Code is a fast, local coding agent for your terminal. It's a community-driven fork of openai/codex focused on real developer ergonomics: Browser integration, multi-agents, theming, and reasoning control — all while staying compatible with upstream.

• 🌐 Browser Integration - CDP support, headless browsing, screenshots
• 📝 Diff Viewer - Side-by-side diffs with syntax highlighting
• 🤖 Multi-Agent Commands - /plan, /solve, /code with agent panels
• 🎨 Theme System - /themes with live preview and accessibility
• 🧠 Reasoning Control - /reasoning for dynamic effort adjustment
• 🔌 MCP support – Extend with filesystem, DBs, APIs, or your own tools.
• 🔒 Safety modes – Read-only, approvals, and workspace sandboxing.
• 🔁 Backwards compatible – Reads both ~/.code/* (primary) and legacy ~/.codex/*; writes only to ~/.code/*

Simple interface	Unified diffs

Browser control	Assist with Claude & Gemini

npx -y @just-every/code

npm install -g @just-every/code
code // or `coder` if you're using VS Code

Note: If another tool already provides a code command (e.g. VS Code), our CLI is also installed as coder. Use coder to avoid conflicts.

Authenticate (one of the following):

• Sign in with ChatGPT (Plus/Pro/Team; uses models available to your plan)
  • Run code and pick "Sign in with ChatGPT"
  • Stores creds locally at ~/.code/auth.json (still reads legacy ~/.codex/auth.json if present)
• API key (usage-based)
  • Set export OPENAI_API_KEY=xyz and run code

Code supports orchestrating other AI CLI tools. Install these and config to use alongside Code.

npm install -g @anthropic-ai/claude-code @google/gemini-cli && claude "Just checking you're working! Let me know how I can exit." && gemini -i "Just checking you're working! Let me know how I can exit."

# Connect code to external Chrome browser (running CDP)
/chrome        # Connect with auto-detect port
/chrome 9222   # Connect to specific port

# Switch to internal browser mode
/browser       # Use internal headless browser
/browser https://example.com  # Open URL in internal browser

# Plan code changes (Claude, Gemini and GPT-5 consensus)
# All agents review task and create a consolidated plan
/plan "Stop the AI from ordering pizza at 3AM"

# Solve complex problems (Claude, Gemini and GPT-5 race)
# Fastest preferred (see https://arxiv.org/abs/2505.17813)
/solve "Why does deleting one user drop the whole database?"

# Write code! (Claude, Gemini and GPT-5 consensus)
# Creates multiple worktrees then implements the optimal solution
/code "Show dark mode when I feel cranky"

# Try a new theme!
/themes

# Change reasoning level
/reasoning low|medium|high

# Switch models or effort presets
/model

# Start new conversation
/new

code [options] [prompt]

Options:
  --model <name>        Override the model (gpt-5, claude-opus, etc.)
  --read-only          Prevent file modifications
  --no-approval        Skip approval prompts (use with caution)
  --config <key=val>   Override config values
  --oss                Use local open source models
  --sandbox <mode>     Set sandbox level (read-only, workspace-write, etc.)
  --help              Show help information
  --debug             Log API requests and responses to file
  --version           Show version number

Code can remember context across sessions:

1. Create an AGENTS.md or CLAUDE.md file in your project root:

# Project Context
This is a React TypeScript application with:
- Authentication via JWT
- PostgreSQL database
- Express.js backend

## Key files:
- `/src/auth/` - Authentication logic
- `/src/api/` - API client code  
- `/server/` - Backend services

2. Session memory: Code maintains conversation history
3. Codebase analysis: Automatically understands project structure

For automation and CI/CD:

# Run a specific task
code --no-approval "run tests and fix any failures"

# Generate reports
code --read-only "analyze code quality and generate report"

# Batch processing
code --config output_format=json "list all TODO comments"

Code supports MCP for extended capabilities:

• File operations: Advanced file system access
• Database connections: Query and modify databases
• API integrations: Connect to external services
• Custom tools: Build your own extensions

Configure MCP in ~/.code/config.toml (legacy ~/.codex/config.toml is still read if present). Define each server under a named table like [mcp_servers.<name>] (this maps to the JSON mcpServers object used by other clients):

[mcp_servers.filesystem]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/project"]

Main config file: ~/.code/config.toml

# Model settings
model = "gpt-5"
model_provider = "openai"

# Behavior
approval_policy = "on-request"  # untrusted | on-failure | on-request | never
model_reasoning_effort = "medium" # low | medium | high
sandbox_mode = "workspace-write"

# UI preferences see THEME_CONFIG.md
[tui.theme]
name = "light-photon"

# Add config for specific models
[profiles.gpt-5]
model = "gpt-5"
model_provider = "openai"
approval_policy = "never"
model_reasoning_effort = "high"
model_reasoning_summary = "detailed"

• CODEX_HOME: Override config directory location
• OPENAI_API_KEY: Use API key instead of ChatGPT auth
• OPENAI_BASE_URL: Use alternative API endpoints
• OPENAI_WIRE_API: Force the built-in OpenAI provider to use chat or responses wiring

How is this different from the original?

This fork adds browser integration, multi-agent commands (/plan, /solve, /code), theme system, and enhanced reasoning controls while maintaining full compatibility.

Can I use my existing Codex configuration?

Yes. Code reads from both ~/.code/ (primary) and legacy ~/.codex/ directories. We only write to ~/.code/, so Codex will keep running if you switch back; copy or remove legacy files if you notice conflicts.

Does this work with ChatGPT Plus?

Absolutely. Use the same "Sign in with ChatGPT" flow as the original.

Is my data secure?

Yes. Authentication stays on your machine, and we don't proxy your credentials or conversations.

We welcome contributions! This fork maintains compatibility with upstream while adding community-requested features.

# Clone and setup
git clone https://github.com/just-every/code.git
cd code
npm install

# Build (use fast build for development)
./build-fast.sh

# Run locally
./codex-rs/target/dev-fast/code

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Make your changes
4. Run tests: cargo test
5. Build successfully: ./build-fast.sh
6. Submit a pull request

• This project is a community fork of openai/codex under Apache-2.0. We preserve upstream LICENSE and NOTICE files.
• Code is not affiliated with, sponsored by, or endorsed by OpenAI.

Using OpenAI, Anthropic or Google services through Code means you agree to their Terms and policies. In particular:

• Don't programmatically scrape/extract content outside intended flows.
• Don't bypass or interfere with rate limits, quotas, or safety mitigations.
• Use your own account; don't share or rotate accounts to evade limits.
• If you configure other model providers, you're responsible for their terms.

• Your auth file lives at ~/.code/auth.json (legacy ~/.codex/auth.json is still read).
• Inputs/outputs you send to AI providers are handled under their Terms and Privacy Policy; consult those documents (and any org-level data-sharing settings).

AI providers can change eligibility, limits, models, or authentication flows. Code supports both ChatGPT sign-in and API-key modes so you can pick what fits (local/hobby vs CI/automation).

Apache 2.0 - See LICENSE file for details.

This project is a community fork of the original Codex CLI. We maintain compatibility while adding enhanced features requested by the developer community.

Need help? Open an issue on GitHub or check our documentation.