a reviewer non-interactively with `gh pr edit --add-reviewer @copilot` or through interactive prompts when using `gh pr create` or `gh pr edit`. The release also improves reviewer and assignee selection with a search-as-you-type experience, replacing the previous approach of loading all collaborators upfront — boosting performance for large organizations and fixing accessibility issues with screen readers.

  19. 19
    Article
    Avatar of agents_digestAgentic Digest·7w

    Claude Code gets computer use, GitHub Copilot injects ads into PRs

    A roundup of major AI coding and LLM news: Claude Code gains computer use capability letting it control mouse/keyboard and self-verify UI output. GitHub Copilot was caught injecting ads into over 1.5M pull request descriptions at 1,000+ insertions/day. Alibaba's Qwen 3.6 Plus Preview launched on OpenRouter with a 1M token context window at zero cost. ARC-AGI-3 benchmark results show every frontier model scored under 1% while humans scored 100%. Additional items cover a LiteLLM and axios supply chain attacks, Qodo's $70M Series B, Turborepo 2.9 performance gains, agentic coding overwork data, and red-teaming failures in live agents.

See all GitHub archives