# GitHub Copilot CLI Terminal-native AI coding assistant from GitHub Copilot with agentic capabilities for command-line workflows. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## GitHub and Anthropic used their own agents for major Rust rewrites -- with very different playbooks DevFeed: [GitHub and Anthropic used their own agents for major Rust rewrites -- with very different playbooks]() Original publisher: [Read original article]() Author: Paul Sawers Published: 2026-09-17T18:06:03Z Content type: article Language: en Sources: [The New Stack]() Topics: [GitHub](), [Rust](), [AI-assisted coding](), [GitHub Copilot app](), [GitHub Copilot CLI](), [rustrover]() Tags: [ai](), [ai-agents](), [bun](), [claude](), [coding](), [coding-agents](), [github](), [github-copilot](), [github-copilot-app](), [memory-management](), [programming-languages](), [rust]() ### AI overview The article examines GitHub's rewrite of the GitHub Copilot agent runtime from TypeScript on Node.js and V8 to more than 800,000 lines of Rust, using GitHub's Copilot agents across incrementally merged pull requests. It compares this with Anthropic's Bun rewrite, where a pre-release Claude model helped convert more than half a million lines of Zig to Rust amid memory-management problems. ### Source excerpt Rust is seemingly the language of the moment, with open-source projects and companies forming an orderly queue to move core The post GitHub and Anthropic used their own agents for major Rust rewrites -- with very different playbooks appeared first on The New Stack. ## Visual Studio Code 1.139 (Insiders) DevFeed: [Visual Studio Code 1.139 (Insiders)]() Original publisher: [Read original article]() Author: Visual Studio Code Team Published: 2026-09-16T13:22:12.332134Z Content type: release Language: en Sources: [Visual Studio Code - Code Editing. Redefined.]() Topics: [Visual Studio Code](), [releases](), [Release notes](), [GitHub Copilot CLI](), [Command-line interface](), [CSS]() Tags: [extension](), [github](), [github-copilot](), [release](), [release-notes](), [terminal](), [visual-studio-code](), [vs-code]() ### AI overview Visual Studio Code 1.139 (Insiders) release notes describe updates added between September 11 and September 15, 2026. Changes include Cargo completions in terminal suggestions, experimental Agent Merge support for creating and reviewing pull requests, CSS color previews, searchable Remote workspace menus, improved Copilot context routing, and other editor and API updates. ### Source excerpt Learn what is new in Visual Studio Code 1.139 (Insiders) Read the full article ## Porting a Discord Bot to Microsoft Teams with GitHub Copilot CLI DevFeed: [Porting a Discord Bot to Microsoft Teams with GitHub Copilot CLI]() Original publisher: [Read original article]() Author: Daniel Doubrovkine (dblock@dblock.org) Published: 2026-09-16T00:00:00Z Content type: article Language: en Sources: [Daniel Doubrovkine]() Topics: [GitHub Copilot CLI](), [Microsoft Teams](), [Artificial Intelligence](), [Discord](), [AdventureX 2025]() Tags: [ai](), [discord](), [github-copilot-cli](), [hackathon](), [microsoft-teams](), [porting](), [ruby](), [strava]() ### AI overview The article compares a manual 2023 port of a Strava chat bot from Slack to Discord with a 2026 port to Microsoft Teams completed with GitHub Copilot CLI. The Teams port took three days and involved authentication, app-manifest, tenant distribution, and Azure setup work. ### Source excerpt Slava (slack-strava) connects a Strava account to a chat and posts a card for every activity, complete with map, pace, and elevation, plus commands like connect, disconnect, stats, and leaderboard. In 2023 I ported Slava to Discord by hand, evening by evening over about three weeks, and it took most of that stretch to get a working bot called Strada (discord-strava). This week I ported the same app to Microsoft Teams as Strata (teams-strava) in 3 days instead of the 3 weeks the Discord port took, using time carved out during the Microsoft Global Hackathon. By "I", I mean GitHub Copilot CLI and I. The 2023 Baseline discord-strava's git history is a fair record of how long a manual port takes. The first commit, "Initial fork from slack-strava," landed July 30, 2023. "Most interactions working" was three days later. Getting install/help/error-handling polish took through August 20: 2023-07-30 23:56 Initial fork from slack-strava. 