ego lite：让你与 AI Agent 并行工作的浏览器
英文标题：🔥 citrolabs/ego-lite
citrolabs 推出 ego lite，一款让用户与 AI Agent 在同一浏览器中并行工作的浏览器产品。每个 Agent 可在独立 Space 中执行浏览任务，不会占用或干扰用户现有标签页，并可通过 Chrome 数据迁移继承登录状态、Cookie、扩展和书签。其 `ego-browser` 技能可连接 Claude Code、Codex、Cursor 及自定义 Agent，并将浏览器操作封装为页面内 JavaScript 工具。官方称，相比 Vercel 的 agent-browser，ego lite 在复杂自动化任务中最高可快 2.5 倍，且消耗更少 Token；目前仅支持 macOS，Windows 和 Linux 版本已列入路线图。
649.2 KB
1.5 KB
1.5 KB
2.5 KB
1.1 KB
2.2 KB
595 B
1.5 KB
1.5 KB
644.7 KB
62.5 KB
62.5 KB
649.2 KB
中文
ego（lite）是一款让你与 AI Agent 并行工作的浏览器。你的 Agent 会在各自的 Space 中运行多个浏览器任务，而你的标签页仍归你所有；任务能以更少的 Token 更快完成。
现有的 browser-use 和 agent-browser 等工具属于浏览器自动化框架：它们需要驱动一个独立浏览器，登录状态无法顺畅继承，而你与 Agent 最终还会争夺同一批标签页。ego lite 是从一开始就为你和 Agent 共同使用而设计的一款浏览器。无需额外设置，Agent 始终可以通过 ego-browser 访问你的真实登录状态和标签页。
ego lite 目前运行于 macOS。Windows 和 Linux 支持已列入路线图。
选择适合你工作流的方式。
1.1 下载 macOS 应用
点击下载，然后打开安装包进行安装。无论采用哪种方式，ego lite 都会将 ego-browser Skill 添加到你设备上每个 Agent 的技能目录中。
1.2 使用 npx 添加 Skill
仅安装 ego-browser Skill：
npx skills add citrolabs/ego-lite
当你的 Agent 首次运行浏览器任务时，它会引导你安装 ego lite 应用。
1.3 让 Agent 为你完成设置
将以下内容粘贴给你的 Agent：
Set up ego lite for me: https://github.com/citrolabs/ego-lite
Read `skills/ego-browser/references/install.md` and follow the steps to install ego lite.
首次启动时，ego lite 会询问一个问题：是否迁移你的 Chrome 数据。选择「是」后，Agent 将继承你现有的登录状态、Cookie、扩展程序和书签。
在 Agent CLI 中，输入 /ego-browser，随后输入一个空格，再用自然语言描述你希望完成的任务：
ego-browser follow @ego_agent on x.com for me
Agent 会调用 ego-browser Skill，在其专属 Space 中打开页面、读取 Snapshot、在页面上执行操作并汇报结果；与此同时，你自己的标签页不会受到影响。
你的浏览数据始终保留在设备上。ego lite 仅会记录你是否在设置期间选择迁移 Chrome 数据。
| 功能 | 作用 |
|---|---|
| 以代码为基础而非以 CLI 为基础，在复杂任务中实现更快运行与更少 Token 消耗 | ego lite 向 Agent 提供的能力被封装为可由 Agent 直接调用的 JavaScript 函数。Agent 可以发挥其最擅长的能力：编写代码，将多步骤任务组合为单个输出，而非陷入「调用两条命令、查看结果、再调用两条命令」的循环。与传统 CLI 方式相比，复杂工作流最高可快 2.5 倍完成，任务成功率更高，且每项任务需要的工具调用显著更少。 |
| 为每个 Agent 提供专属 Space | ego lite 为每个 Agent 提供完全隔离的专属 Space。你可以在前台浏览，Agent 则在后台工作，双方互不干扰。你可以随时查看哪个 Space 正在运行 Agent，也可以接管或停止它。 |
| 你的 Agent 可在 Space 中多任务处理——同一浏览器内的并行工作区 | 每个 Space 都可分配独立的 AI Agent 或独立任务，并同时运行。Claude Code 可在 10 个并行 Space 中丰富 10 条销售线索；Codex 可在另外 5 个 Space 中抓取 5 个竞品网站。它们不会相互冲突，也不会占用你的标签页。你的鼠标仍会停留在原来的位置。 |
| 市场上能力最强的页面 Snapshot | 得益于内核级定制，ego lite 可生成高质量的页面 Snapshot——这是文本模型用来「看见」并操作网页的视图。它能够稳定处理深层嵌套 iframe 等棘手场景，而其他方案通常会在这些场景中失效。 |
任何 Agent 都可通过 ego-browser 驱动它 |
