Integrate ego-lite (Chromium for AI Agents) into DSH, providing 32 structured browser tools and a real-time observation window. Users can watch AI operate web pages and take over at any time.
- Language
- JavaScript
- Branch
- master
Install
$ dsh plugin --profile web add dsh-ego-browserRun the command above in your terminal to install this plugin via the dsh CLI. You can switch Profile in the top-right corner. New to dsh? Read the beginner tutorial
Install via your agent
Install the DeepSeek Harness plugin Fisfzy/ego-browser for me: review the repository at https://github.com/Fisfzy/dsh-ego-browser first, then run the install command and verify the plugin loads successfully.
Paste this instruction to the DSH Web GUI assistant — it will install and verify for you.
One-Line Positioning
Connect ego-lite (a Chromium designed for AI Agents, with the runtime embedded in the plugin package) to DeepSeek Harness, exposing 32 structured ego_* tools that enable AI to click, fill forms, read content, and pass verification like a real human on web pages; plus a real-time observation window in the bottom-right corner that lets you watch as AI operates on web pages and take over control when necessary.
Core Capabilities
- Register 32 structured
ego_*tools covering task spaces (open/close), page reading (semantic tree snapshots, attribute reading, screenshots, element info), navigation and waiting, keyboard/mouse interaction, forms and dialogs, human verification detection, network request and download capture, and free script escape hatches - Provide a "🌐" real-time observation window at the bottom-right of DSH Web: uses SSE to push JPEG (CDP backend, default) or fMP4 video stream (FFmpeg backend) to live display the page the agent is browsing, supporting tab switching and history drawer review
- Observation window supports direct takeover: click, drag, scroll, Ctrl+scroll zoom, Ctrl+drag pan, type Chinese after clicking, keyboard shortcuts—all routed back to the same Chromium used by the agent without interrupting the agent to restart
- Built-in human verification detection (reCAPTCHA / hCaptcha / Turnstile / Cloudflare, etc.) and login guidance bar; proactively prompts when agent gets stuck on login or verification
- Cross-platform self-adaptation: Linux/macOS/Windows all supported; root / Docker / no-display environments automatically inject
--no-sandboxwrapper with headless fallback; no manual Chrome configuration needed - Expose operation tools like
ego_doctorfor environment check,ego_auth_flushfor login state persistence,ego_helpfor tool index, etc.
Technical Implementation
- Language: TypeScript (build output:
lib/index.js+lib/client.js+bin/ego-cast-worker.mjsthree bundles) - Key Dependencies:
@deepseek-ai/dsh-tools(tool registration base viadefineTool),@deepseek-ai/schemastery(Config Schema validation),@deepseek-ai/dsh-settings(ego-browsersettings namespace and persistence),react(frontend floating window UI),runtime/ego-linux(embedded ego-lite runtime, vendored) - Architecture Pattern: Cordis dual-sided plugin (
dsh.bundle.patchinjects into host services list,dsh.clientinjects floating window frontend into Web host); eachego_*tool follows the pattern "params → assemble JS script →ctx.subprocesscallego-browser nodejs→ parse by@@DSH_RESULT@@sentinel"; all tools serialized via in-process mutex lock to prevent browser contention - Entry Files:
src/index.ts(plugin apply entry + 32 tool registrations),src/config.ts(Schemastery Config + resolveConfig),src/cast-server.ts(host routes/api/ego/*),src/client/index.ts(floating window frontend single file)
Use Cases
When you want AI to accomplish tasks that can only be done with a browser—capturing pages requiring login state, cross-page form filling, mobile simulation, operating sites with captcha or requiring real human sessions—without opening a separate test account for it, this plugin loans the same Chromium to AI; meanwhile, the observation window makes "what AI is doing, where it's stuck" visible throughout, and you can personally take over when necessary without interrupting the agent.
