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.
★ 15,743⑂ 1,229👁 44⑃ 326● 536▤ 67
+14
Daily
+267
Weekly
+1,651
Monthly
15,743
stars
1,229
forks
44
watchers
326
prs
536
issues
67
releases
README
macOS Intel · All releases English · 简体中文 · 日本語 · 한국어 Get started · What’s new · Architecture · Troubleshooting Use the ChatGPT Web models available on your account, including Pro, from Codex’s native model picker. Messages run through your signed-in ChatGPT Web session and are subject to the limits applied to that account. Keep the same interface, tasks, images, and streaming. Full harness mode connects ChatGPT to the current task’s files, terminal, tools, and approvals through MCP. Conversations stay tied to your Codex task, so you can keep working as the context grows. Get started Available models: Free/Go → Luna / Think. Paid accounts → GPT-6 Sol and GPT-5.6 Sol, with Instant–High, plus Extra High and Pro when available. Each version has its own entry; existing GPT-5.6 chats keep GPT-5.6. Availability depends on your account and workspace. 1. Install the launcher using the download for your system above. 2. Sign in to ChatGPT in the embedded browser and run the browser smoke test. 3. Install models and restart Codex once. In automatic mode, choose a model ending in (Web). Pro versions have separate entries; Sol reasoning is selected through Effort. Zero Risk keeps its dedicated entry. 4. For coding with tools, open MCP in the launcher and complete the Full harness setup below. The app includes its browser and runtime. No separate Chrome, Node, or Bun installation is needed. Terminal install, updates & repair 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 bash curl -fsSL https://github.com/miuuyy/codex-chatgpt-web/releases/latest/download/install-launcher.sh | sh Windows PowerShell powershell irm https://github.com/miuuyy/codex-chatgpt-web/releases/latest/download/install-launcher.ps1 | iex Models, modes & MCP setup 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 p
Top issues
#622[Tracking] ChatGPT safety blocks and tool/token failures33 comments · 2026-09-21#975[Bug] It returns to the Sign In section6 comments · 2026-11-09#983Free (Luna-only) account: setup --refresh-account-capabilities fails on effort slider verification5 comments · 2026-11-11#977[Bug] 6.1.17/6.1.18: ChatGPT now restores saved composer drafts; Bigger Context stages fail "composer did not preserve the complete prompt" (commonPrefixChars=0)4 comments · 2026-11-09#974[Bug] stream disconnected before completion: ChatGPT final DOM could not be aligned with text already streamed to Codex4 comments · 2026-11-09#982[Bug] 6.1.18 rejects same-turn midnight delta when <subagents> lists plain lines (compaction continuation)2 comments · 2026-11-11#991Passkey session import rejects browser-valid localStorage values above 2 Mi characters1 comments · 2026-11-13#993[Bug] Turns fail after 70 s with "model controls are unavailable" when ChatGPT disables every effort option0 comments · 2026-11-15
Discussions
#992I couldn't able to send messages due to that limit expired popup0 comments · 2026-11-14#990Local execution policy bypass0 comments · 2026-11-12#989Add option to send attachments in base64 strings0 comments · 2026-11-12#988Помогите не могу настроить1 comments · 2026-11-12#980Add Copilot0 comments · 2026-11-10#972Can't add custom MCP server with new account Chat GPT Plus (cre: 4/11/26)2 comments · 2026-11-06#967Unlimited session0 comments · 2026-11-05#966Prepare for R.I.P1 comments · 2026-11-05
Latest release
v6.1.18 v6.1.18 2026-11-08V6 brings ChatGPT Web models into Codex's model and Effort selectors, optional Pro usage estimates, Bigger Context, and control over browser conversations. 6.1.18 improves long-task continuation, preserves goal changes, and fixes macOS passkey-session import. [!IMPORTANT] If Codex shows only Luna (Web) despite a paid ChatGPT account, install this update, open Setup → Install into Codex → Reinstall, and fully restart Codex. The update preserves your launcher settings and ChatGPT profile. Changes in 6.1.18 - Current workspace folders survive partial updates and compaction. The bridge check