ego-browser 是任意 Agent CLI（Claude Code、Codex、Cursor 或自定义 CLI）与 ego lite 之间的连接层。它将浏览器暴露为一组页面内 JavaScript 工具：snapshot、fill、click、wait、navigate、capture。Agent 编写调用这些工具的 JavaScript 代码片段，ego-browser 会一次性在页面中执行。 |
| 使用越多、Agent 越快的经验积累 （即将推出） | Agent 在浏览器任务中大部分时间都花在试错上。ego lite 的官方 Skill 会将每次成功操作提炼为可复用工具和工作流，因此后续的类似任务最高可快 5 倍完成。 |
ego lite 与现有产品对比
大多数工具都可以自动化浏览器。真正的问题在于：Agent 使用的是哪一种浏览器、你能否同时继续工作，以及该工具是为你已经在使用的 Agent 设计，还是只支持内置 Agent。
| 能力 | ego lite | Browser-Use | agent-browser (Vercel) | ChatGPT Atlas | Perplexity Comet |
|---|---|---|---|---|---|
| 并行多任务处理 | ✓ | — | — | — | — |
| 可复用 Skill | ✓ | — | — | — | — |
| 继承 Chrome 数据 | ✓ | — | — | ✓ | ✓ |
| 同一浏览器、独立工作区 | ✓ | — | — | — | — |
| 压缩语义输入 | ✓ | — | ✓ | — | — |
| 可由外部 Agent 控制 | ✓ | ✓ | ✓ | — | — |
| 数据本地存储 | ✓ | ✓ | ✓ | — | — |
| 无登录摩擦 | ✓ | — | — | ✓ | ✓ |
| 日常使用浏览器 | ✓ | — | — | ✓ | ✓ |
| 免费 | ✓ | ✓ | ✓ | — | — |
另外两类产品也试图解决同一个问题。Browser-Use 和 Vercel 的 agent-browser 等浏览器自动化框架，是由 Agent 调用的库；它们不提供自己的浏览器，因此需要驱动一个独立浏览器，你的登录状态也很少能顺畅继承。ChatGPT Atlas 和 Perplexity Comet 等 AI 浏览器则提供内置 Agent，并且只有该内置 Agent 能够驱动浏览器。ego lite 则是一款从一开始就设计为让你与任何自带 Agent 共同使用的浏览器。
我们在四项复杂浏览器自动化任务中，将 ego lite 与 Vercel 的 agent-browser 进行了基准测试。ego lite 在每项任务中最高可快 2.5 倍完成，并显著减少 Token 消耗。任务越复杂，差距越大。请查看对比结果。
教程、完整工具参考文档和集成指南见 lite.ego.app/document/。
社区
本仓库内容依据 MIT License 发布。ego lite 浏览器为独立提供的免费下载产品。
English / 原文
ego (lite) is a browser where you and your AI agents work in parallel. Your agents run multiple browser tasks in their own Spaces while your tabs stay yours, and tasks complete faster on fewer tokens.
Existing tools like browser-use and agent-browser are browser automation frameworks: they need a separate browser to drive, logins never carry cleanly, and you and the agent end up fighting for the same tabs. ego lite is one browser designed from the start for the two of you to share. No extra setup, and the agent can always reach your real logins and tabs through ego-browser.
01_codex_x_scape_1080p_265.mp4
ego lite runs on macOS today. Windows and Linux are on the roadmap.
Pick whichever fits your flow.
1.1 Download the macOS app
Click to download, then open it to install. Either way, ego lite adds the ego-browser skill to every agent's skills directory on your machine.
1.2 Add the skill with npx
Install just the ego-browser skill:
npx skills add citrolabs/ego-lite
The first time your agent runs a browser task, it walks you through installing the ego lite app.
