# GitHub Engineering Updates, ideas, and inspiration from GitHub to help developers build and design software. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Migrating the GitHub Copilot runtime to Rust, using Copilot DevFeed: [Migrating the GitHub Copilot runtime to Rust, using Copilot]() Original publisher: [Read original article]() Author: Stephen Toub Published: 2026-09-17T00:26:43Z Content type: article Language: en Sources: [GitHub Engineering]() Topics: [GitHub Copilot](), [Rust](), [Agent Harness](), [GitHub Copilot SDK](), [GitHub]() Tags: [agent-harness](), [ai-agents](), [ai-ml](), [developer-experience](), [generative-ai](), [github](), [github-copilot](), [github-copilot-sdk](), [rust]() ### AI overview The GitHub Copilot agent runtime was rewritten from TypeScript on Node.js and V8 into more than 800,000 lines of production Rust. AI agents wrote most of the code across 128 pull requests, and the runtime was shipped incrementally while regressions were fixed and performance improved by orders of magnitude. ### Source excerpt A rewrite this size wasn't affordable before agents. Here's what porting the Copilot agent runtime to 800,000 lines of production Rust actually took. The post Migrating the GitHub Copilot runtime to Rust, using Copilot appeared first on The GitHub Blog. ## Marketing ops as code: Automating events from planning to follow-up on GitHub DevFeed: [Marketing ops as code: Automating events from planning to follow-up on GitHub]() Original publisher: [Read original article]() Author: Tomoko Tanaka Published: 2026-09-11T18:26:10Z Content type: tutorial Language: en Sources: [GitHub Engineering]() Topics: [AI-assisted coding]() Tags: [ai-ml](), [api](), [automation](), [cli](), [events](), [github](), [github-actions](), [github-copilot](), [github-issues]() ### AI overview A GitHub marketing lead describes using GitHub Copilot and GitHub Actions to automate event operations from a GitHub Issue, including setup, daily registrant processing, and post-event cleanup. ### Source excerpt If you can write down how you do your work, you can automate it. Here's what I did to support GitHub's APAC marketing team. The post Marketing ops as code: Automating events from planning to follow-up on GitHub appeared first on The GitHub Blog. ## GitHub Copilot app for Beginners: Using the diff, terminal, and browser DevFeed: [GitHub Copilot app for Beginners: Using the diff, terminal, and browser]() Original publisher: [Read original article]() Author: Kayla Cinnamon Published: 2026-09-10T21:31:19Z Content type: tutorial Language: en Sources: [GitHub Engineering]() Topics: [GitHub Copilot](), [AI-assisted coding](), [dev-tools](), [web applications]() Tags: [ai-coding](), [ai-ml](), [github-copilot](), [github-copilot-app](), [github-copilot-app-for-beginners](), [pull-request](), [review](), [web-browser]() ### AI overview A beginner-oriented guide to using the GitHub Copilot app's diff, terminal, and browser panels to review agent-made code changes, run a project, preview a web feature, iterate, and create a pull request. ### Source excerpt Checking agent-generated code usually means hopping between tabs. Learn how to view diffs, run terminal commands, and preview web apps side by side in the GitHub Copilot app. The post GitHub Copilot app for Beginners: Using the diff, terminal, and browser appeared first on The GitHub Blog. ## GitHub availability report: August 2026 DevFeed: [GitHub availability report: August 2026]() Original publisher: [Read original article]() Author: Jakub Oleksy Published: 2026-09-10T02:05:17Z Content type: article Language: en Sources: [GitHub Engineering]() Topics: [GitHub](), [site-reliability-engineering](), [migration](), [MySQL](), [GitHub Actions]() Tags: [availability](), [azure](), [company-news](), [database](), [github](), [github-actions](), [github-availability-report](), [migration](), [monitoring](), [mysql](), [news-insights](), [outage](), [performance](), [production]() ### AI overview GitHub reports five August incidents with degraded service performance and describes capacity, resiliency, database, Azure migration, and GitHub Actions improvements. ### Source excerpt In August, we experienced five incidents that resulted in degraded performance across GitHub services. The post GitHub availability report: August 2026 appeared first on The GitHub Blog. ## Project HydraFusion: Frontier quality via multi-model orchestration DevFeed: [Project HydraFusion: Frontier quality via multi-model orchestration]() Original publisher: [Read original article]() Author: GitHub Staff Published: 2026-09-04T16:04:14Z Content type: release Language: en Sources: [GitHub Engineering]() Topics: [Orchestration](), [Model Routing](), [GitHub Copilot](), [AI-assisted coding](), [Optimization](), [Claude]() Tags: [agentic-coding](), [ai-ml](), [benchmarking](), [benchmarks](), [claude](), [cost](), [github-copilot](), [llms](), [optimization](), [orchestration](), [routing]() ### AI overview GitHub introduces Project HydraFusion, a GitHub Copilot research preview that selects multi-model execution workflows to balance quality, cost, and latency for coding tasks. ### Source excerpt In controlled offline evaluations, HydraFusion's selective coding workflows matched or exceeded the evaluated Opus 5 baseline while reducing estimated workflow cost. Now available as a research preview in GitHub Copilot. The post Project HydraFusion: Frontier quality via multi-model orchestration appeared first on The GitHub Blog. ## GitHub Copilot app for Beginners: Run several agents at once DevFeed: [GitHub Copilot app for Beginners: Run several agents at once]() Original publisher: [Read original article]() Author: