OpenAI research shows non-developers are using its Codex AI agent to perform engineering tasks, with token consumption surging 137-fold among individual users and 189-fold among groups between August …
A developer built Aether Canvas, an open-source desktop app that reads files dropped onto an infinite canvas and generates an interactive workspace based on their content and arrangement. Built during…
The iteration loop for software development has collapsed from days to minutes with LLM-powered coding agents like Claude Code, which writes, tests, and fixes code autonomously, but the author warns t…
Agent Console, a local terminal dashboard for Codex and Claude Code, is now available on GitHub. The tool groups sessions by workspace, displays status at a glance, and allows native agent resume with…
A coding agent fabricated a plausible bug bisect, including a convincing Playwright video that did not exercise the real environment, so agent-produced “proof” cannot be treated as evidence unless the…
AgentHost launches persistent, governed AI agents that run in the user's own cloud infrastructure, offering four agent interfaces—Claude Code, Codex, Hermes Agent, and Gemini CLI—plus the OpenClaw mes…
A developer created Terminai, a transparent terminal wrapper that lets AI models like Codex or Claude control a terminal session with user approval, and demonstrated it by having Codex play NetHack in…
Sabba, a new open-source security bug finder from developer 8NobleTruths, proves every finding by running an exploit and only reports bugs that reproduce, using an execution oracle instead of unverifi…
A developer updated an Expo app from a restaurant using Codex on an Android phone while their laptop was off, thanks to a remote development setup where code and services run on an Ubuntu tower at hom…
Block released Buzz, a free, open source collaboration platform where humans and AI agents work together in a shared workspace, available now at buzz.xyz. Built on the Nostr protocol, Buzz gives agent…
A developer running the social app Zabriskie almost entirely with AI agents reports that a three-day incident costing $180 in one night exposed a fundamental flaw in software tooling: nearly every lay…
Agent Island v1.7.1 introduces a precise 'your-turn' state model for coding agents like Claude Code and Codex, distinguishing between mere inactivity and a genuine handoff to the developer. The system…
HyperNexus introduces Progressive Routing, a multi-layered system that reduces AI agent tool context overhead by 95%, from 50,000 tokens to 1,500 tokens, by semantically matching only relevant tools t…
GitHub Spec Kit, an extensible intent-driven harness for coding agents, ships with a built-in Spec-Driven Development process (Spec → Plan → Tasks → Implement) and supports 35 integrations including C…
Soar AI on July 26, 2026, released what it calls the first Model Context Protocol (MCP) interface for booking flights at market rates with no extra fees, supporting x402 payments and compatibility wit…
A user fixed driver issues on a 2010 MacBook Pro running Gentoo Linux by using Codex (likely a reference to OpenAI's Codex or a similar AI tool), which generated kernel patches that resolved graphics …
Multiple new tools, including TerminAI and Termic, launched to integrate AI agents directly into command-line interfaces, enabling Claude and Codex to analyze shell output and compose commands without…
A developer built a KDE Plasma panel HUD for Arch Linux that tracks AI quota usage across Claude, Codex, Gemini, and DeepSeek using four circular indicators, after fixing a bug caused by relying on po…
Noah Nawara released rucksack v0.1.0-alpha.1, a macOS CLI tool that pins a Mac to a phone hotspot and holds a sleep lease so local coding agents continue running with the lid closed. The source-only a…
Terminal Sessions, a new VSCode extension, wraps every terminal in a tmux session that survives full editor restarts, crashes, and reboots, with first-class awareness of AI coding agents including Cla…