A
agent-desktop
93.3
24,948 stars · Apache-2.0
Workflow Automation
nanobot leads by 4.6 · narrow
A
93.3
24,948 stars · Apache-2.0
B · leads
97.9
50,147 stars · MIT
agent-desktop versus nanobot 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; nanobot is written mainly in Python. The composite score is 93.3 for agent-desktop and 97.9 for nanobot.
nanobot has 50,147 GitHub stars to agent-desktop's 24,948, a gap of 25,199 (2.01×). Forks are 1,864 for agent-desktop and 8,755 for nanobot. On the log scale used inside this pair, adoption is 94 versus 100, and the fork community is 83 versus 100.
Push history: agent-desktop was last pushed on 17 November 2026 (0 days ago), and nanobot was last pushed on 17 November 2026 (0 days ago). Open issues stand at 260 for agent-desktop (0.010 per star) and 872 for nanobot (0.017 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. nanobot 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 nanobot. This is a procurement signal, not legal advice.
In Workflow Automation, both agent-desktop (24,948 stars) and nanobot (50,147 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, nanobot is open source.
nanobot 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 17 points (83 vs 100), and the tightest is self-hosting at 0 points (100 vs 100).
nanobot finishes ahead at 97.9 against agent-desktop at 93.3, a 4.6 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 | nanobot |
|---|---|---|
| GitHub stars | 24,948 | 50,147 |
| Forks | 1,864 | 8,755 |
| Open issues | 260 | 872 |
| Adoption | 94 | 100 |
| Activity | 100 | 100 |
| Community | 83 | 100 |
| Issue health | 84 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 93.3 | 97.9 |
Computer use CLI for AI agents
Your lightweight open-source personal agent.
nanobot has more GitHub stars: 50,147 versus 24,948 for agent-desktop. The gap is 25,199 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both agent-desktop and nanobot 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. nanobot 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.
nanobot scores 97.9 and agent-desktop scores 93.3. This page calls that a narrow lead for nanobot.