Don Syme, GitHub Next, Visiting Professor, King's College London
We have a draft of new report from GitHub Next! We analyze the impact of Repo Assist, a proactive AI repository agent, across 13 open source repositories that adopted it between February and March 2026. The agent reduced open issue counts in every repository — 578 issues total. Across all repositories, which were previously largely dormant, issue closure Continue reading The Impact of Automated…
We have recently written a SIGPLAN PL Perspectives article: Repositories Are Human/Agent Knowledge Factories Here s a simple example of what that means in practice: The Large File Simplifier 🧩 Imagine you have problems where humans and AI produce code where files are too large, and that this is resulting in bad engineering practices. You have Continue reading Understanding Repositories as…
Formal verification is one of the hardest things in software engineering. You need fluency in a proof assistant, deep understanding of invariant discovery, and months sometimes years of dedicated effort. This expertise barrier has limited formal verification to a handful of well-funded teams working on a handful of high-value targets. Formal verification is Continue reading 📐Lean Squad: Exploring…
I have been using GitHub Agentic Workflows to help automate the maintenance of software libraries and tools. The workflow I m using is called Repo Assist. Here s my morning today! The first is fixing a bug no one had spotted, no one had filed. It happened because, overnight, when Repo Assist ran, it rolled the what Continue reading Start Your Day With Code That’s Better 🌤️
In my previous post I introduced Repo Assist: Crunching the Technical Debt with GitHub Agentic Workflows. In my first version of Repo Assist, tasks were selected by round-robin: the agent tracked which tasks it had run most recently and rotated through them. This worked, but it had a problem the agent was spending equal Continue reading Adding Weighted Task Selection to a GitHub Agentic Workflow
I have spent the weekend using GitHub Agentic Workflows to make Repo Assist, a generic, all-purpose automated repository assistant for software maintainers. For some repos, some of the time. I crafted RepoAssist for my own purposes, for helping with repos with long term technical debt. These are repositories where: I used Repo Assist to re-engage Continue reading 🌈Repo Assist: Crunching the…
Happy to share my latest post to the GitHub Blog, with Peli de Halleux. Main post: Automate repository tasks with GitHub Agentic WorkflowsI ll add some more personal thoughts please read the above post first! :) Over the last year we have been working to bring coding agents to repository automation. This opens a staggering Continue reading On the GitHub Blog: Automate repository tasks with GitHub…
People using coding agents in a loop have discovered the joy of implementing programming language compilers using this technique. It s a lot of fun it s impressive how much can be achieved. I dug out my notes from an experiment (really a spike ) we did in July 2025. In this work we used shared GitHub Issues Continue reading Spike from July 2025: Creating a Programming Language using Coding Agents…
In previous posts I ve written about Natural Language Programming, and Intent/Realization Toolchains as two grounding concepts in AI productivity tools, particularly AI for Code. In this post I want to explore another angle that comes up in features in AI productivity tools, particularly those that generate documentation, synthesize specifications, discover build rules or other extractive Continue…
Developer tools are some of the most interesting, inspiring and satisfying jobs in the industry. In what other job can you create such fundamental, useful, elegant, powerful tools, meet customers, see your tools get used, see the huge difference they make to productivity? However, developer tools often exist in a business context. This can be Continue reading Three Laws of the Business Side of…