# I Built an Open-Source Remote Console to Control Codex, Claude Code, Antigravity & Grok From My Phone

> Source: <https://ainexusdaily.vercel.app/article/2026-11-17-i-built-an-open-source-remote-console-to-control-codex-claude-code-antigravity-g>
> Published: 2026-11-17 15:30:12+00:00

# I Built an Open-Source Remote Console to Control Codex, Claude Code, Antigravity & Grok From My Phone

If you run Codex, Claude Code, Antigravity, and Grok across multiple projects (or even multiple Codex accounts), two pains hit you fast: At your desk: Juggling 4+ IDE windows and terminals eats gigabytes of RAM just to check who is stuck waiting for permission. Away from your desk: You walk away for

coffee or a commute and have no clean way to inspect diffs, approve tool calls, interrupt a runaway loop, or queue the next instruction from your phone. Existing codex-bridge scripts usually cover only one engine or require setting up Tailscale/chat bots manually. So I built Agent Control—an open-source (AGPL-3.0), self-hosted desktop & mobile remote console with a built-in 5-language UI (English, 简体中文, 繁體中文, 日本語, 한국어). Website: https://hub.guuguo.top/agent-control GitHub: https://github.com/guuguo/agent-control Remote-controlling local coding agents requires real trust, so Agent Control is designed around strict local boundaries: Strictly Read-Only Upstream Indexing: Reads ~/.codex, ~/.claude, and ~/.gemini histories in read-only mode.

Custom titles, tags, and archives live in Agent Control's own data directory—your upstream databases are never modified. Zero Cloud Prompt Storage: Your code and conversations never touch a third-party cloud database. Remote connections route directly through your chosen tunnel or self-hosted relay, protected by one-time pairing codes and HTTP-only session cookies. Automatically discovers multiple local Codex accounts and displays per-account quotas side by side alongside Claude Code, Antigravity, and Grok sessions—grouped cleanly by project workspace.

Scan a QR code from your phone's browser to check live streaming output, review code diffs, approve/deny tool calls, or queue follow-up turns. Starts with a $0 Cloudflare Quick Tunnel out of the box (QR code ready in ~5 seconds, no account needed), and lets you switch anytime to $0 Tailscale Funnel (*.ts.net), Cloudflare Named Tunnel, or a self-hosted Docker / Sealos Relay. Includes a wake-locked VAD voice mode that announces task completions or pending approvals and lets you approve/dispatch tasks hands-free using low-latency models (Claude Sonnet, GPT, Antigravity, or Grok). Check out the full documentation (available in English, 简体中文, 日本語, 한국어, and 繁體中文), security architecture, and one-line install instructions on GitHub or the project site: Project Page: https://hub.guuguo.top/agent-control GitHub Repository: https://github.com/guuguo/agent-control If you juggle multiple AI coding agents too, feedback and stars are always appreciated!

## Key Takeaways

- •Existing codex-bridge scripts usually cover only one engine or require setting up Tailscale/chat bots manually.
- •This story was reported by **Dev.to** , covering developments in the**dev** space.
- •AI advancements continue to reshape industries — read the full article on Dev.to for complete coverage.

📖 Continue reading the full article:

[Read Full Article on Dev.to →](https://dev.to/guuguo/i-built-an-open-source-remote-console-to-control-codex-claude-code-antigravity-grok-from-my-gk8)
