citrolabs/ego-lite

This page introduces an external open-source repository. It is not an HDATF product.

What it does

A macOS browser shared by a person and AI agents such as Codex or Claude Code. Agents run browser tasks in their own Spaces with the user's existing logins, while the user's own tabs stay separate.

How it helps ATF

Its split between the user's tabs and the agent's own Spaces is worth comparing with how the AI assistant in ATF Works acts inside each person's permissions, since reusing real logins raises the same access questions.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

• andrewyng/openworker
  An open-source desktop AI coworker that produces finished work such as security reviews, documents, Slack replies and a triaged inbox. It works with the user's chosen model or local Ollama, and every agent action is governed and logged.
• bojieli/ai-agent-book
  An open-source book, written in Chinese, on AI agent design and engineering, built around the idea that an agent is an LLM plus context plus tools. The repository holds the full text, a compiled PDF and code for each chapter.
• kvcache-ai/AgentENV
  A distributed platform that runs many agent environments on Firecracker across machines and loads OCI images on demand. Environments can snapshot, pause, resume and fork into separate sandboxes for parallel agent work.
• HKUDS/Vibe-Trading
  Vibe-Trading is a personal trading agent that gives an agent trading capabilities such as sentiment analysis, chart pattern detection and an options engine. It offers API and MCP access.
• yc-software/qm
  An agent harness for teams that runs in Slack and on the web. Each person and room gets scoped memory, files, permissions, scheduled jobs and a sandbox, and Pi, OpenCode, Codex or Claude Code can drive the same core.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.