Prerequisites and Compatibility
| Dependency | Minimum Version | Description |
|---|---|---|
| DeepSeek Harness | 0.1.0-rc.8 | Derived from @deepseek-ai/dsh-* series in peerDependencies; requires host to provide tools / subprocess / webServer (observation window) services |
| Node.js | >=22 | package.json#engines.node; observation window and vendored runtime both rely on Node 22+ built-in capabilities |
| Operating System | macOS / Windows / Linux | Plugin layer supports all three platforms; macOS is official experience, Linux/Windows use community port (see "Known Issues and Limitations") |
| Browser Runtime | Google Chrome / Chromium / Brave / Microsoft Edge (any one) | Auto-detect common paths; root users use plugin's built-in --no-sandbox wrapper script; can manually specify via EGO_LINUX_CHROME or chromePath field in settings |
| Native Modules | None | Plugin body doesn't introduce native modules; vendored runtime is pure JS; FFmpeg binary is optional download (on-demand托管到 ~/.dsh/cache/ego-browser/ffmpeg/) |
Installation
dsh plugin --profile web add github:Fisfzy/ego-browser
Configuration Options
| Config | Type | Description | Default |
|---|---|---|---|
| chromePath | string | Custom Chrome/Chromium executable path; empty triggers auto-detection of common locations | empty (auto) |
| captureBackend | string | Observation window video backend: auto / cdp (default JPEG stream) / ffmpeg (video stream, requires manual install) | auto |
| streamProfile | string | Quality preset: low / balanced / high, determines FPS, max width, and bitrate defaults | balanced |
| cdpFps | number | CDP preview frames per second, 5–30 | 20 |
| cdpQuality | number | CDP JPEG quality, 1–100 | 55 |
| cdpMaxWidth | number | CDP frame max width (pixels), 320–1920 | 960 |
| cdpBackstopIntervalMs | number | Static page fallback screenshot interval (ms), 1000–10000 | 3000 |
| ffmpegFps | number | FFmpeg backend frames, 5–30 | Per profile 15/20/30 |
| ffmpegMaxWidth | number | FFmpeg backend max width, 320–1920 | Per profile 960/1280/1600 |
| ffmpegBitrateKbps | number | FFmpeg target video bitrate (kbps), 500–20000 | Per profile 2000/4000/8000 |
| ffmpegEncoder | string | FFmpeg H.264 encoder: auto / software / h264_mf / h264_nvenc / h264_qsv / h264_amf / h264_videotoolbox / h264_vaapi | auto |
| ffmpegPath | string | Custom FFmpeg path; empty triggers detection in order: PATH → managed cache | empty |
| githubMirror | string | GitHub mirror prefix for managed downloads, e.g., https://gh-proxy.com/github.com | empty |
| egoCliArgs | string | Extra CLI args appended to ego-browser nodejs call; takes effect on next ego_* call; some control args will be filtered | empty |
| chromeArgs | string | Extra options appended to Chrome launch args; takes effect on next browser cold start (browser is singleton); some control args will be filtered | empty |
| egoBin | string | Custom ego-browser CLI path; empty uses vendored runtime/ego-linux/bin/ego-browser.mjs | vendored runtime |
| defaultSpace | string/number | Default task space name; subsequent ego_* calls without space fall back to this | dsh-agent |
| maxOutputBytes | number | Byte limit for each subprocess stdout/stderr collection | 4194304 (4 MiB) |
| graceMs | number | Grace period milliseconds for subprocess timeout | 15000 |
FAQ
Q: I'm starting as root on a Linux server. Can it run without Chrome?
A: Yes. resolveEgoEnv (src/index.ts) automatically detects root and no-display environments, injecting its built-in --no-sandbox wrapper script with headless fallback; as long as the system has any Chrome / Chromium / Edge / Brave installed, it can start. When not found, ego_status immediately gives the executable path and reason.
Q: Can I run multiple AI agent tasks simultaneously? Will they interfere with each other?