2023-08-02 23:46 Most interactions working. 2023-08-03 06:18 Remove PNG retrieval, Discord displays redirects correctly. 2023-08-03 06:26 Removed clubs. 2023-08-03 08:28 Fixed model specs. 2023-08-03 18:20 Fix API specs. 2023-08-04 19:44 Fix command specs. ... 2023-08-08 10:34 Countinously poll with 1 minute intervals. 2023-08-20 22:59 Improved install button and text. 20 commits spread across 9 evenings over roughly three weeks (there's a real job and a life in between those timestamps). All hand-typed, with GitHub Copilot's inline autocomplete helping the way it helped everyone in 2023, but no agent driving the actual porting work. The 2026 Port teams-strava's git history is a single continuous Copilot CLI session, 107 conversational turns over three calendar days, and the timestamps compress dramatically: 2026-09-14 11:05 Initial port of discord-strava to Microsoft Teams 2026-09-14 16:39 Fix local dev setup and personal-scope install handling 2026-09-14 16:43 Fix 400 error replying to personal-scope install notice 2026-09-15 08:29 Document ## Why Short AI Coding Prompts Can Cost You More Time DevFeed: [Why Short AI Coding Prompts Can Cost You More Time]() Original publisher: [Read original article]() Author: Dean Hume Published: 2026-09-03T09:17:56Z Content type: opinion Language: en Sources: [Dean Hume]() Topics: [Prompt Engineering](), [ai-coding](), [GitHub Copilot](), [Artificial Intelligence](), [Agent Harness](), [GitHub Copilot CLI](), [Testing]() Tags: [agent-harness](), [ai](), [ai-coding](), [coding](), [copilot](), [github-copilot](), [prompt](), [testing]() ### AI overview This opinion article connects GitHub Copilot team's findings about compressing tool output with everyday AI coding prompts. It argues that optimizing a visible step, such as shortening a response or prompt, can increase total time and cost when missing details force follow-up questions, reruns, or recovery work. It recommends giving coding assistants the full problem and relevant source material, and treating instruction files carefully because rewriting guidance can change agent behavior. ### Source excerpt Ever tried to save time by keeping a prompt short - only to spend the next ten minutes answering follow-up questions because the AI didn't have what it needed? Yeah, me too. I recently came across a really interesting post from the GitHub Copilot team about making ## How we make AI coding more cost efficient without sacrificing task quality DevFeed: [How we make AI coding more cost efficient without sacrificing task quality]() Original publisher: [Read original article]() Author: Erik Kristensen Published: 2026-09-02T18:00:00Z Content type: article Language: en Sources: [GitHub](), [GitHub Engineering]() Topics: [GitHub Copilot](), [AI-assisted coding](), [GitHub Copilot CLI](), [coding](), [GitHub Copilot app](), [GitHub Copilot code review]() Tags: [agentic-ai](), [agentic-coding](), [ai](), [ai-coding](), [ai-ml](), [architecture-optimization](), [benchmarks](), [compression](), [cost](), [engineering](), [experiments](), [github-copilot](), [github-copilot-cli](), [github-copilot-code-review](), [llms](), [prompt-engineering]() ### AI overview GitHub Copilot's efficiency work focuses on total task cost and duration rather than minimizing tokens in individual tool responses. The article describes evaluating changes with coding benchmarks and controlled experiments, and explains that overly compressed output can cause agents to repeat work. ### Source excerpt Why shorter outputs can cost more, and how GitHub Copilot reduces wasted work across the complete coding task. The post How we make AI coding more cost efficient without sacrificing task quality appeared first on The GitHub Blog. ## Visual Studio Code 1.133 DevFeed: [Visual Studio Code 1.133]() Original publisher: [Read original article]() Author: Visual Studio Code Team Published: 2026-08-12T17:00:00Z Content type: release Language: en Sources: [Visual Studio Code - Code Editing. Redefined.]