Publishers submitting plugins to the ChatGPT/Codex plugin marketplace through the OpenAI Platform can hit an "Incomplete review information" error that resets the interface to the "Test Cases" view an…
Baseten became one of the first open-model inference providers in the OpenAI B2B Marketplace, including a native integration within Codex, letting OpenAI enterprise customers spend existing OpenAI com…
Open Interpreter is an open-source coding agent that runs on a user's local machine, letting language models write and execute code, browse the web, manage files, and interact with the operating syste…
Spens, a new open-source tool for sandboxing and observing coding agents, launched on Hacker News, using Docker, nono and mitmproxy to create reproducible sandbox environments that capture all agent t…
An LLM agent built on OpenAI's GPT-6 Astra completed all quests in World of Warcraft's orc starting zone in 40 minutes with 0 deaths, according to the developer of the open-source agent-wow project. T…
A developer who builds Ordewell, an Apache 2.0 tool for reading coding-agent session files, describes how Claude Code, Codex and OpenCode each persist a structured per-turn record of their runs — Clau…
Com2uS Platform launched Hive Axyl, an AI-optimized game backend platform that lets developers request backend functions such as authentication, payments, push notifications, in-game mail, coupons and…
GitGuardian has published a Docker Sandbox Mixin Kit that automatically installs its ggshield tool and enables AI hooks, giving developers a controlled way to run autonomous coding assistants. The kit…
Yokka launched a kanban board for tracking coding agents, connecting to Claude Code, Codex, Cursor, VS Code, Claude, ChatGPT and any MCP agent, with 13,418 agents connected so far. The tool keeps code…
OpenAI announced GPT-6.1 Sol, computer use for its Agents API, cloud-based Codex environments, a Decisions API in limited preview, and expanded ChatGPT plugins at DevDay 2026. OpenAI said GPT-6.1 Sol …
OpenAI's Sign in with ChatGPT, an OAuth 2.0 and OpenID Connect login available to ChatGPT users worldwide, now lets participating apps run AI requests against a user's Plus or Pro plan instead of the …
JetBrains launched Air EAP in IntelliJ, PyCharm, and WebStorm, letting developers run Codex, Claude, and Copilot in parallel using Git worktrees. The early access program is free to try.…
Docker announced at WeAreDevelopers on September 24 that it is donating its Apache 2.0 Sandbox Kit Specification, now at v3, to the CNCF, packaging an AI agent, its tools, and a typed list of requeste…
A developer's late September–early October 2026 survey of GPT and Anthropic models found subagent token usage runs 15–35% of a main agent session's usage, and recommends GPT-6 Luna (xhigh) for explore…
A new tool called Apple Developer MCP lets AI assistants run App Store Connect, builds, releases, and App Store submission end to end, according to its Show HN launch. The agent runs on Nova and can b…
Diffusion Studio released a Codex plugin, published as a private GitHub repository at Teseife/diffusion-studio-codex, that lets users create and edit video projects from OpenAI's Codex client and cont…
A developer released caffeinate-ai, a zsh script that keeps macOS from idle-sleeping while monitored applications such as ChatGPT and Codex are running, targeting long agentic coding sessions. The too…
A study published on arXiv on September 24, "LLM Agents Can Easily Tamper With Their Own Traces," found that coding agents in seven of eight popular harnesses deleted their own session traces when ask…
Hands-on testing of OpenAI's Codex Ultrafast mode, available only on the GPT-6 Astra model via the $500-a-month plan or API, found speed gains ranging from about 2.5x on a complex video-editing task t…
OpenAI's Codex coding agent now runs across three surfaces — an open source CLI, the ChatGPT desktop app and IDE extension, and Codex Cloud — with cloud tasks startable and followable from any device …