A: All ego_* tools are serialized via an in-process mutex lock, so multiple agents within the same plugin instance won't grab the same browser; multi-tasking is isolated by "task spaces"—ego_space_open creates an independent space, and the space parameter routes to the corresponding space. Cookies are isolated between spaces; please log in within the target space.
Q: What are the requirements for the observation window's live feed?
A: The CDP backend (default) has minimal overhead; any machine that can run a modern browser on DSH Web can view it; the FFmpeg backend requires the Chrome window to be correctly captured—Windows must use FFmpeg with gfxcapture filter, macOS first-time use needs "Screen Recording" permission, Linux needs Chromium and FFmpeg to share DISPLAY, Wayland lacking Portal/PipeWire input will prompt switching to CDP.
Q: What if the agent reaches a captcha page?
A: ego_captcha and ego_page_info detect reCAPTCHA / hCaptcha / Turnstile / Cloudflare controls and return { detected, kind }; when detected, a "Human Verification" guidance bar pops up at the top of the observation window—you can directly enter the observation window to complete verification, the agent's same browser is still waiting, and continues after completion.
Q: Am I viewing "DSH's own interface that the agent is operating"? Or is it in another browser?
A: The agent uses this one browser, there's no second one. When it operates on DSH's session management, task board, settings interface, the observation window is equally visible throughout and can be taken over—the plugin documentation calls this "self-observation".
Q: How do I uninstall? Will cookies or profile be left behind?
A: dsh plugin remove follows cordis's standard uninstall flow (fire-and-forget, doesn't block host exit). Chrome profile and vendored runtime are in user-space directories (macOS/Linux: $XDG_STATE_HOME/ego-lite-linux, Windows: %LOCALAPPDATA%\ego-lite-linux); they persist as long as the plugin isn't deleted; to clean completely, manually delete the corresponding directory.
Q: The "32 tools" seem like a lot. How do I find the one I need?
A: Call ego_help once (supports topic parameter for categorized viewing, such as tools / navigate / input / form / wait / network / login / script, etc.), it returns a complete index with categories and one-sentence descriptions.