() Topics: [Visual Studio Code](), [GitHub Copilot CLI](), [GitHub Copilot app](), [MCP Server](), [SDKs](), [API keys](), [EJS]() Tags: [api](), [claude](), [copilot](), [github-copilot](), [html](), [manifest](), [mcp-server](), [plugin](), [plugins](), [release](), [sdk](), [visual-studio](), [vs-code]() ### AI overview Visual Studio Code 1.133 introduces more flexible Claude sessions, including provider switching between turns and API-key access when GitHub sign-in is unavailable. It also adds an agent host for sharing sessions across VS Code windows, support for the Agent Plugins standard, and automatic reloading for HTML previews. ### Source excerpt Learn what's new in Visual Studio Code 1.133 Read the full article ## Generating AI Descriptions of Automated Pull Requests DevFeed: [Generating AI Descriptions of Automated Pull Requests]() Original publisher: [Read original article]() Author: Daniel Doubrovkine (dblock@dblock.org) Published: 2026-08-11T00:00:00Z Content type: tutorial Language: en Sources: [Daniel Doubrovkine]() Topics: [GitHub Copilot CLI](), [GitHub Actions](), [GitHub Copilot](), [Large Language Model](), [Ruby](), [Slack](), [changelog](), [Pull Request](), [Open Source](), [JSON](), [YAML]() Tags: [ai](), [automated](), [changelog](), [ci](), [cli](), [copilot](), [github](), [github-actions](), [github-copilot](), [github-copilot-cli](), [json](), [llm](), [open-source](), [pull-request](), [pull-requests](), [ruby](), [yaml]() ### AI overview A tutorial explains how the maintainer of the slack-ruby-client library uses a scheduled GitHub Actions workflow and GitHub Copilot CLI to generate meaningful commit messages, pull request bodies, and CHANGELOG entries from diffs of regenerated Slack API code. It also covers YAML indentation, prompt files, response logging, and extracting a JSON result from Copilot CLI output. ### Source excerpt The slack-ruby-client library, an open source Ruby gem I maintain, runs a scheduled GitHub Actions workflow that regenerates code from Slack's API definitions and opens a pull request with the diff. The commit message and CHANGELOG entry used to be a generic "Update API (2026-08-11)", which told a reviewer nothing about what actually changed. Here's how we taught the workflow to describe its own diffs, using GitHub Copilot CLI, which open source maintainers can get for free. The Idea The workflow already computes a diff before opening the pull request. Instead of a boilerplate commit message, we pipe that diff through an LLM and ask it to summarize what changed, then use the response as the commit message and PR body. - name: Check for changes id: changes run: | if git diff --quiet; then echo "changed=false" >> "$GITHUB_OUTPUT" else echo "changed=true" >> "$GITHUB_OUTPUT" fi - name: Prepare diff for AI summary if: steps.changes.outputs.changed == 'true' run: | git diff --stat | sed 's/^/ /' > /tmp/diff_stat.txt git diff | head -c 20000 | sed 's/^/ /' > /tmp/diff.txt The sed 's/^/ /' indent isn't decorative. actions/ai-inference substitutes template variables as raw text into a prompt YAML file before parsing it, so a multi-line diff starting at column 0 breaks the indentation of the enclosing content: |- block scalar. Pre-indenting the file to match keeps the YAML valid no matter what the diff looks like. The Prompt File actions/ai-inference supports .prompt.yml files, a small convention for keeping the system/user prompt out of the workflow YAML. messages: - role: system content: |- You write CHANGELOG entries describing an automated API update to slack-ruby-client, a Ruby gem whose Web API endpoint methods, argument validations, specs, and bin commands are code-generated from vendored Slack API method definitions (via a git submodule and rake task). Given a diffstat and a diff of the regenerated