Kayla Cinnamon Published: 2026-09-03T16:00:00Z Content type: tutorial Language: en Sources: [GitHub Engineering]() Topics: [AI Chat]() Tags: [agents](), [ai](), [ai-agents](), [ai-ml](), [copilot](), [developer](), [developer-tools](), [development](), [git](), [github](), [github-copilot](), [github-copilot-app](), [github-copilot-app-for-beginners]() ### AI overview A beginner tutorial on using the GitHub Copilot app to run several AI agent sessions in parallel. It explains that sessions are isolated through separate Git worktrees and retain their own context, then demonstrates concurrent feature work, accessibility review, and testing. ### Source excerpt Learn how to run parallel agents in the GitHub Copilot app, and experience the moment it stops feeling scary and starts feeling powerful. The post GitHub Copilot app for Beginners: Run several agents at once appeared first on The GitHub Blog. ## Decoding the new AI lingo: Loops, harnesses, squads, hill climbing... oh my! DevFeed: [Decoding the new AI lingo: Loops, harnesses, squads, hill climbing... oh my!]() Original publisher: [Read original article]() Author: Cassidy Williams Published: 2026-09-02T21:00:00Z Content type: article Language: en Sources: [GitHub Engineering]() Topics: [AI Development](), [Software Engineering](), [Open Source Models & Datasets]() Tags: [agent](), [agentic-ai](), [agents](), [ai](), [ai-ml](), [engineering](), [github-podcast](), [loops](), [models](), [observability](), [open-source](), [routing](), [skills](), [validation](), [workflow]() ### AI overview A guide to emerging AI-development terminology, explaining loop engineering and Ralph loops, multi-agent squads and fleets, and related concepts such as open weights and open source models. ### Source excerpt From loop engineering to harnesses, squads, and open weights, the GitHub Podcast breaks down the AI terms showing up in developer conversations. The post Decoding the new AI lingo: Loops, harnesses, squads, hill climbing... oh my! appeared first on The GitHub Blog. ## 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. ## OpenClaw went viral. Meet the maintainers building and securing it. DevFeed: [OpenClaw went viral. Meet the maintainers building and securing it.]() Original publisher: [Read original article]() Author: Gregg Cochran Published: 2026-08-27T16:00:00Z Content type: article Language: en Sources: [GitHub Engineering]() Topics: [OpenClaw](), [Maintainers](), [pull-requests](), [GitHub](), [Code review](), [supply-chain-security](), [Security](), [Artificial Intelligence]() Tags: [agent](), [agents](), [ai](), [ai-agents](), [blog](), [code](), [contributors](), [developers](), [development](), [github](), [maintainers](), [open-source](), [openclaw](), [pull-request](), [pull-requests](), [review](), [security](), [supply-chain]() ### AI overview OpenClaw maintainers discuss the project's rapid growth, the resulting flood of pull requests, contributor trust, code review, software supply chain risks, and security. They describe welcoming contributions from first-time contributors, non-developers, and people using AI agents while refining promising changes. ### Source excerpt OpenClaw is the fastest-growing project in GitHub history. Peter Steinberger and several maintainers share what they learned in the project's first six months. The post OpenClaw went viral. Meet the maintainers building and securing it. appeared first on The GitHub Blog. ## GitHub Copilot app for Beginners: Automate Dependabot pull request triage DevFeed: [GitHub Copilot app for Beginners: Automate Dependabot pull request triage]() Original publisher: [Read original article]() Author: Christopher Harrison Published: 2026-08-26T20:12:53Z Content type: tutorial Language: en Sources: [GitHub Engineering]() Topics: [GitHub Copilot app](), [pull-requests](), [Automation](), [GitHub Copilot](), [GitHub](), [Vulnerabilities]() Tags: [ai-ml](), [automation](), [copilot](), [developer](), [github](), [github-copilot](), [github-copilot-app](), [github-copilot-app-for-beginners](), [pull-request](), [workflow]() ### AI overview Learn how to create a daily automation in the GitHub Copilot app to triage Dependabot pull requests. The automation reviews open pull requests, groups updates by risk, checks CI status, and returns a summary highlighting changes ready to merge or requiring closer attention. ### Source excerpt Managing library updates can be tedious at times. Learn how the GitHub Copilot app can handle this type of repetitive task. The post GitHub Copilot app for Beginners: Automate Dependabot pull request triage appeared first on The GitHub Blog. ## How to evaluate LLMs before production DevFeed: [How to evaluate LLMs before production]() Original publisher: [Read original article]() Author: Mariko Wakabayashi Published: 2026-08-25T21:35:11Z Content type: article Language: en Sources: [GitHub Engineering]() Topics: [Large Language Model](), [Secret Scanning](), [Benchmark](), [datasets](), [GitHub](), [Security]() Tags: [ai-ml](), [benchmark](), [benchmarks](), [code](), [developer-tools](), [evaluation](), [github](), [llms](), [secret-scanning](), [security]() ### AI overview This article explains how to evaluate LLM-based systems before moving them into production. Using GitHub secret scanning as an example, it emphasizes defining the product decision first, testing against realistic production conditions, accounting for ambiguity and edge cases, and balancing reduced false positives with sufficient recall. ### Source excerpt These are the lessons we learned evaluating LLMs for real-world secret scanning. The post How to evaluate LLMs before production appeared first on The GitHub Blog.