ego-lite
Enables AI agents and engineers to operate simultaneously in the same browser context, reducing context switching and accelerating workflows where automation…
ego lite is a macOS browser built for you and your AI agents to share. Agents run browser tasks in their own Spaces while your tabs stay yours, and can reach your real logins, cookies, and extensions if you opt into Chrome data migration at first launch. Installing the app (or running npx skills add citrolabs/ego-lite) adds an ego-browser skill to your agents' skills directories; you then type /ego-browser followed by a plain-language task.
- Ask Claude to browse and analyze competitor websites while you code simultaneously
- Generate automated reports by having Claude extract data from multiple web pages in parallel
- Automate testing workflows where Claude inspects live websites while your team works elsewhere
Enables AI agents and engineers to operate simultaneously in the same browser context, reducing context switching and accelerating workflows where automation and human oversight occur in parallel.
Engineering teams integrating AI agents into development pipelines requiring real-time human review and intervention.
https://github.com/citrolabs/ego-lite
By citrolabs
How to Get It
npx skills add citrolabs/ego-lite # or download the macOS .dmg (Apple Silicon / Intel) from the repo
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Browse and analyze competitor websites while me code simultaneously
Trust Signals Auto-scanned
Community Pulse Emerging
Discussed on Hacker News
- Show HN: Ego lite – why our browser agent writes JavaScript not CLI commands — Hacker News · 12 pts
1 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 95 GitHub stars; contributors unknown; last commit 2d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 95 GitHub stars; contributors unknown; last commit 2d ago; license MIT.