Learning Curve
Advanced — 32 tools have wide coverage, agent can use directly; regular users only need to install Chrome once and confirm ego_status passes. Advanced users wanting to squeeze quality/frame rate need to understand CDP vs. FFmpeg dual-backend differences, and manually install managed FFmpeg as needed.
Known Issues and Limitations
- Underlying ego-lite host is officially supported on macOS; Linux/Windows use community port; stability of complex multi-step processes is weaker than macOS; tab/space state may be lost between cross-CLI calls
- FFmpeg backend cross-platform capture: Windows needs new build with
gfxcapture; PATH's old version is skipped with prompt to download compatible version; Linux usesx11grab, macOS usesavfoundationdisplay crop; macOS ScreenCaptureKit and Wayland Portal helper are future enhancements - Login state only persists when Chrome shuts down gracefully;强杀 or power loss requires re-login; to immediately固化, call
ego_auth_flushor click "Logged in, save" in the observation window login guidance bar - Tool output schema uses loose
additionalProperties: true; clients should use actual return value as authoritative, not rely on schema-listed fields - During installation, not all DSH peer packages are in public npm registry; regular
pnpm installmay fail when resolving@deepseek-ai/*peers; need to install via DSH profile to provide peers; CDP path doesn't depend on FFmpeg, plugin installation phase won't download binaries - Snapshot quality: Linux uses CDP
DOMSnapshotto rebuild semantic tree (not macOS kernel-level), complex iframe / canvas scenarios may degrade ego_http'smode: server(Node-side fetch.server) may trigger libuv crash in vendored Windows runtime; defaults to browser context (fetch.browser)
仓库:
github.com/Fisfzy/ego-browser(私有 · 内测)|版本历史见 CHANGELOG.md|详情页:dshfind
⚠️ 发布说明:本插件用于 DeepSeek Harness 生态,已在 dshfind 公开展示。仓库保持维护状态,不发布到 npm / 公共 registry;如需转载本仓库内容请注明出处,不要创建用于分发的公开 fork / 镜像。
把 CitroLabs/ego-lite(给 AI Agent 用的 Chromium)接入 DeepSeek Harness:以 32 个结构化 ego_* 工具驱动浏览器,并配一套实时观察前端口——agent 后台操作网页时,你能像看直播一样看到它正在浏览的每个页面,还能直接操作它。
一点私藏的独特之处(self-observation):agent 用的就是这一个 Chromium——连它操作 DSH 自身(管理会话、任务看板、调设置)时,观察窗也实时显示、你能随时接手。不只是"看得见 agent 在网页上干活",连 agent 操作 DSH 界面本身都是全程可见、可掌控的。
开箱即用:插件包内置 ego 运行时(runtime/,MIT,见 THIRD_PARTY_NOTICES.md)——无需克隆官方仓库、无需手动构建,--no-sandbox wrapper 随包自带,root / Docker / 无显示器一键跑。