1.3 Let your agent set it up
Paste this into your agent:
Set up ego lite for me: https://github.com/citrolabs/ego-lite
Read `skills/ego-browser/references/install.md` and follow the steps to install ego lite.
On first launch, ego lite asks one question, whether to migrate your Chrome data. Say yes and your agent inherits your existing logins, cookies, extensions, and bookmarks.
In your agent CLI, type /ego-browser followed by a space, then describe what you want in plain language:
ego-browser follow @ego_agent on x.com for me
The agent picks up the ego-browser skill, opens the page in its own Space, reads a Snapshot, acts on the page, and reports back, all while your own tabs stay untouched.
Your browsing data stays on your device. ego lite only records whether you opted into Chrome migration during setup.
| Feature | What it does |
|---|---|
| Code base, not CLI base, for faster runs with fewer tokens on complex tasks | The capabilities ego lite exposes to the agent are wrapped as JavaScript functions the agent calls directly. The agent gets to do what it does best: write code, composing a multi-step task into a single output instead of getting stuck in a "call two commands, look at the result, call two more commands" loop. Compared to the conventional CLI approach, complex workflows finish up to 2.5× faster with higher task success rates and far fewer tool calls per task. |
| A dedicated Space for every agent | ego lite gives each agent its own fully isolated Space. You browse up front, your agent works in the background, and they don't get in each other's way. You can see which Space has an agent running at any moment, and take it over or stop it whenever you want. |
| Your agents multitask in Spaces, parallel workspaces inside the same browser | Each Space gets its own AI agent or its own task, all running at the same time. Claude Code enriching 10 leads in 10 parallel Spaces. Codex scraping 5 competitor sites in 5 more. They don't collide or steal your tabs. Your mouse stays where you left it. |
| The strongest page Snapshot on the market | Thanks to kernel-level customization, ego lite produces the highest-quality page snapshots, the view text models rely on to "see" and act on a webpage. It reliably handles tough cases like deeply nested iframes, exactly where other approaches consistently break down. |
Any agent can drive it throughego-browser |
ego-browser is the connection layer between any agent CLI (Claude Code, Codex, Cursor, or a custom one) and ego lite. It exposes the browser as a set of in-page JavaScript tools: snapshot, fill, click, wait, navigate, capture. The agent writes a JavaScript snippet calling those tools, and ego-browser runs it on the page in one pass. |
| Experience accumulation that makes your agent faster the more you use it (coming soon) | Most of an agent's time on browser tasks goes to trial and error. ego lite's official Skill distills every successful action into reusable tools and workflows, so similar tasks down the line run up to 5x faster. |
ego lite vs existing products
Most tools can automate a browser. The real questions are what browser the agent gets, whether you can keep working at the same time, and whether the tool is built for the agent you already use or a built-in one.
| Capability | ego lite | Browser-Use | agent-browser (Vercel) | ChatGPT Atlas | Perplexity Comet |
|---|---|---|---|---|---|
| Multitask in parallel | ✓ | — | — | — | — |
| Reusable skills | ✓ | — | — | — | — |
| Inherits Chrome's data | ✓ | — | — | ✓ | ✓ |
| Same browser, separate workspace | ✓ | — | — | — | — |
| Compressed semantic input | ✓ | — | ✓ | — | — |
| Controllable by external agents | ✓ | ✓ | ✓ | — | — |
| Data stored locally | ✓ | ✓ | ✓ | — | — |
| No login friction | ✓ | — | — | ✓ | ✓ |
| Daily-use browser | ✓ | — | — | ✓ | ✓ |
| Free | ✓ | ✓ | ✓ | — | — |
Two other categories try to solve the same problem. Browser automation frameworks like Browser-Use and Vercel's agent-browser are libraries the agent calls; they ship no browser of their own, so they need a separate one to drive and your logins rarely carry cleanly. AI browsers like ChatGPT Atlas and Perplexity Comet ship a built-in agent, and only that agent can drive the browser. ego lite is one browser, designed from the start for you and any agent you bring to share.
We benchmarked ego lite against Vercel's agent-browser on four complex browser automation tasks. ego lite finished each task up to 2.5× faster, with substantially fewer tokens. The harder the task, the bigger the gap. Check the comparison.
Tutorials, the full tool reference, and integration guides live at lite.ego.app/document/.
Community
The contents of this repository are released under the MIT License. The ego lite browser is a separate, free download.