OpenAI Codex
OpenAIOpenAI's coding agent for the terminal, editor and cloud tasks
Asynchronous coding agent from Google that clones a GitHub repository into a cloud VM, plans a change, runs tests and opens a pull request.
Jules is a coding agent that works on its own while you do something else. You connect a GitHub repository, pick a branch and describe a task such as fixing a bug, bumping a dependency, writing tests or migrating a framework. Jules clones the code into a cloud virtual machine, writes a plan for you to approve, makes the changes, runs the existing tests or new ones, and shows a diff. When you approve, it pushes a branch and helps open a pull request. Tasks can also be assigned by adding a label to a GitHub issue, and it is available from a command-line tool and an API. It suits developers and small teams with a backlog of routine maintenance work. Compared with an editor assistant that suggests code as you type, it runs whole tasks in the background, several at once, and higher tiers raise the daily task count and model access.
OpenAI's coding agent for the terminal, editor and cloud tasks
Code completion and agents inside the editors most teams already use
Autonomous coding agents in the cloud and on the desktop that take a ticket and return a ready pull request
AI-first code editor with multi-file agent editing