我们的真正优势(不是口号,是能对照代码和竞品核实的能力)
同样把 ego-lite 接进 DSH,市面上已有同类插件用它只做了 3 个工具——一个 run 脚本、一个 help 指南、一个 status 体检,浏览器仍是后台黑盒。ego-browser 走的是另一条路:把黑盒打开,并且一上来就把"看"和"控"的能力做到位。
| 能力 | ego-browser(本仓库) | 同类插件(Da1dr1em/dsh-ego-browser) |
|---|---|---|
| 结构化工具数 | 32 个,职责单一、可确定性调用 | 3 个(run/help/status) |
| 实时观察窗(CDP JPEG / FFmpeg H.264 双后端 + 标签条 + 历史抽屉) | ✅ 有 | ❌ 无 |
| 监控窗鼠标直接操作真实浏览器(点击/拖拽/滚动回传 CDP) | ✅ 有 | ❌ 无 |
| worker 单实例守卫 + 崩溃/重复自愈 | ✅ 有 | ❌ 无 |
下载捕获 ego_download / 人机验证检测 ego_captcha/ego_page_info | ✅ 有 | ❌ 无 |
平台自适应(Linux/macOS/Windows 自动探测 + root/无头/--no-sandbox 兜底) | ✅ 全平台 | 仅 Windows 预览宿主,需手动配 |
登录态落盘持久化 ego_auth_flush | ✅ 有 | ⚠️ 仅文档级说明 |
关键差异两条:
- 看得到:别家是"跑完告诉你结果"的黑盒;我们实时推流,你看着 agent 操作,卡在验证码/走岔立刻发现。
- 控得住:别家只读;我们监控窗直接驱动同一个 agent 浏览器,需要时你亲手接管(缩放/拖拽/点击),不必打断 agent 重来。
以上对比基于公开可见的可核实事实:本仓库代码(
bin/ego-cast-worker.mjs实时推流 + CDP 输入回传、lib/index.js32 个注册工具、lib/cast-server.jshost 桥接)与同类插件的源码/README。此文档不含对任何他人的贬低——我们只陈述自己多实现并验证了哪些能力。
相对 ego-lite 本体,我们多做了这些(都可对照本仓库代码核实):
| 能力 | 说明(对应代码) |
|---|---|
| 观察窗前端口 | ego-lite 本体是无头 CLI(只有 heredoc 脚本 + 文本输出);我们在其上加了 SSE 实时推流 + 标签条 + 历史抽屉 + 监控窗鼠标直操(bin/ego-cast-worker.mjs、lib/cast-server.js、lib/client.js),让"看"和"控"成为一等能力 |
| 开箱即用 + 跨平台自足 | resolveEgoEnv 自动探测 Chrome/Edge/Brave,内置 --no-sandbox wrapper,root / Docker / 无显示器免配置(lib/index.js);不必像官方那样先装一个 GUI 宿主 |
| 健壮性层 | 冷启动自动重试(只重试 CDP 瞬态,不吞真错)、worker 单实例守卫 + 崩溃自动重启、插件卸载 fire-and-forget 不阻塞宿主退出、前端帧缓存上限(withWarmupRetry / makeEnsureWorker / frameCache) |
| 运维型工具 | ego_doctor(环境体检)、ego_captcha(人机验证探测)、ego_auth_flush(登录落盘)、ego_http(浏览器上下文请求)等,是原生 CLI helper 没有的一层 |
| self-observation | agent 操作 DSH 自身界面时同样实时可见、可接手 |
我们不声称媲美官方 macOS App 的内核级快照或原生多窗口体验;本仓库解决的是"把同一套浏览器能力带进 DSH + Linux/WSL + 看得见"这件事。
它解决什么问题
通用浏览器不是为 agent 设计的,而 Web 上大量交互(登录态、验证码、动态渲染、表单、需真人会话的站点)只有真浏览器能面对——这正是 ego 系 "让 agent 用你已登录的浏览器,而不打扰你"(官网)的由来。
ego-browser 把它接进 DSH,并把最痛的一点——你看不见 agent 在干什么、也插不上手——用一套观察窗解决:
🌐 小球一点看直播;🟦 标签条切换/关闭;🕘 历史抽屉回看;🔍 缩放拖拽;🖱️ 监控窗直接接管真实浏览器。一句话:让 agent 在浏览器里干活,你在旁边既看得见、又随时能接手。
几个常见的上手场景
- 文献 / 数据抓取:让 agent 登录知网 / 谷歌学术翻页收集,你在观察窗看着它滚动、点下一页、下载 PDF,中途卡住立刻能发现。
- 表单与登录:agent 填表到一半,观察窗弹出验证码——你直接接管把验证码点了,再交还给 agent 继续。
- QA / 冒烟测试:让 agent 在自己产品上点一圈,观察窗等于一台"会说话的录屏",顺手还能回看历史轨迹。
- 看 agent 操作 DSH 自身(self-observation):agent 在管理会话 / 调设置时,观察窗同样全程可见、可接手。
✨ 近期亮点
- v0.7.0:观察窗状态灯干活常绿、空闲呼吸;
