Tags: Claude Code

OpenAI has added plugin support to its Codex coding assistant, a move aimed at narrowing the functional gap with rival AI coding tools from Anthropic and Google. The new plugins are packaged bundles that may contain skills, app integrations, and Model Context Protocol (MCP) servers, letting users configure Codex for specific tasks with a single click. While power users could already achieve similar results through custom instructions and MCP servers, the plugin library—featuring integrations such as GitHub, Gmail, Box, Cloudflare, and Vercel—offers a more streamlined, searchable experience. Read more

Anthropic has begun previewing a new "auto mode" inside Claude Code, offering a middle ground between the default safety‑first behavior and fully autonomous operation. The feature uses a classifier to allow Claude to perform actions it deems safe while steering away from potentially dangerous commands, such as mass file deletions or malicious code execution. Anthropic cites recent high‑profile AI‑related outages as motivation, and warns that the system is not flawless. The mode is initially available to team‑plan users, with broader Enterprise and API rollout planned in the coming days. Read more

Anthropic has launched an auto mode for its Claude Code tool, allowing the AI to act on users' behalf while reducing the risk of unwanted actions. The feature flags and blocks potentially risky operations, prompting the model to retry or request user intervention. Currently available as a research preview for Team plan users, Anthropic plans to extend access to Enterprise and API users in the coming days. The company emphasizes that the tool remains experimental and recommends use in isolated environments. Read more

Anthropic announced that its Claude Code and Claude Cowork tools are being updated to operate directly on a user's computer. The new functionality lets the AI open files, browse the web, and run development tools. When activated, Claude first looks for connectors to services like Google Workspace or Slack, but can still perform tasks without a connector. The system asks for permission before taking actions, and Anthropic advises against using it for sensitive data. The feature launches as a research preview for Claude Pro and Claude Max subscribers on macOS and integrates with the Dispatch messaging platform. Read more

OpenAI announced an agreement to acquire Astral, the creator of popular open‑source Python development tools such as uv, Ruff, and ty. The acquisition will integrate Astral’s projects into OpenAI’s Codex team, allowing AI agents to work more directly with tools developers already use. OpenAI pledged continued support for the open‑source community while enhancing Codex’s capabilities. The move intensifies competition with Anthropic’s Claude Code, which recently added the JavaScript runtime Bun. Earlier this month, OpenAI also secured Promptfoo, an open‑source security tool for large language models. Read more