win-pilot
与代理无关的 Windows 和 Chromium 计算机使用运行时，适用于 Codex、Claude Code、Qoder、Pi 和 DeepSeek Harness。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add win-pilot@0.1.3Win Pilot 以 win-pilot 发布，当前版本为 0.1.3。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
English | 中文
Win-Pilot is an Agent Plugin for Windows Computer Use. It gives Windows agents one consistent computer tool for desktop applications and isolated Chromium sessions, with the same actions, recovery rules, and results across plugin, MCP, CLI, skill, and native-host integrations.
| Feature | Concrete behavior |
|---|---|
| Agent Plugin package | .codex-plugin/plugin.json bundles the MCP server and operating skill |
| Native Windows control | UI Automation, Win32 input/window management, and window-scoped screenshots |
| Background-first actions | Supported capture and input paths avoid unnecessary focus stealing |
| Isolated browser control | Launches Edge sessions and controls them through CDP-bound targets and tokens |
| Recoverable protocol | Stable ok, outcome, error_code, post-action observations, and unknown-outcome handling |
| Universal fallbacks | Local stdio MCP for tool-aware agents; JSON CLI plus skill for shell-capable agents |
| Schema portability | Tool schema is validated for OpenAI- and Gemini-family consumers |
Send this single instruction to an agent on the Windows machine:
Install and verify Win-Pilot by following https://raw.githubusercontent.com/JeremyWangCY/win-pilot/main/AGENT_INSTALL.md
The agent will prefer the complete plugin, then fall back to MCP or CLI only when its host lacks plugin support.
Plugin-capable hosts can install JeremyWangCY/win-pilot. The package contains both .mcp.json and skills/win-pilot.
For other hosts:
npm install -g win-pilot@latest
win-pilot doctor --probe
Register this local MCP server through the host's normal plugin/tool settings:
{
"mcpServers": {
"win-pilot": { "command": "win-pilot", "args": ["mcp"] }
}
}
Convenience installers are provided for known hosts, while generic modes remain available for every other agent:
win-pilot install --agent codex
win-pilot install --agent claude
win-pilot install --agent qoder
win-pilot install --agent pi
win-pilot install --agent dsh
win-pilot install --agent mcp
win-pilot install --agent cli
Verify with:
win-pilot --version
win-pilot status --json
win-pilot doctor --probe --json
Expected: version 0.1.1, platform win32, and every required doctor check marked ok.
Finish active UI tasks, update the runtime, and restart or reload the host's plugin/MCP process:
npm install -g win-pilot@latest
win-pilot doctor --probe
DSH profiles must be restarted separately. Re-run win-pilot install when you want its managed skill copy refreshed; user-maintained custom skills are not updated in the background.
When a sandbox reaps children after every command, configure win-pilot mcp in the host's persistent plugin or MCP supervisor. Do not detach a process from an ephemeral command. Shell-only agents can use one-shot win-pilot request calls.
MCP and plugin hosts expose computer. Shell-only hosts use the identical JSON interface:
win-pilot request --payload '{"action":"list_apps"}' --json
win-pilot request --payload '{"action":"get_window_state","hwnd":12345,"include_text":true}' --json
win-pilot request --payload '{"action":"click","hwnd":12345,"element_index":7,"snapshot_id":"<snapshot>"}' --json
| Family | Actions | Main inputs |
|---|---|---|
| Discovery | list_apps, list_windows, get_app_identity | app, hwnd |
| Observation | get_window_state, get_window, screenshot | include_text, include_screenshot |
| Pointer | click, double_click, mouse_move, drag, scroll | x, y, element_index, snapshot_id |
| Keyboard | type_text, press_key, hold_key, set_value | text, key, keys, duration_ms |
| Windows | launch_app, activate_window, minimize_window, close_window | name, hwnd, foreground |
| Browser | browser_state, browser_observe, browser_open, browser_click, browser_click_text, browser_click_point, browser_type, browser_replace, browser_key, browser_upload | browser, tab_id, browser_element, screenshot_id, url |
| Sequencing | wait, batched actions | seconds, when, expect |
The live MCP tools/list result is authoritative for the complete parameter schema and defaults.
Windows Agent
├─ Agent Plugin ─┐
├─ stdio MCP ────┼─> Win-Pilot runtime ─> PowerShell helper ─> UIA / Win32 / WGC
├─ CLI + Skill ──┤ └────────────> CDP provider ─────> isolated Edge
└─ Native Adapter┘
The runtime is the deep module: it owns action semantics and results. Adapters only register and render its interface, so fixes remain local and every host receives the same behavior.
Win-Pilot runs with the Windows user's permissions. It contains no telemetry and does not upload screenshots. Browser navigation makes ordinary network requests to requested sites. Installing the plugin does not bypass host approvals, sandbox rules, or task authorization.
| Symptom | Likely cause | Fix |
|---|---|---|
computer is absent | Plugin/MCP added after session start | Restart the agent or reload MCP servers |
| MCP exits immediately | Started inside an ephemeral sandbox command | Move it to the persistent host supervisor |
browser_endpoint required | No owned browser exists | Launch Edge with headless: true first |
| Token is stale | Target state changed or token expired | Observe the same target again |
| Doctor fails | Runtime prerequisite missing | Inspect win-pilot doctor --probe --json |
Compatibility-build diagnostics currently use %TEMP%\win-pilot-diag.log.
git clone https://github.com/JeremyWangCY/win-pilot.git
cd win-pilot
npm test
npm pack --dry-run
Tests exercise the public CLI protocol, MCP discovery/calls, plugin manifest, installation plans, and owned Windows/browser fixtures.