
Codex CLI is an open source coding assistant that runs on your computer and works with local repositories. It's for developers who want to explore code, make changes, and use their existing development tools from the terminal. It runs on macOS, Windows, and Linux under the Apache 2.0 license.
The agent can inspect files, edit code, and run commands. You choose its permissions and can see commands and diffs as a task progresses. A separate review mode checks uncommitted changes, a commit, or changes against a base branch without editing the working tree. You can steer an active task and return to a saved session later.
Codex CLI also fits repeatable work: its noninteractive mode can run tasks from scripts and CI. It accepts images, including screenshots and diagrams, as context for a task. Skills provide reusable instructions, while plugins and MCP servers connect it to other tools and data. Web search is available when a task needs current information.
The CLI runs locally, but getting started involves signing in through ChatGPT or another available method. You can choose the model and reasoning effort for a session. Codex cloud is a separate option for submitting work to a configured environment and applying the result to your local repository.
Claim this page with an email at developers.openai.com. Codex CLI gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Codex CLI?Promote it
Something wrong or outdated on this page?
27.5KUpdated 34 minutes agoMIT
VS Code · JetBrains#Code execution#Git integration#MCP
Kilo Code is an AI coding agent for developers who want help writing and understanding code in their editor or terminal. It runs in VS Code, JetBrains IDEs and the CLI, with cloud agents available for remote work. The project is open source under the MIT license and can be self-hosted.
211.1KUpdated 1 hour agoMIT
macOS · Windows · Linux#Code execution#Human approval#Multi-agent workflows
42Updated 12 hours ago
macOS · Windows · Linux · Docker#Agent Skills#Code execution#Distributed execution
4.4KUpdated 19 hours agoMIT
macOS · Windows · Linux · Web · JetBrains#Agent Client Protocol#Code execution#Git integration
89.6KUpdated 3 hours agoMIT
macOS · Windows · Linux · Docker#Agent Client Protocol#Git integration#Human approval
28.2KUpdated 1 day agoApache-2.0
macOS · Windows · Linux · Web · VS Code · JetBrains#Code execution#Git integration#MCP
OpenCode is a free, MIT-licensed AI coding agent for developers working in a terminal, IDE, or desktop app. The desktop app runs on macOS, Windows, and Linux, with support for both Apple Silicon and Intel Macs. It can use local models, giving developers a way to run the model on their own hardware.
Code Buddy is an AI coding assistant for developers who want a terminal agent running on their own machine, with a choice of local or cloud models. It reads repositories, edits code and runs commands on Linux, macOS and Windows. Ollama keeps model inference local without an API key or account; cloud providers send model requests off the machine. Routing includes automatic provider failover.
gptme is a self-hosted AI agent that works directly in your terminal, with access to your files and installed tools. It's for developers who want a coding assistant in their own environment, and people who want an agent for data analysis or other knowledge work. The software is free under the MIT license and doesn't require a gptme account.
OpenHands is a coding agent platform for developers and teams that want agents to make changes across a codebase and handle recurring engineering work. You can run it on your own computer or self-host it on a server. Its core is open source under the MIT license, and a separate OpenHands Cloud service offers hosted execution.
Qwen Code is an Apache 2.0 licensed AI coding agent for developers who want help working through a codebase, changing code and checking the result. It runs on macOS, Windows and Linux, with a terminal interface and a desktop app. It builds on Google Gemini CLI and has developed into an agent that can use Qwen models alongside other model providers.