files, respond with ONLY a single JSON object (no markdown code fence ## How credential issuance controls software built by legal teams with agent CLIs DevFeed: [How credential issuance controls software built by legal teams with agent CLIs]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-06T16:29:26Z Content type: opinion Language: en Sources: [WorkOS Blog]() Topics: [Authorization](), [GitHub Copilot CLI](), [Security](), [Command-line interface](), [Code review](), [GitHub]() Tags: [agent](), [code-review](), [copilot](), [github](), [security](), [tools]() ### AI overview This commentary examines how legal and other non-engineering teams use agent CLIs to build software, arguing that credential issuance and access controls are more important security control points than code review for tools that may never enter a pull-request workflow. ### Source excerpt Agent CLIs turned every department into a builder. The control point for the tools they ship is credential issuance, not code review. Here's the paved path. ## C++ Dependencies Without the Headache: vcpkg + Copilot CLI DevFeed: [C++ Dependencies Without the Headache: vcpkg + Copilot CLI]() Original publisher: [Read original article]() Author: Augustin Popa Published: 2026-07-20T21:05:25Z Content type: article Language: en Sources: [C++ Team Blog]() Topics: [GitHub Copilot CLI](), [Vcpkg](), [C++](), [GitHub Copilot](), [MSVC](), [Command-line interface](), [GitHub]() Tags: [blog](), [c-plus-plus](), [cli](), [cmake](), [copilot](), [github](), [github-copilot](), [github-copilot-cli](), [msvc](), [open-source](), [programming](), [pure-virtual-c-plus-plus](), [vcpkg](), [writing-code]() ### AI overview A practical walkthrough of building a C++ console application from an empty folder with CMake, MSVC Build Tools, vcpkg, and GitHub Copilot CLI. It demonstrates dependency selection, installation, integration, reproducible builds, and controlled dependency updates through a terminal-first workflow. ### Source excerpt At Pure Virtual C++ 2026, we build a C++ console app from an empty folder using CMake, MSVC, and GitHub Copilot CLI. This walkthrough shows a practical prompt sequence for dependency selection, reproducible builds, and controlled updates. The post C++ Dependencies Without the Headache: vcpkg + Copilot CLI appeared first on C++ Team Blog. ## Pure Virtual C++ 2026 Is Tomorrow and On-Demand Sessions Are Now Available DevFeed: [Pure Virtual C++ 2026 Is Tomorrow and On-Demand Sessions Are Now Available]() Original publisher: [Read original article]() Author: Marian Luparu Published: 2026-07-20T16:05:54Z Content type: news Language: en Sources: [C++ Team Blog]() Topics: [C++](), [MSVC](), [Optimization](), [Vcpkg](), [GitHub Copilot CLI]() Tags: [announcement](), [blog](), [c-plus-plus](), [cpu](), [msvc](), [optimization](), [performance](), [pure-virtual-c-plus-plus](), [release](), [synthetic](), [twitch](), [youtube]() ### AI overview Pure Virtual C++ 2026 is a free virtual conference whose on-demand sessions are already available on YouTube. The article previews the live broadcast and highlights sessions on Sample Profile-Guided Optimization, C++ tooling, package management, MSVC, and C++ standards. ### Source excerpt The on-demand sessions for Pure Virtual C++ 2026 are available now on YouTube. Watch seven talks on SPGO, vcpkg + Copilot CLI, CMake Tools, PackageReference, MSVC upgrades, and C++23/26 status -- then join us live tomorrow. The post Pure Virtual C++ 2026 Is Tomorrow and On-Demand Sessions Are Now Available appeared first on C++ Team Blog. ## Using local LLMs for agentic coding DevFeed: [Using local LLMs for agentic coding]() Original publisher: [Read original article]() Author: Alex Ewerlöf Published: 2026-06-04T09:01:34Z Content type: tutorial Language: en Sources: [Alex Ewerlof Notes]() Topics: [coding](), [agentic-coding](), [Large Language Model](), [GitHub Copilot CLI](), [Linux](), [llama.cpp](), [Ollama](), [NVIDIA RTX]() Tags: [agentic-coding](), [agents](), [ai](), [claude](), [coding](), [github](), [linux](), [llama](), [llama-cpp](), [llms](), [local](), [local-llms](), [microsoft](), [nvidia](), [nvidia-rtx](), [ollama](), [quality](), [rocm](), [state]() ### AI overview A practical guide to using local language models for agentic coding. It covers running local models, configuring coding agents such as Copilot and Pi, and evaluating local models against cloud models in terms of cost, privacy, tooling, and performance. ### Source excerpt AI honeymoon pricing is over, but your work is not ## Github Copilot vs Google Antigravity DevFeed: [Github Copilot vs Google Antigravity]() Original publisher: [Read original article]() Author: Alex Ewerlöf Published: 2026-03-22T23:19:06Z Content type: comparison Language: en Sources: [Alex Ewerlof Notes]() Topics: [GitHub Copilot](), [google-antigravity](), [GitHub Copilot CLI](), [Google](), [Chrome]() Tags: [browser](), [gemini-cli](), [github-copilot](), [google](), [google-antigravity]() ### AI overview A firsthand comparison of GitHub Copilot and Google Antigravity based on the author's experience using both tools. The article describes Antigravity's browser integration and Plan mode, while noting that its newer product maturity is visible compared with Copilot. ### Source excerpt Why Github gets developers and why it's hard to tell who Antigravity is for ## Using Gemini CLI and the Obsidian CLI to manage note metadata DevFeed: [Using Gemini CLI and the Obsidian CLI to manage note metadata]() Original publisher: [Read original article]() Published: 2026-02-21T20:33:17Z Content type: article Language: en Sources: [maiatoday]() Topics: [Obsidian](), [AI Agent](), [GitHub Copilot CLI](), [Command-line interface](), [Script](), [Documentation](), [Markdown](), [Git]() Tags: [agent](), [ai-agent](), [ai-agents](), [automation](), [cli](), [docs](), [gemini](), [gemini-cli](), [git](), [knowledge-management-systems-metadata](), [markdown](), [obsidian](), [script]() ### AI overview The author describes using Gemini CLI with the Obsidian CLI, along with shell tools and scripts, to analyze and standardize metadata across an Obsidian vault. The work covered status values, Type and ContentType properties, tags, documentation, and validation scripts for future consistency checks. ### Source excerpt Let's talk about the "Obsidian Paralysis." For a while, I've been using Obsidian to jot down ideas, plan content, and collect those random snippets from the internet that feel like digital gold. I moved over from Notion a while back. The freedom of simple Markdown managed by Git was liberating. Pure, texty goodness. But--and there's always a but, isn't there?--one thing always held me back. That nagging little voice: Am I doing it right? I know, I know. The "experts" say just write the notes and let the system emerge organically. But I was forever second-guessing myself. Is this a status: NotStarted or status: not-started? Is the type a "thought" or a "note"? I was spending more time fiddling with the taxonomy and the metadata "meta-system" than actually creating content. But today, everything changed. I opened Obsidian and saw the news: they now have a CLI interface. 💡: "What if I introduced the Obsidian CLI to an AI Agent CLI?" For my experiments, I called in Gemini CLI. I basically sat them down in a terminal together, let Gemini CLI figure out what the Obsidian CLI could do, and then--with a spicy mix of grep, sed, awk, and the new Obsidian commands, we went to work. Here's the "Metadata Makeover": 1. The Status Cleanup I had Gemini pull every single Status property from every note in my vault to analyze them for consistency. It detected patterns I didn't even know I had (like all the versions of Idea Ideas Research researching). We cleaned up the mess, documented the new "Golden Rules" for statuses, and Gemini wrote a validation script that I can run that will clean things up or highlight inconsistencies. 