Cursor, a popular AI-powered code editor, has launched a new ‘Agent’ feature designed to compete directly with established coding assistants like Anthropic’s Claude Code and OpenAI’s Codex. The new experience moves beyond simple code completion, allowing developers to assign complex, multi-step tasks to the AI agent. The agent can autonomously plan, write, and test code to fulfill these requests, aiming to handle entire features or refactors. This launch signals an intensifying competition in the AI coding assistant space, with tools evolving from copilots into more independent agents. Read the full article at https://www.wired.com/story/cusor-launches-coding-agent-openai-anthropic/