NestMux is a desktop app that runs Claude Code, Codex, Gemini CLI, and others in a grid of real terminals, each with its own HOME directory and git worktree. The key design choice, isolated environments with node-pty, prevents agents from stepping on each other in shared repos. It's a pragmatic answer to the 'agent swarm' problem that doesn't require a new orchestration framework.
programmingSunday, August 23, 2026
AI agents get their own terminal grid
The day's programming news is split between two camps: developers building practical tools to manage multiple AI agents at once, and a growing unease about what that means for the culture of software. A new desktop app runs five coding agents side by side in isolated panes, while a longer essay argues that authoritarian patterns are baked into how we write code.
Multi-agent tooling
The agent workflow problem is shifting from 'can an agent write code?' to 'how do you run several of them at once without chaos?' Two new tools tackle that.

Kepler's biggest update since public preview frames the hard part as 'not writing the code anymore' but managing the agents who do. The tool positions itself as a single place to go from idea to merged PR. It's competing directly with the workflow gap that NestMux also targets, but from a more opinionated, GitKraken-integrated angle.
Culture and craft
Meanwhile, two pieces push back on the narrative that LLMs have made programming trivial, one from a cultural angle, one from a practical one.
Zed Shaw argues that software development culture is deeply authoritarian, and that even developers who see themselves as anti-authoritarian internalize those patterns. The essay offers a framework for evaluating practices and communities on an authoritarian-to-totalitarian spectrum. It's a long, deliberately provocative piece that lands in the middle of the current debate about AI-generated code and human agency.
Armin Ronacher pushes back on the 'programming is solved' meme by arguing that language familiarity and friction have decreased, but language choice itself matters less than before. The real shift is that developers can now rewrite code in unfamiliar languages with LLM help. It's a measured take that neither hypes nor dismisses the AI moment.
Model milestone
And a single benchmark-style post makes the case that open-weights models are now capable of work that used to require a frontier API.
A developer gave Qwen 3.8 27B a complex reverse-engineering task and got results in 30 minutes on a local workstation. The base performance was modest, but optimizations with SGLang and speculative decoding pushed it to usable speeds. The implication is that open-weights models are crossing a threshold where they can handle work previously reserved for API-only frontier models.
Also today15
Death to px, long live ch!shkspr.mobi
MartyPC Web Editionmartypc.net- Developer launches badBANANA Threat Observatory to surface cyber threat data transparentlyshortsingh.com
- Foreign Correspondent: Aug 25tvtonight.com.au
- How to prevent stack overflow when dropping deep structures?users.rust-lang.org
- TWiR quote of the weekusers.rust-lang.org
Maintaining Apache Iceberg Tables: Compaction, Snapshots, Metadata and Orphan Filesitnext.io
The complete guide to Iceberg table maintenance — the four operations every table requires, why they must run in a specific order, and the two approaches to keeping your lake healthy: an intelligent control plane vs. manual scripts and orchestration. The operational gap in Apache
Best Project Management Tools Compared (2026)www.blog.brightcoding.dev
We compared the top project management tools of 2026: pricing, features, and who each one actually fits
LibreOffice 26.8 Will Bring a Better Tabbed Interface — Not a Single ‘Best’ Onefossforce.com
The new Tabbed interface is an improvement, not a retreat from LibreOffice’s longstanding commitment to offering users multiple ways to work. The post LibreOffice 26.8 Will Bring a Better Tabbed Interface — Not a Single ‘Best’ One appeared first on FOSS Force .
China’s reusable rocket engine just ran for a full 100 seconds without a single hitchinterestingengineering.com
A Chinese rocket engine just ran for a full 100 seconds without a hitch. That...
How to Write Effective AI Prompts: Complete Guidewww.blog.brightcoding.dev
Learn how to write AI prompts that produce usable results with a simple framework, real examples, and common mistakes
Four Corners: Aug 24tvtonight.com.au
Mark Willacy investigates the opaque business of political lobbyists getting “face time” with ministers and why vested interests are winning.
NRG 2026 | October 23 - 25 | Poznań, Polandm.pouet.net
Stop Your App From Hammering A Dying Servicepython.plainenglish.io
One small pattern keeps a single broken dependency from taking down everything around it. Continue reading on Python in Plain English »
The Pandas Mistake That Turns a Fast Script Into a Frozen Onepython.plainenglish.io
Your code works fine on a thousand rows. Then someone hands you a million, and it just stops responding. Here is exactly why, with the fix. Continue reading on Python in Plain English »
More roundups that day
One animator's 14-year labor of love
Clive Davis remembered, Paramount chaos continues
tv roundup