A · leads
leon
96.2
17,690 stars · MIT
Workflow Automation
leon leads by 3.6 · narrow
A · leads
96.2
17,690 stars · MIT
B
92.6
23,434 stars · AGPL-3.0
leon versus skyvern is a Workflow Automation comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. leon is written mainly in TypeScript; skyvern is written mainly in Python. The composite score is 96.2 for leon and 92.6 for skyvern.
skyvern has 23,434 GitHub stars to leon's 17,690, a gap of 5,744 (1.32×). Forks are 1,484 for leon and 2,246 for skyvern. On the log scale used inside this pair, adoption is 97 versus 100, and the fork community is 95 versus 100.
Push history: leon was last pushed on 17 November 2026 (0 days ago), and skyvern was last pushed on 17 November 2026 (0 days ago). Open issues stand at 118 for leon (0.007 per star) and 301 for skyvern (0.013 per star). Issue-health scores are 84 and 84; activity scores are 100 and 100.
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. skyvern is listed as AGPL-3.0, which this catalog treats as a network copyleft grant. Letting users interact with a modified copy over a network can trigger a duty to offer them the corresponding source. License scores in this pair are 96 for leon and 52 for skyvern. This is a procurement signal, not legal advice.
In Workflow Automation, both leon (17,690 stars) and skyvern (23,434 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: leon is open source, skyvern is open source.
The lead is split. leon is furthest ahead on license flexibility (96 to 52), while skyvern is furthest ahead on fork community (100 to 95). Choose the dimension a rollout cannot compromise on.
leon finishes ahead at 96.2 against skyvern at 92.6, a 3.6 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 | leon | skyvern |
|---|---|---|
| GitHub stars | 17,690 | 23,434 |
| Forks | 1,484 | 2,246 |
| Open issues | 118 | 301 |
| Adoption | 97 | 100 |
| Activity | 100 | 100 |
| Community | 95 | 100 |
| Issue health | 84 | 84 |
| License | 96 | 52 |
| Self-hosting | 100 | 100 |
| Composite | 96.2 | 92.6 |
🧠 Leon is your open-source personal assistant.
Automate browser based workflows with AI
skyvern has more GitHub stars: 23,434 versus 17,690 for leon. The gap is 5,744 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both leon and skyvern as self-hostable. Confirm each project's deploy docs before you plan a migration.
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. skyvern is listed as AGPL-3.0, which this catalog treats as a network copyleft grant. Letting users interact with a modified copy over a network can trigger a duty to offer them the corresponding source. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
leon scores 96.2 and skyvern scores 92.6. This page calls that a narrow lead for leon.