citrolabs/ego-lite

The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config.

What it solves

Existing browser automation tools often force AI agents to hijack your primary browser, leading to unstable connections, lost session data, and constant interference with your own work. ego lite solves this by providing a dedicated, browser-native environment where agents can perform tasks in isolated "Spaces" without interrupting your active browsing session.

How it works

ego lite acts as both a browser and an integration layer. It provides an ego-browser skill that allows any AI agent (such as Claude Code or Codex) to interact with the web via JavaScript-based tools rather than slow, repetitive CLI commands. By executing these tasks directly within the browser engine, the agent can perform complex, multi-step workflows in a single pass, using your existing cookies and logins while keeping its activity in a separate, parallel workspace.

Who it’s for

This project is for developers and power users who rely on AI agents for web automation, scraping, or repetitive browser tasks and want a more stable, efficient, and non-intrusive way to run these agents alongside their daily work.

Highlights

  • Code-based execution: Agents call JavaScript functions directly, reducing token usage and increasing task speed compared to traditional CLI-based automation.
  • Isolated Spaces: Each agent operates in its own dedicated, parallel workspace, ensuring they never collide with your tabs or each other.
  • High-fidelity Snapshots: The browser engine generates optimized, text-only page representations that allow models to navigate complex structures like nested iframes more reliably.
  • Seamless Integration: Inherits your existing Chrome logins, bookmarks, and extensions, allowing agents to act with your authenticated identity immediately.
  • Cross-Agent Compatibility: Works with any agent CLI, acting as a universal bridge for browser-based AI tasks.

Related

  • Project
    johannesjo/parallel-code

    A GUI for dispatching multiple AI coding agents in parallel, using git worktrees to isolate each task into its own branch and directory for conflict-free development.

  • Project
    vercel-labs/agent-browser

    A high-performance Rust-based browser automation CLI designed to give AI agents reliable, semantic control over web pages and browser state.

  • Project
    feder-cr/invisible_dots

    invisible_dots is an open-source, self-hosted AI agent platform where each agent (a "Dot") lives in its own hardware-accelerated virtual machine with a patched Firefox browser that evades anti-bot detection. It allows long-running tasks, scheduled automations, and integration via MCP servers, CLI, web UI, and messaging channels.

  • Project
    jackwener/OpenCLI

    A browser automation CLI that converts websites into deterministic interfaces for humans and AI agents, allowing them to operate websites using logged-in Chrome sessions.

  • Project
    agent0ai/agent-zero

    Agent Zero is an open‑source Docker‑based framework that gives an LLM‑driven AI agent a full Linux desktop, a browser with DOM‑annotation, live document editors, and a plugin ecosystem. Agents can run GUI apps (e.g., Blender, LibreOffice), edit files, browse and annotate web pages, and even spawn sub‑agents, all while you watch and intervene through a web UI. Installation is via a cross‑platform launcher or a one‑line script, and the system supports project‑scoped workspaces, host‑machine bridging, time‑travel snapshots, and extensive community plugins.