Lead AI Dev’s Post

There’s something about running agent operations via CLI that just hits different. I’ve swapped from the Copilot IDE extension in VSCode to using my license through OpenCode. It feels more "natural" to keep advanced agentic workflows where the rest of my advanced tools live: the terminal. Less distraction from the UI, more focus on the logic and the agents. Highly recommend it for those who prefer the command line over the "auto-complete" experience. https://lnkd.in/ePbNAJN5 #SoftwareEngineering #Terminal #AI #CTOlife

GitHub Copilot is not just another tool for developers. To create meaningful enterprise outcomes, organizations need to invest in enablement, standardize workflows, and measure impact over time. In this Lantern Minute, Head of GitHub AI Solutions Esteban Garcia shares why treating Copilot as a long-term capability is key to unlocking durable, AI-driven innovation velocity.

🤖 One of GitHub's most interesting updates this week is happening in the CLI: GitHub Copilot CLI now supports BYOK and local models⚡ What that means: ▶️ teams can connect their own model provider ▶️ they can also run fully local models ▶️ GitHub-hosted routing is no longer the only option ▶️ authentication is optional when using your own provider Why this matters: ✅ more flexibility in model choice ✅ more control over LLM spend ✅ better fit for restricted or air-gapped environments ✅ easier alignment with enterprise infrastructure choices This is a meaningful step for teams that want the Copilot CLI experience, but with more control over how and where inference happens. #GitHub #GitHubCopilot #CLI #AI #DeveloperTools

🚀 What if your GitHub repo could improve itself? Join us for GitHub Agentic Workflows: Automation That Actually Reads the Room and see how AI agents can autonomously triage issues, fix CI failures, update docs, and improve tests—with just a markdown file and one command. 🔍 In this live demo, Ari LiVigni, Senior Learning Advocate at GitHub, will walk through: - From minimal workflow file → AI agent in action - Safe, sandboxed pipelines that deliver ready‑to‑review PRs - How to keep your repo on autopilot while staying fully in control 📅 May 7, 2026 ⏰ 9:00–10:00 AM PT 🎥 Live and on-demand at any time after wrap 👉 Register now: https://msft.it/6040QxqQE 📍 Explore the series: https://msft.it/6041QxqQ1 #MicrosoftReactor #learnconnectbuild #GitHubCopilot #AgenticWorkflows #AgentOrchestration #GHCP #Fleet

GitHub Copilot gets called an autocomplete tool. That undersells it significantly. Yes, it suggests code inline as you type. But the more interesting capability is what it does at the workspace level — it can read your entire codebase, answer questions about it, explain unfamiliar code, and act as an agent that spans multiple files. The numbers back up the adoption: 1.8M+ paid subscribers, integrations across every major IDE, and deep GitHub ecosystem access that no third-party coding agent can replicate natively. If you're evaluating AI coding tools, GitHub Copilot is the baseline everything else gets compared to. Full profile and alternatives → https://lnkd.in/ewkPwZeA

Big upgrade for local AI workflows Ollama now supports working with GitHub Copilot CLI, bringing powerful repo-aware capabilities right into your terminal. Just run: ollama launch copilot With this integration, you can: • Explore GitHub issues and pull requests without leaving your terminal • Search repositories using labels like “good first issue” or “help wanted” • Turn an issue into a clear execution plan • Let Copilot suggest edits and run commands in your project • Navigate and understand unfamiliar codebases faster This means you can combine local models with real repository context, making your development workflow faster and more private. No switching tabs. No breaking focus. Just building. Are you using Ollama with Copilot CLI yet? Curious to hear how it’s working for you.

Disabling Copilot code review in your repositories If there are Copilot Pro or Copilot Pro+ users with access to your enterprise's repositories, they will be able to use Copilot code review and will not be restricted by your policies. Alternatively, you can disable the agent for all repositories owned by your enterprise. Navigate to your enterprise. For example, from the Enterprises page on GitHub.com. At the top of the page, click AI controls. In the "Installed Agents" section, click Copilot code review. In the "Copilot code review" section, next to "Block Copilot code review in all enterprise repositories", click the toggle. https://lnkd.in/gsTBcmUP

I kept running into the same 𝙥𝙧𝙤𝙗𝙡𝙚𝙢 𝙬𝙞𝙩𝙝 𝙂𝙞𝙩𝙃𝙪𝙗 𝘾𝙤𝙥𝙞𝙡𝙤𝙩: I could see that I was using it a lot. I could not clearly see which repo/workspace was driving that usage. So I built a local-first 𝘾𝙤𝙥𝙞𝙡𝙤𝙩 𝙪𝙨𝙖𝙜𝙚 𝙩𝙤𝙤𝙡𝙠𝙞𝙩. It has two parts: • a "𝘝𝘚 𝘊𝘰𝘥𝘦 𝘦𝘹𝘵𝘦𝘯𝘴𝘪𝘰𝘯" that shows token usage directly inside the editor • a "𝘴𝘵𝘢𝘯𝘥𝘢𝘭𝘰𝘯𝘦 𝘊𝘓𝘐 + 𝘥𝘢𝘴𝘩𝘣𝘰𝘢𝘳𝘥" for repo/workspace-level analytics, trends, model usage, and premium request estimates The goal was not perfect billing reconciliation. It was 𝙥𝙧𝙖𝙘𝙩𝙞𝙘𝙖𝙡 𝙫𝙞𝙨𝙞𝙗𝙞𝙡𝙞𝙩𝙮: better usage awareness, easier debugging, and clearer per-project attribution when working across multiple systems in parallel. Open source: https://lnkd.in/dzRdyvxM I’d love feedback from heavy Copilot users: what’s the one usage metric you wish GitHub exposed more clearly today? #GitHubCopilot #VSCode #OpenSource

𝐂𝐨𝐩𝐢𝐥𝐨𝐭'𝐬 𝐍𝐞𝐰 𝐁𝐢𝐥𝐥𝐢𝐧𝐠 𝐑ule: Heads up, tech leaders and developers! GitHub is moving Copilot to a usage-based model starting June 1st, using new 'AI Credits.' 𝑾𝒉𝒂𝒕 𝒕𝒉𝒊𝒔 𝒎𝒆𝒂𝒏𝒔 : Standard code completions won't consume credits, but advanced features like agentic workflows and code reviews will. Reviews will also use GitHub Actions minutes. 𝑲𝒆𝒚 𝑻𝒂𝒌𝒆𝒂𝒘𝒂𝒚: Existing monthly plans migrate soon; annual plans stay, but the cost calculation changes. It's time to start planning for more granular spending management.

#GitHub Copilot CLI has reached General Availability, marking a milestone in bringing generative AI across the entire software development lifecycle. The move signals GitHub’s push to make the terminal a first-class surface for AI-assisted development. Learn more: https://bit.ly/4dMdgF2 #InfoQ #DevOps #Copilot #AIcoding #AIAssistedCoding