2. The "Type" vs. "ContentType" Tangle We did the same for Type and ContentType. It turns out I was using them interchangeably like a chaotic neutral character. Gemini helped me settle on a single source of truth, updated my docs, and tweaked the validation script to keep things tidy. 3. The Tag Jungle We looked at everything--frontmatter tags, in-document hashtag ## Introducing: Devstral 2 and Mistral Vibe CLI. DevFeed: [Introducing: Devstral 2 and Mistral Vibe CLI.]() Original publisher: [Read original article]() Published: 2025-12-09T12:00:00Z Content type: news Language: en Sources: [Mistral AI Blog]() Topics: [Artificial Intelligence](), [coding](), [Large Language Model](), [Open Source](), [Automation](), [GitHub Copilot CLI](), [Transformer](), [Command-line interface](), [context window](), [Terminal](), [Fine-tuning](), [on-prem]() Tags: [ai](), [ai-assistants](), [automation](), [autonomous-agents](), [claude](), [cli](), [code](), [coding](), [context-window](), [deepseek](), [fine-tuning](), [hardware](), [models](), [on-prem](), [open-source](), [terminal]() ### AI overview Mistral introduces Devstral 2, Devstral Small 2, and the Mistral Vibe CLI. The open coding models target autonomous software engineering, with deployment options spanning APIs, local consumer hardware, and on-premises environments. Devstral 2 supports a 256K context window, codebase-wide changes, failure recovery, and fine-tuning, while Mistral Vibe provides terminal-based code automation. ### Source excerpt The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models. ## GitHub Copilot for CLI for PowerShell DevFeed: [GitHub Copilot for CLI for PowerShell]() Original publisher: [Read original article]() Author: Scott Hanselman Published: 2023-04-25T15:31:49Z Content type: tutorial Language: en Sources: [Scott Hanselman]() Topics: [GitHub Copilot CLI](), [PowerShell](), [Command-line interface](), [GitHub]() Tags: [ai](), [command-line](), [github](), [github-copilot-cli](), [powershell]() ### AI overview This article explains how GitHub Copilot CLI routes its shell commands through the github-copilot-cli executable and demonstrates PowerShell aliases that adapt those commands for PowerShell, including an option to run the generated command. ### Source excerpt GitHub Next has this cool project that is basically Copilot for the CLI (command line interface). You can sign up for their waitlist at the Copilot for CLI site. Copilot for CLI provides three shell commands: ??, git? and gh? This is cool and all, but I use PowerShell. Turns out these ?? commands are just router commands to a larger EXE called github-copilot-cli. So if you go "?? something" you're really going "github-copilot-cli what-the-shell something." So this means I should be able to to do the same/similar aliases for my PowerShell prompt AND change the injected prompt (look at me I'm a prompt engineer) to add 'use powershell to.' Now it's not perfect, but hopefully it will make the point to the Copilot CLI team that PowerShell needs love also. Here are my aliases. Feel free to suggest if these suck. Note the addition of "user powershell to" for the ?? one. I may make a ?? and a p? where one does bash and one does PowerShell. I could also have it use wsl.exe and shell out to bash. Lots of possibilities. function ?? { $TmpFile = New-TemporaryFile github-copilot-cli what-the-shell ('use powershell to ' + $args) --shellout $TmpFile if ([System.IO.File]::Exists($TmpFile)) { $TmpFileContents = Get-Content $TmpFile if ($TmpFileContents -ne $nill) { Invoke-Expression $TmpFileContents Remove-Item $TmpFile } } } function git? { $TmpFile = New-TemporaryFile github-copilot-cli git-assist $args --shellout $TmpFile if ([System.IO.File]::Exists($TmpFile)) { $TmpFileContents = Get-Content $TmpFile if ($TmpFileContents -ne $nill) { Invoke-Expression $TmpFileContents Remove-Item $TmpFile } } } function gh? { $TmpFile = New-TemporaryFile github-copilot-cli gh-assist $args --shellout $TmpFile if ([System.IO.File]::Exists($TmpFile)) { $TmpFileContents = Get-Content $TmpFile if ($TmpFileContents -ne $nill) { Invoke-Expression $TmpFileContents Remove-Item $TmpFile } } } It also then offers to run the command. Very smooth. Hope you like it. Lots of fun stuff happening in this space.