This is post #4 in The Agent-Ready SDLC series. In post #1 we laid out the Ferrari-in-a-Fiat-500 problem - the engine is great, the chassis isn't. In post #2 we covered the first bottleneck: context. In post #3 we covered the second: feedback loops. Now we're at the third piece - and it's the one nobody wants to talk about.
LLM coding agents moved fast from cloud demos to tools running on developer workstations. They don't just suggest code anymore. They execute it. They start shells, install packages, edit repos, run tests, and sometimes open PRs. All with the same permissions you have. In the first part of the miniseries, Jakub Bocheński will look at Context, Motivation, and available sandboxing tools.
Open any README in your repository. That flagship one. The one that's 800 lines long with a "Getting Started" section written in 2022. Read it with fresh eyes - as if you were a new developer, or better yet - as an AI agent who's never been to a standup, never seen Slack, never heard the legend of why we don't touch the InvoiceReconciler class in the payment service. Now ask yourself one question: based on this README, can you safely modify anything in this service?
While API based LLMs are great for rapid, fast, and easy development, they can be less secure and costly in the long-term horizon for load-intensive applications. The solution are Small Language Models (SLM), self-hosted and finetuned on the downstream task. This article presents a case study of a Supervised Fine-Tuning (SFT) of the SLM on the Invoice Processing task. It shows that while SLMs have higher investment costs at start, they are faster, cheaper, and more secure in the long-term, especially for high-load intensive applications.
You've probably heard about the first METR study from July 2025 - it made the rounds at every conference and every newsletter. 16 experienced open-source developers, a proper randomized controlled trial (not a vendor survey), and the result: 19% slower with AI. In this article, Artur argues that the problem lies in the environment, not the model. Read on to find out exactly.
Monorepo keeps coming up in conversations about large-scale software architecture. For some organizations, it’s a way to bring order to a growing ecosystem of applications. For others, it raises a lot of concerns. We spoke with Bartek Sądel, an expert who works with enterprise monorepos, about how this approach works in practice, what questions companies ask, and what the real benefits and challenges are.
Welcome to GitHub All-Stars, our biweekly series where we pick a trending or freshly minted open-source project and put it under the microscope. We focus on new, relatively unknown gems - not another breakdown of the latest React release (because let's be honest, the world has enough of those). This time, we're looking at a project that lives at an unusual intersection of prepper culture, self-hosting enthusiasm, and edge computing philosophy. And it just exploded on Hacker News.
Today's subject has become one of the most talked-about open-source projects in the AI agent space, racking up over 11,000 GitHub stars in less than a month. We're looking at NanoClaw by Gavriel Cohen - a lightweight, container-isolated personal AI assistant that connects to WhatsApp (and Telegram, Discord, Slack, Signal) and runs on Anthropic's Agent SDK. Written in TypeScript, MIT-licensed, and built around one radical premise: the software that hosts powerful AI agents should be simple enough to read in eight minutes.
Most of the time, the knowledge base we want to chat and reason about with an LLM has strong inter-relations. Even the famous PageRank algorithm, which gave Google a competitive advantage and made it ahead of others, is based on the quantity and quality of links between websites. The relations within a knowledge base are crucial to fully understand it. The problem with classical RAG is that it chunks the text, discarding all internal relations. So can we do better?
Today's project dropped on Hacker News frontpage just days ago and instantly sparked one of the most interesting security discussions I've seen in a while. We're looking at Matchlock by Jingkai He - a CLI tool for running AI agents in ephemeral microVMs with network allowlisting and secret injection via MITM proxy. Built to answer a question that every developer running claude --dangerously-skip-permissions should be asking: "What's the worst that could happen?"
In the second part, Adam will focus on reinforcement learning networks by summarizing the "1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities", an article featured in NeurIPS 2025.
With the rapid growth of generative AI, we have a new great model coming out every month. It makes it hard to keep track of all the different kinds of models and choose the right one for your task. In this article, I will cover the best generative AI models at the doors of 2026. I hope to make your selection of a model at least a bit easier.
