A · level
agent-desktop
97.1
24,948 stars · Apache-2.0
Workflow Automation
Too close to call · 97.1 to 96.9
A · level
97.1
24,948 stars · Apache-2.0
B · level
96.9
32,478 stars · Apache-2.0
agent-desktop versus conductor 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; conductor is written mainly in Java. The composite score is 97.1 for agent-desktop and 96.9 for conductor.
conductor has 32,478 GitHub stars to agent-desktop's 24,948, a gap of 7,530 (1.30×). Forks are 1,864 for agent-desktop and 1,074 for conductor. On the log scale used inside this pair, adoption is 98 versus 100, and the fork community is 100 versus 93.
Push history: agent-desktop was last pushed on 17 November 2026 (0 days ago), and conductor was last pushed on 17 November 2026 (0 days ago). Open issues stand at 260 for agent-desktop (0.010 per star) and 300 for conductor (0.009 per star). Issue-health scores are 84 and 84; activity scores are 100 and 100.
Both agent-desktop and conductor 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 conductor (32,478 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, conductor is open source.
The lead is split. agent-desktop is furthest ahead on fork community (100 to 93), while conductor is furthest ahead on adoption (100 to 98). Choose the dimension a rollout cannot compromise on.
Composite score: agent-desktop 97.1, conductor 96.9. 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 | conductor |
|---|---|---|
| GitHub stars | 24,948 | 32,478 |
| Forks | 1,864 | 1,074 |
| Open issues | 260 | 300 |
| Adoption | 98 | 100 |
| Activity | 100 | 100 |
| Community | 100 | 93 |
| Issue health | 84 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.1 | 96.9 |
Computer use CLI for AI agents
Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents
conductor has more GitHub stars: 32,478 versus 24,948 for agent-desktop. The gap is 7,530 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both agent-desktop and conductor 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. conductor 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.
Neither tool clears a one-point margin. agent-desktop scores 97.1 and conductor scores 96.9.