A
agent-desktop
96.0
24,948 stars · Apache-2.0
Workflow Automation
sim leads by 1.9 · narrow
A
96.0
24,948 stars · Apache-2.0
B · leads
97.9
30,151 stars · Apache-2.0
agent-desktop versus sim 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; sim is written mainly in TypeScript. The composite score is 96.0 for agent-desktop and 97.9 for sim.
sim has 30,151 GitHub stars to agent-desktop's 24,948, a gap of 5,203 (1.21×). Forks are 1,864 for agent-desktop and 3,915 for sim. On the log scale used inside this pair, adoption is 98 versus 100, and the fork community is 91 versus 100.
Push history: agent-desktop was last pushed on 17 November 2026 (0 days ago), and sim was last pushed on 17 November 2026 (0 days ago). Open issues stand at 260 for agent-desktop (0.010 per star) and 330 for sim (0.011 per star). Issue-health scores are 84 and 84; activity scores are 100 and 100.
Both agent-desktop and sim are listed as Apache-2.0. 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. The license score is therefore level at 96 versus 96, and the decision moves to adoption, activity, and hosting. This is a procurement signal, not legal advice.
In Workflow Automation, both agent-desktop (24,948 stars) and sim (30,151 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, sim is open source.
sim 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 9 points (91 vs 100), and the tightest is self-hosting at 0 points (100 vs 100).
sim finishes ahead at 97.9 against agent-desktop at 96.0, a 1.9 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 | sim |
|---|---|---|
| GitHub stars | 24,948 | 30,151 |
| Forks | 1,864 | 3,915 |
| Open issues | 260 | 330 |
| Adoption | 98 | 100 |
| Activity | 100 | 100 |
| Community | 91 | 100 |
| Issue health | 84 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 96.0 | 97.9 |
Computer use CLI for AI agents
Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.
sim has more GitHub stars: 30,151 versus 24,948 for agent-desktop. The gap is 5,203 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both agent-desktop and sim 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. sim 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. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
sim scores 97.9 and agent-desktop scores 96.0. This page calls that a narrow lead for sim.