A · leads
nanobot
97.9
50,147 stars · MIT
Workflow Automation
nanobot leads by 22.9 · decisive
A · leads
97.9
50,147 stars · MIT
B
75.0
2,639 stars · MIT
nanobot versus shepherd is a Workflow Automation comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. Both projects are written mainly in Python. The composite score is 97.9 for nanobot and 75.0 for shepherd.
nanobot has 50,147 GitHub stars to shepherd's 2,639, a gap of 47,508 (19.00×). Forks are 8,755 for nanobot and 227 for shepherd. On the log scale used inside this pair, adoption is 100 versus 73, and the fork community is 100 versus 60.
Push history: nanobot was last pushed on 17 November 2026 (0 days ago), and shepherd was last pushed on 09 September 2026 (69 days ago). Open issues stand at 872 for nanobot (0.017 per star) and 13 for shepherd (0.005 per star). Issue-health scores are 84 and 96; activity scores are 100 and 58.
Both nanobot and shepherd are listed as MIT. 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 nanobot (50,147 stars) and shepherd (2,639 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: nanobot is open source, shepherd is open source.
The lead is split. nanobot is furthest ahead on recent activity (100 to 58), while shepherd is furthest ahead on issue health (96 to 84). Choose the dimension a rollout cannot compromise on.
nanobot finishes ahead at 97.9 against shepherd at 75.0, a 22.9 point decisive 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 | nanobot | shepherd |
|---|---|---|
| GitHub stars | 50,147 | 2,639 |
| Forks | 8,755 | 227 |
| Open issues | 872 | 13 |
| Adoption | 100 | 73 |
| Activity | 100 | 58 |
| Community | 100 | 60 |
| Issue health | 84 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.9 | 75.0 |
Your lightweight open-source personal agent.
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents
nanobot has more GitHub stars: 50,147 versus 2,639 for shepherd. The gap is 47,508 stars.
nanobot was pushed more recently: 17 November 2026 versus 09 September 2026 for shepherd. That is 69 days apart.
Yes. This catalog marks both nanobot and shepherd as self-hostable. Confirm each project's deploy docs before you plan a migration.
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. shepherd 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 shepherd scores 75.0. This page calls that a decisive lead for nanobot.