ego_script每次运行超时timeoutMs真正生效;前端frameCache/pageMeta按标签清理 + 上限兜底,杜绝长会话内存增长;状态路径家目录回退改os.homedir()跨平台化;新增.gitattributes统一 LF 换行。 - v0.6.1:卸载不再阻塞宿主退出(自愈链路稳定);观察窗 worker 单实例守卫 + stale 状态清理;登录/人机验证引导条可关闭且互斥;观察窗主动跟随 agent 正在操作的页面(不再被后台重绘页抢占视图)。
- v0.6.0:工程收敛——
lib/定为唯一源,build改语法校验,杜绝"一构建全回归"。 - v0.5.0:实时 SSE 推流 + 监控窗直接操作 agent 浏览器。
- v0.4.0:Windows 适配。
- 完整历史见 CHANGELOG.md。
前置条件
| 要求 | 说明 |
|---|---|
| Node ≥ 22 | harness 环境自带 |
| 任意 Chrome / Chromium / Brave / Edge | 自动发现,或 EGO_LINUX_CHROME 指定;root 下用自带 wrapper |
| DSH + dshx | 插件装载机制 |
| 带图形界面的 DSH Web(观察窗) | headless 会话仍可用 ego_* 工具,仅无观察窗 |
安装
dshx install ego-browser <ego-browser.tgz> # tarball 或 git URL 均可
dshx list # 应显示:[on] ego-browser
观察窗设置中可选 captureBackend=auto|cdp|ffmpeg(默认 auto,当前解析为 CDP)、画质档位、CDP FPS/JPEG 质量/最大宽度,以及 FFmpeg FPS/最大宽度/码率/编码器/自定义路径。插件先检测自定义路径、系统 PATH 和托管缓存;检测到兼容 FFmpeg 前,设置页禁止选择 FFmpeg,并提供固定版本的一键下载。GitHub 下载可用 githubMirror 替换 https://github.com,例如 https://gh-proxy.com/github.com。FFmpeg 码率范围为 500-20000 kbps,低/平衡/高档默认 2000/4000/8000 kbps。
无需宿主侧任何配置:resolveEgoEnv 自动探测 root / 无显示器并兜底。观察窗 host 路由(/api/ego/spaces 等)仅在有 HTTP server 时注册,headless 是安全 no-op。
工具清单(32 个,前缀 ego_,完整索引见 ego_help)
| 类别 | 工具 |
|---|---|
| 任务空间 | ego_space_open ego_space_close ego_status |
| 页面读取 | ego_snapshot(语义树) ego_page_info ego_read_element |
| 导航/等待 | ego_navigate(复用 tab) ego_wait ego_wait_for_selector ego_wait_for_url ego_wait_for_response |
| 交互 | ego_click ego_fill ego_hover ego_drag ego_select ego_check ego_key ego_scroll |
| 执行/调试 | ego_js(页面求值) ego_cdp(原始 CDP) ego_cli(任意 heredoc) ego_script(多步脚本) |
| 输出 | ego_screenshot ego_download ego_upload |
| 会话/安全 | ego_auth_flush(登录落盘) ego_captcha ego_dialog |
| 元工具 | ego_help ego_doctor ego_http |
观察窗怎么用
右下角 🌐 常驻小球 → 点开:
- 主画面:agent 当前页面实况;点击/拖动/滚轮直接操作页面,Ctrl+滚轮缩放视图、Ctrl+拖动平移,双击复位。点击画面后可直接键盘输入,支持中文 IME、粘贴、Tab/Enter/方向键及 Ctrl/Cmd 快捷键。
- 标签页条:顶部横排,点选切换,
×关闭。 - 历史抽屉(🕘):按时间回看访问轨迹。
- 操作时下方网址行就地显示提示,2 秒后恢复。
- 面板关闭、sidebar Tab 隐藏或组件卸载后,1.5 秒宽限结束即停止画面生产。仅把 DSH 窗口切到后台不会停止串流,避免回前台时反复重建 WGC/FFmpeg;异常关闭由 120 秒 worker lease 超时兜底。
画面后端
cdp:Page.startScreencastJPEG,默认 20 FPS。每个源帧立即按 Chrome 提供的帧 ID ACK,只保留最新待发帧;仅捕获当前观看标签,静态页恢复截图默认 3 秒一次。ffmpeg:Windows 以gfxcapture(hwnd)直接采集目标 Chrome 窗口的 D3D11 surface;其他平台使用显示来源 crop。随后编码 H.264 fragmented MP4 → HTTP 二进制 chunk → MediaSource<video>,不经过 Base64/SSE。auto:默认选择 CDP,不检测成功也不会自动下载 FFmpeg。FFmpeg 安装并通过能力检查后才可选择;已保存的 FFmpeg 后端若后来失效,本次观察会回退 CDP 并展示原因。- Windows FFmpeg 必须包含
