Code - A CLI that understands your browser. Sign in with ChatGPT!
by•
Fast, effective, mind-blowing, coding CLI. Browser integration, multi-agents, theming, unified diffs, and reasoning control. Orchestrate agents from OpenAI, Claude, Gemini or any provider.
npm install -g @just-every/code
code // or coder if you have vscode
Replies
Chargedesk
NoteUX Chrome Extension
@zemaj Great work James keep it up (Y)
Chargedesk
@nabeel_khan Thanks!
I love the concept of unified diffs and theming it definitely makes debugging a lot cleaner. Is there a way to save and share custom themes or diff setups for the team?
Chargedesk
@harper_youngÂ
Thank you for the kind words! You can absolutely create your own themes. Code’s theme system lets you start from a base theme and override colours or build an entirely custom palette via your `~/.codex/config.toml`. To share with teammates, you can commit your theme section into your repo and have others copy it into their `.codex` directory. Diff display settings live in the config too; there’s no built‑in cloud sync yet, but we’re exploring easier ways to share presets.
It's super fast. Can it work with other editors besides VSCode?
Chargedesk
@daniel_reed3 Thanks! The CLI doesn’t depend on VS Code – it’s a standalone terminal tool. During installation it registers both a `code` command and a `coder` command to avoid clashing with Visual Studio Code. You can run it from any editor or none at all on macOS, Linux or Windows via WSL with Node 22+.Â
I'm impressed with the unified diffs but does it allow for real time collaboration?
Chargedesk
@brooklyn_campbell Thanks! Right now Code is focused on single‑developer workflows, so there isn’t a real‑time collaboration mode between human users. The multi‑agent commands run GPT‑5, Claude and Gemini together on your machine but don’t sync sessions across developers. For now you can share diffs via version control; real‑time collab is on our radar.
@zemaj Does it run natively on Windows or is it just for macOS/Linux?
Chargedesk
@benjamin_ande Thanks! Officially supported systems are macOS 12+, Ubuntu 20.04+/Debian 10+, and Windows 11 via WSL2. Node 22+ is also required. A native Windows build is a longer‑term goal, but running inside WSL today provides a smooth experience.
The reasoning control is powerful. Can we set custom prompts for each agent?
Chargedesk
@abigail_martinez1 Appreciate it! You can adjust reasoning effort globally via the `/reasoning` command or configure different models and settings via profiles in `config.toml`. At the moment there’s no per‑agent custom prompt hook – multi‑agent commands like `/plan` and `/code` construct prompts automatically – but you can influence behaviour by putting guidance in an `AGENTS.md` file. Fine‑grained per‑agent prompts are something we’re discussing internally.
How do you manage conflicting instructions when multiple agents generate different outputs?
Is there a built-in way to resolve those conflicts?
Chargedesk
@amelia_smith19Â Great question. Multi-agent commands work to avoid conflicts up front: `/plan` builds a consolidated plan across GPT-5, Claude and Gemini, `/solve` runs them in a race and picks the fastest valid answer, and `/code` uses consensus before applying changes. The CLI then shows you a unified diff and requires your approval before any modifications are written. There is no automated merge engine for divergent outputs yet, but the diff viewer makes it easy to choose what to keep.
Does the CLI allow real-time collaboration between agents or is it designed more for executing tasks one after the other?
Chargedesk
@olivia_johnston1Â Right now Code is focused on single-developer workflows. There isn't a real-time collaboration mode between human users; the multi-agent commands run GPT-5, Claude and Gemini together on your machine but don't sync sessions across developers. For now you share diffs via version control. Real-time collaboration is on our radar.
Can the CLI be fully integrated into CI/CD pipelines or is it primarily meant for local development?
Chargedesk
@juan_smith1Â Yes! Code includes a non-interactive mode for CI/CD. You can pass prompts directly with flags such as --no-approval or --quiet to run it headless. The docs include an example GitHub Action that updates changelogs or runs tests in a pipeline.
This CLI looks super versatile with its multi agent orchestration. Can you link reasoning across different providers like OpenAI → Claude → Gemini all in one workflow?
Chargedesk
@scytalelabs_marketing Definitely. Code is built for cross‑provider orchestration. You can install Claude and Gemini adapters alongside Code and then use multi‑agent commands to coordinate them. For example, `/plan` asks GPT‑5, Claude and Gemini to build a shared plan, `/solve` runs a race between them and picks the fastest valid answer, and `/code` applies their consensus before making changes. We’re still working on deeper context passing, but multi‑provider workflows are supported today.