AI Repo: ayghri/i-have-adhd

Skyler: Hey everyone, welcome back to Git News A I, the show where we dig through the hottest trending A I repositories on GitHub so you don't have to. Big thanks to our sponsors keeping this show running — Ada, helping teams integrate A I into their workflows seamlessly, Ago Consulting, your silicon development partners from A I all the way to SoC, and Zen Semiconductor, an umbrella company with a whole portfolio of silicon-industry companies, plus Ada for deploying A I at scale in any business, and their Vect appliance that runs local L L Ms and vector search on dedicated hardware. Today we've got five repos that are genuinely exciting — we're talking ADHD-friendly coding agents, Chrome DevTools for A I, autonomous cybersecurity pentesting, a monster document converter, and an agent framework from NousResearch that's racking up stars like crazy. Let's get into it. Skyler: First up is something that made me laugh the moment I read the name — ayghri/i-have-adhd. Yes, that is a real GitHub repository name, and yes, it is exactly what it sounds like. So here's the problem this solves: you're working with a coding agent, you ask it a question, and instead of giving you the answer, it buries the actual useful information under a wall of explanation, caveats, context, and "great question!" fluff. If you've ever used an A I coding assistant and found yourself scrolling and scrolling just to find the one line that matters, this repo is for you. It's a skill — essentially a plugin or capability layer — designed to force your coding agent to front-load the answer. No more preamble, no more lengthy setups before the actual response. It's ADHD-friendly in the best possible way, meaning it respects your attention and your time. The repo is sitting at over thirty thousand stars right now, which tells you this is a pain point a lot of developers share. Recent activity shows a Windows fix for importing the OpenCode plugin via pathToFileURL, so it's actively maintained and cross-platform support is improving. If you're using any A I coding assistant and you're constantly frustrated by verbose, meandering responses, this is a really clever little tool to add to your setup. Definitely check the show notes for the link. Skyler: Alright, number two — ChromeDevTools/chrome-devtools-mcp. This one is from the official Chrome DevTools team, and it's a big deal for anyone building A I coding agents. So MCP stands for Model Context Protocol, which is essentially a standard for letting A I models interact with tools and external systems. What this repo does is expose Chrome DevTools as an MCP server, meaning your A I coding agent can actually use Chrome DevTools directly — things like inspecting the DOM, checking network requests, reading console errors, and debugging web applications. Think about what that unlocks. Instead of you manually copying error messages from the browser console and pasting them into your chat with an A I, the agent can just go look at the browser itself. That is a massive quality of life improvement for web development workflows. It's written in TypeScript, which makes sense given the web-focused nature of the tool, and it's sitting at over fifty-one thousand stars, which is genuinely impressive. The recent activity shows steady dependency updates and some activity bucketing work for analytics, so the team is keeping things healthy. If you're building or using an A I agent for web development, this is one of those integrations that can completely change how you debug. Seriously, check the show notes for the link on this one. Skyler: Okay, number three is where things get a little spicy — 0x4m4/hexstrike-ai. This is HexStrike A I, an advanced MCP server that lets A I agents like Claude, GPT, Copilot, and others autonomously run over a hundred and fifty cybersecurity tools. We're talking automated pentesting, vulnerability discovery, bug bounty automation, and security research. So if you're in the cybersecurity space, you already know that a huge amount of pentest work involves running the same set of tools — nmap, sqlmap, ffuf, nuclei — in a systematic way. What HexStrike does is bridge L L Ms with those real-world offensive security capabilities through the MCP protocol. Your A I agent can essentially conduct a full pentest workflow without you manually invoking each tool. Now, obviously this comes with a big responsibility caveat — this is for authorized security research, bug bounties, and environments you have permission to test. But for legitimate security professionals and researchers, this is a genuinely powerful force multiplier. It's rated a hundred percent A I relevant, and rightly so — this is one of the most direct applications of agentic A I to a real-world technical domain I've seen in a while. Over eleven thousand stars and climbing. Recent activity is mostly README updates as the author documents the expanding toolset. Security researchers, red teamers, and bug bounty hunters — check the show notes for this one. Skyler: Alright, number four — microsoft/markitdown. Now this one has been around for a bit, but it keeps growing and honestly it deserves a spotlight because the star count is absolutely wild — over a hundred and eighty-one thousand stars. For context, that puts it in truly elite GitHub territory. So what is it? MarkItDown is a Python tool that converts files and office documents into Markdown. PDFs, Word docs, PowerPoints, Excel spreadsheets, HTML pages — you feed them in, you get clean Markdown out. Now why does this matter so much for A I? Because Markdown is one of the most L L M-friendly formats out there. When you're building R A G pipelines, knowledge bases, document Q and A systems, or any kind of A I application that needs to ingest real-world documents, you need a reliable way to convert those documents into something the model can actually work with cleanly. MarkItDown has become a go-to solution for exactly that use case. It handles a huge variety of file types, it's Python-based so it drops right into your M L pipelines, and Microsoft actively maintains it. The recent activity shows a bug fix for PowerPoint chart titles, which tells you they're sweating the details on edge cases. If you're doing anything with document ingestion for A I applications and you haven't looked at this yet, I genuinely don't know what you're waiting for. Show notes link is there for you. Skyler: And last but absolutely not least — NousResearch/hermes-agent. The tagline is "the agent that grows with you," and with two hundred and forty-three thousand stars, this is the biggest repo we're covering today by a significant margin. NousResearch is well known in the open source A I community for their Hermes model series, which are fine-tuned L L Ms designed for strong instruction following, tool use, and agentic behavior. The hermes-agent repo is their agent framework built around those capabilities. The idea is an agent architecture that adapts and scales with your needs — whether you're building something simple or something complex with lots of tool integrations. The recent activity is really interesting — there's work on MCP OAuth, specifically keeping refresh tokens when a refresh response omits them, and there's Windows self-test work for desktop environments. That tells you this is a production-grade framework being used in real deployments across multiple platforms, not just a research demo. For M L engineers and developers building agentic applications, NousResearch brings serious credibility here — they've been at the forefront of open source L L M development for a while. If you want an agent framework backed by a team that deeply understands the model layer, this is worth a serious look. Two hundred and forty-three thousand stars don't lie. Check the show notes for the link. Skyler: And that's a wrap on today's episode of Git News A I — five repos ranging from quality-of-life developer tools all the way to full-blown autonomous security agents and a framework with nearly a quarter million stars. Massive thank you to our sponsors — Ada for helping teams bring A I into their workflows, Ago Consulting for expert silicon development guidance from A I to SoC, and Zen Semiconductor for their incredible portfolio of silicon-industry companies, the Ada platform for deploying A I at scale, and the Vect appliance bringing local L L Ms and vector search to dedicated hardware. If you want more A I news and deep dives, check out A I Special Report, another great show in the Ada podcast network — it's fantastic if you want broader coverage of what's happening in the A I industry. As always, subscribe so you never miss an episode, and all the repo links are waiting for you in the show notes. See you next time.