A · level
agent-desktop
97.9
24,948 stars · Apache-2.0
Workflow Automation
Too close to call · 97.9 to 97.1
A · level
97.9
24,948 stars · Apache-2.0
B · level
97.1
23,377 stars · MIT
agent-desktop versus ego-lite is a Workflow Automation comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. agent-desktop is written mainly in Rust; ego-lite is written mainly in JavaScript. The composite score is 97.9 for agent-desktop and 97.1 for ego-lite.
agent-desktop has 24,948 GitHub stars to ego-lite's 23,377, a gap of 1,571 (1.07×). Forks are 1,864 for agent-desktop and 1,324 for ego-lite. On the log scale used inside this pair, adoption is 100 versus 99, and the fork community is 100 versus 96.
Push history: agent-desktop was last pushed on 17 November 2026 (0 days ago), and ego-lite was last pushed on 17 November 2026 (0 days ago). Open issues stand at 260 for agent-desktop (0.010 per star) and 291 for ego-lite (0.012 per star). Issue-health scores are 84 and 84; activity scores are 100 and 100.
agent-desktop is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. ego-lite is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. License scores in this pair are 96 for agent-desktop and 96 for ego-lite. This is a procurement signal, not legal advice.
In Workflow Automation, both agent-desktop (24,948 stars) and ego-lite (23,377 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: agent-desktop is open source, ego-lite is open source.
agent-desktop is ahead on every scored dimension that is not level. Level dimensions: recent activity, issue health, license flexibility, self-hosting. The widest gap is fork community at 4 points (100 vs 96), and the tightest is self-hosting at 0 points (100 vs 100).
Composite score: agent-desktop 97.9, ego-lite 97.1. The margin is under one point, so this page calls a tie. Use the dimension breakdown rather than the headline number.
Scores are computed inside this pair only. Method and weights.
Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.
| Signal | agent-desktop | ego-lite |
|---|---|---|
| GitHub stars | 24,948 | 23,377 |
| Forks | 1,864 | 1,324 |
| Open issues | 260 | 291 |
| Adoption | 100 | 99 |
| Activity | 100 | 100 |
| Community | 100 | 96 |
| Issue health | 84 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.9 | 97.1 |
Computer use CLI for AI agents
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.
agent-desktop has more GitHub stars: 24,948 versus 23,377 for ego-lite. The gap is 1,571 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both agent-desktop and ego-lite as self-hostable. Confirm each project's deploy docs before you plan a migration.
agent-desktop is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. ego-lite is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
Neither tool clears a one-point margin. agent-desktop scores 97.9 and ego-lite scores 97.1.