A · leads
agent-desktop
97.9
24,948 stars · Apache-2.0
Workflow Automation
agent-desktop leads by 1.6 · narrow
A · leads
97.9
24,948 stars · Apache-2.0
B
96.3
17,690 stars · MIT
agent-desktop versus leon 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; leon is written mainly in TypeScript. The composite score is 97.9 for agent-desktop and 96.3 for leon.
agent-desktop has 24,948 GitHub stars to leon's 17,690, a gap of 7,258 (1.41×). Forks are 1,864 for agent-desktop and 1,484 for leon. On the log scale used inside this pair, adoption is 100 versus 97, and the fork community is 100 versus 97.
Push history: agent-desktop was last pushed on 17 November 2026 (0 days ago), and leon was last pushed on 17 November 2026 (0 days ago). Open issues stand at 260 for agent-desktop (0.010 per star) and 118 for leon (0.007 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. leon 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 leon. This is a procurement signal, not legal advice.
In Workflow Automation, both agent-desktop (24,948 stars) and leon (17,690 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, leon 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 adoption at 3 points (100 vs 97), and the tightest is self-hosting at 0 points (100 vs 100).
agent-desktop finishes ahead at 97.9 against leon at 96.3, a 1.6 point narrow margin under the published weights.
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 | leon |
|---|---|---|
| GitHub stars | 24,948 | 17,690 |
| Forks | 1,864 | 1,484 |
| Open issues | 260 | 118 |
| Adoption | 100 | 97 |
| Activity | 100 | 100 |
| Community | 100 | 97 |
| Issue health | 84 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.9 | 96.3 |
Computer use CLI for AI agents
🧠 Leon is your open-source personal assistant.
agent-desktop has more GitHub stars: 24,948 versus 17,690 for leon. The gap is 7,258 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both agent-desktop and leon 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. leon 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.
agent-desktop scores 97.9 and leon scores 96.3. This page calls that a narrow lead for agent-desktop.