A · leads
ai-engineering-from-scratch
96.6
79,233 stars · MIT
AI Agents
ai-engineering-from-scratch leads by 2.7 · narrow
A · leads
96.6
79,233 stars · MIT
B
93.9
192,622 stars · MIT
ai-engineering-from-scratch versus ponytail is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. ai-engineering-from-scratch is written mainly in Python; ponytail is written mainly in JavaScript. The composite score is 96.6 for ai-engineering-from-scratch and 93.9 for ponytail.
ponytail has 192,622 GitHub stars to ai-engineering-from-scratch's 79,233, a gap of 113,389 (2.43×). Forks are 14,142 for ai-engineering-from-scratch and 10,810 for ponytail. On the log scale used inside this pair, adoption is 93 versus 100, and the fork community is 100 versus 97.
Push history: ai-engineering-from-scratch was last pushed on 17 November 2026 (0 days ago), and ponytail was last pushed on 29 October 2026 (19 days ago). Open issues stand at 68 for ai-engineering-from-scratch (0.001 per star) and 254 for ponytail (0.001 per star). Issue-health scores are 96 and 96; activity scores are 100 and 78.
Both ai-engineering-from-scratch and ponytail 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 AI Agents, both ai-engineering-from-scratch (79,233 stars) and ponytail (192,622 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: ai-engineering-from-scratch is open source, ponytail is open source.
The lead is split. ai-engineering-from-scratch is furthest ahead on recent activity (100 to 78), while ponytail is furthest ahead on adoption (100 to 93). Choose the dimension a rollout cannot compromise on.
ai-engineering-from-scratch finishes ahead at 96.6 against ponytail at 93.9, a 2.7 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 | ai-engineering-from-scratch | ponytail |
|---|---|---|
| GitHub stars | 79,233 | 192,622 |
| Forks | 14,142 | 10,810 |
| Open issues | 68 | 254 |
| Adoption | 93 | 100 |
| Activity | 100 | 78 |
| Community | 100 | 97 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 96.6 | 93.9 |
Learn AI Engineering! Learn it. Build it. Ship it for others.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
ponytail has more GitHub stars: 192,622 versus 79,233 for ai-engineering-from-scratch. The gap is 113,389 stars.
ai-engineering-from-scratch was pushed more recently: 17 November 2026 versus 29 October 2026 for ponytail. That is 19 days apart.
Yes. This catalog marks both ai-engineering-from-scratch and ponytail as self-hostable. Confirm each project's deploy docs before you plan a migration.
ai-engineering-from-scratch 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. ponytail 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.
ai-engineering-from-scratch scores 96.6 and ponytail scores 93.9. This page calls that a narrow lead for ai-engineering-from-scratch.