miuuyy/codex-chatgpt-web: Use ChatGPT Web (including Pro) as a native model in Codex — with context, tools, streaming and images, without using Codex quota.

Quit the launcher before updating. These installers select the platform and architecture, verify the published checksums, and preserve your ChatGPT profile and launcher settings.

macOS / Linux

curl -fsSL https://github.com/miuuyy/codex-chatgpt-web/releases/latest/download/install-launcher.sh | sh

Windows PowerShell

irm https://github.com/miuuyy/codex-chatgpt-web/releases/latest/download/install-launcher.ps1 | iex

Automatic modes offer Luna/Think when the account has no reasoning selector; otherwise Instant–High, with Extra High and Pro available independently when exposed by the account.

| Mode | Sending messages | Local Codex tools | | --- | --- | --- | | Browser-only | Automatic | No | | Full harness (With Automation) | Automatic | Yes, through MCP | | Zero Risk | Paste and send manually | Yes, through a separate MCP connector |

Zero Risk does not read or operate the ChatGPT page. Choose the model and Codex Zero Risk connector yourself, paste and send the prepared prompt, then confirm Sent in the launcher. Automatic models ending in (Web) expose their supported Effort choices in Codex. Instant and each Pro version have separate entries to preserve their context budgets; older saved model entries keep their original fixed mode.

Full harness

Full mode connects ChatGPT's tool calls back to the current Codex task through the official OpenAI tunnel-client. The tunnel is outbound: it does not expose a public IP, open an inbound port, or require router forwarding.

The launcher uses your system proxy for the tunnel. Explicitly configured proxy environment variables take priority; local connections stay local.

The launcher's MCP page guides the complete setup. For the exact clicks, see the video walkthroughs.

Limits

> See Limits for the current

ChatGPT message allowances for GPT-5.6 Sol Pro and GPT-6 Astra. Context limits depend on

the account type and selected effort. Plus Medium/High uses a measured 90,000-token window.

GPT-5.6 supports up to 270,000 tokens with experimental 3× context enabled, with native

Codex compaction supported throughout.

> GPT-6 Sol supports Bigger Context at Medium, High and available Extra High: **120,000 tokens

on Plus, with compaction at 110,000, and 240,000 on Pro, with compaction at 220,000**.

GPT-6 Instant uses standard context.

GPT-5.6 and GPT-6 Pro keep their existing Bigger Context limits.

1. Finish the required setup, open MCP, create the Tunnel and regular API key, then press

1. Enable ChatGPT Developer Mode and create a new Tunnel connector named exactly

1. Run Verify runtime to confirm that Codex Native2 is attached and available.

Use Activity for safe local diagnostics and Settings → Run doctor for end-to-end health. Settings can also cancel a retained browser turn or remove the Codex integration before uninstall. Save chats in ChatGPT keeps task conversations in ChatGPT history. On by default for new setups; independent of New browser chat for each turn. Existing explicit choices are preserved when updating. Turn it off to use Temporary Chat, where ChatGPT may not expose your connector. Set CODEX_CHATGPT_WEB_BROWSER_DIAGNOSTICS=1 only when every browser checkpoint needs a screenshot.

New installs use Compatibility V1 for cross-backend subagents. Native preserves Codex's own feature settings and enables plaintext Web-to-Web V2 delegation. Restart Codex and start a new task after changing the protocol:

codex-chatgpt-web subagents status
codex-chatgpt-web subagents compatibility-v1
codex-chatgpt-web subagents native

• This is unofficial browser automation, not an OpenAI API. ChatGPT UI changes can break selectors;

• Browser state is a sensitive login artifact, and the loopback listener is reachable by processes

• Release packages currently target macOS 13+ (arm64/x64), Windows x64, and Linux x64. Runtime,

• Builds are not yet platform-signed, so Gatekeeper or SmartScreen may warn. The installers verify

Read the complete architecture and security model before enabling full mode. Report vulnerabilities through SECURITY.md.

Temporary Chat is a ChatGPT privacy mode; prompts are still processed by OpenAI.

Validation coverage: release validation.

This is independent software and is not affiliated with or endorsed by OpenAI. Use it only with your own account and in accordance with applicable Terms of Use and workspace policies; it does not bypass authentication or access controls.

git clone https://github.com/miuuyy/codex-chatgpt-web.git && \
cd codex-chatgpt-web && \
bun run app

This source path requires Bun 1.4.0. The command installs locked dependencies and opens the app.

bun run app
bun run dev:launcher
bun run src/cli.ts dev status
bun run dev:chat compaction-lab "Reply with exactly: DEV READY"
bun run verify
bun run smoke:subagents
bun run app:package

dev:launcher uses a separate profile and account under ~/.codex-chatgpt-web-dev. dev:chat exercises the real browser and compaction paths with explicit simulated tool results, without changing your normal Codex route. See the DEV chat harness for setup and commands.