Kick off Codex agents on your machine from your phone. Check in on the train, review on the couch, merge from the park.
SeaWorknpm install -g @seawork/cli && seaworkI'll split this into design, copy, and implementation.
Got the plans. Spinning up Codex for the refresh.
Implementation done. Asking Claude for a visual review.
Homepage, docs, and downloads are ready.
Claude Code
Codex
Grok
$ npm run dev --workspace=@seawork/website> @seawork/website@1.0.7 dev> vite --host 127.0.0.1 VITE v7.3.1 ready in 487ms Local: http://127.0.0.1:8082/ hmr update /src/components/landing-hero.astro hmr update /src/components/landing-phone-showcase.astro route /download rebuilt in 132ms route /docs rebuilt in 94ms preview refreshedWhen you want to step away from your desk, you can.
The native mobile app has full feature parity with desktop.
SeaWork
MacBook Pro
Local daemon - connected
seawork/website
Codexcodex/visual-refresh
seawork/app
Claudeclaude/mobile-review
Today
12 runs
Reviews
4 clean
Codex
seawork/website
Polish website mockups for a real SeaWork workflow.
Make PC and mobile previews product-native.
Read packages/website
DoneUpdate hero mockup
DoneTune phone previews
RunningRun typecheck
QueuedReview
landing-hero.astro
+112Claude review
No blocking issues found.
Run multiple providers from a single interface. SeaWork runs the native agent harness as you'd normally run it, with your skills, config and MCP servers intact.
Claude Code
Long-form reasoning and review
Codex
Fast edits inside real repos
Grok
Fast, open-weights builds
Run agents on your laptop, a VM, or a dev server. Control them from any device with a direct connection or an E2E encrypted relay.
E2E Encrypted Relay
or
Direct Connection
Every action has a shortcut. Panels, splits, agents - all from the keyboard.
Fully local voice stack. Speech-to-text and text-to-speech run entirely on your machine, nothing leaves your network.
Refactor the auth middleware to use the new session store, then run the test suite
I'll update the auth middleware to use SessionStore instead of the legacy cookie-based approach. Let me refactor the middleware and update the tests.
Launch agents locally or on any remote host. The --worktree flag spins up an isolated git branch so you can run multiple agents on the same repo without conflicts.
seawork run --agent codex \ --repo ~/code/seawork \ --worktree feat/mobile-review \ "Audit the mobile review flow and open a PR"Have one agent do the work, another verify the result, and loop until it passes. Built-in, no shell scripting needed.
seawork loop run \ --agent claude \ --reviewer codex \ --until "npm run typecheck" \ "Refactor the websocket reconnect path"Run agents on a cron schedule. Automate recurring tasks like dependency updates, security audits, or report generation.
seawork schedule create weekly-security \ --cron "0 9 * * 1" \ --agent codex \ "Review dependency updates and file issues"No. Codex runs on your machine via the official CLI. SeaWork monitors and controls that local agent — prompts, diffs, and code stay on your hardware.
The terminal is fine at your desk. SeaWork adds mobile and desktop control, multi-agent orchestration, and remote access over an E2E encrypted relay so long Codex runs don’t stall when you leave the keyboard.
Yes. Create a Codex agent in SeaWork, pick a GPT-5.6 tier, and connect from iOS or Android to approve tools and send follow-ups while the agent stays on your machine.