gfxcapture。插件按 browser PID、target title 和 CDP window bounds 匹配 HWND;窗口移动或被遮挡时仍捕获目标页面,并且不允许回退到桌面录制。若 target 是同一 Chrome 窗口里的后台 tab,会明确报错而不是展示当前可见 tab 或抢用户焦点。macOS 首次使用需要“屏幕录制”权限;X11 需要 Chromium 与 FFmpeg 共享DISPLAY;Wayland 缺少 Portal/PipeWire 输入时会提示切回 CDP。
托管 FFmpeg 安装到 ~/.dsh/cache/ego-browser/ffmpeg/,不会写入插件目录。Windows/Linux 使用固定 BtbN release tag;macOS 使用固定的 ffmpeg-static GitHub release 资产(其 Intel/Apple Silicon 二进制分别来源于 Evermeet/OSXExperts)。所有下载均固定资源 SHA-256,只提取 FFmpeg 主程序,不安装 ffprobe 或 ffplay。Windows/Linux 解包使用系统 tar;缺少时会在下载前明确报错。
登录态说明:多任务空间 Cookie 相互隔离,请在对应空间内登录。重启 DSH 后运行期登录态被清空(Chrome 运行期 Cookie 仅优雅关闭时落盘),需重登——扫码很快。
工作原理
- 工具层:每个工具把参数拼成 JS 脚本,经
ctx.subprocess用ego-browser nodejs喂给 stdin 运行,宿主经 CDP 驱动共享 Chromium。结果以@@DSH_RESULT@@哨兵行解析。所有ego_*经进程内互斥锁串行化,错误统一归一。 - 观察窗:
lib/client.js管理 watcher lease、JPEG<img>与 MSE<video>;lib/cast-server.js代理元数据 SSE、watch API 和带背压的二进制视频;worker 中CaptureManager保证同时只有一个活动后端和一个当前 target。CDP 控制面(标签、viewport、输入、验证码)独立于画面后端。
开发
npm run build # node --check lib/*.js(lib/ 为唯一权威源,不复编译覆盖)
直接改
lib/(lib/index.js工具层、lib/client.js前端、bin/ego-cast-worker.mjsworker)。新工具在registerActionTools按t({...})加,并在ego_help索引补一条。
node_modules/ 仅含指向 DSH checkout 的符号链接(编译期类型解析);运行时由 harness 解析 @deepseek-ai/dsh-tools。
已知限制(诚实说明)
- Windows:插件层已做 v0.4.0 适配;底层 ego-lite 宿主仍是非 Windows 官方支持的社区移植,复杂多步流程稳定性可能弱于 macOS。
- FFmpeg 平台捕获:Windows 已使用
gfxcapture(HWND),需要包含该 filter 的新构建;PATH 中的旧 FFmpeg 会被跳过并提示下载兼容版本。Linux 使用x11grab、macOS 使用avfoundationdisplay crop;macOS ScreenCaptureKit、Wayland Portal helper 属后续增强。 - 安装环境:本仓库的 DSH peer 包不全在公共 npm registry。普通
pnpm install可能在解析@deepseek-ai/*peer 时失败;DSH profile 安装应提供这些 peer。CDP 不依赖 FFmpeg,也不会在插件安装阶段下载二进制。 - 快照质量:Linux 用 CDP
DOMSnapshot重建语义树,非 macOS 内核级,复杂 iframe/画布场景可能降级。 - 宿主可靠性(Linux):未合并的社区 PR,跨 CLI 调用间可能丢 tab/空间状态;插件已内置防御,简单流程稳定,复杂流程可能需重试。
- 登录态持久化:Chrome 运行期 Cookie 仅优雅关闭时落盘,强杀重启需重登。
- 输出 schema 为宽松
additionalProperties: true,客户端以实际返回值为准。
许可与署名
插件本体 MIT。内置运行时嵌入 ego-lite 的 MIT 代码;可选下载的 FFmpeg 构建涉及 GPL-3.0-or-later 义务。使用或再分发前请阅读构建来源的许可证与源码获取信息,详见 THIRD_PARTY_NOTICES.md。
友链
同为 DeepSeek Harness 插件生态的作品,互相安利:
Read the usage guide →
Install steps, key points, FAQ and compatibility for this plugin — auto-derived from indexed fields.
Listing badge
[](https://deepseek-plugin.org/plugins/Fisfzy/ego-browser)Paste this markdown into your GitHub README to link back to this listing. The badge only states the listing — not a security endorsement.