A · leads
ai-engineering-from-scratch
97.8
79,233 stars · MIT
AI Agents
ai-engineering-from-scratch leads by 3.9 · narrow
A · leads
97.8
79,233 stars · MIT
B
93.9
127,431 stars · MIT
ai-engineering-from-scratch versus orca 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; orca is written mainly in TypeScript. The composite score is 97.8 for ai-engineering-from-scratch and 93.9 for orca.
orca has 127,431 GitHub stars to ai-engineering-from-scratch's 79,233, a gap of 48,198 (1.61×). Forks are 14,142 for ai-engineering-from-scratch and 8,082 for orca. On the log scale used inside this pair, adoption is 96 versus 100, and the fork community is 100 versus 94.
Push history: ai-engineering-from-scratch was last pushed on 17 November 2026 (0 days ago), and orca was last pushed on 17 November 2026 (0 days ago). Open issues stand at 68 for ai-engineering-from-scratch (0.001 per star) and 8,552 for orca (0.067 per star). Issue-health scores are 96 and 52; activity scores are 100 and 100.
Both ai-engineering-from-scratch and orca 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 orca (127,431 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, orca is open source.
The lead is split. ai-engineering-from-scratch is furthest ahead on issue health (96 to 52), while orca is furthest ahead on adoption (100 to 96). Choose the dimension a rollout cannot compromise on.
ai-engineering-from-scratch finishes ahead at 97.8 against orca at 93.9, a 3.9 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 | ai-engineering-from-scratch | orca |
|---|---|---|
| GitHub stars | 79,233 | 127,431 |
| Forks | 14,142 | 8,082 |
| Open issues | 68 | 8,552 |
| Adoption | 96 | 100 |
| Activity | 100 | 100 |
| Community | 100 | 94 |
| Issue health | 96 | 52 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.8 | 93.9 |
Learn AI Engineering! Learn it. Build it. Ship it for others.
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
orca has more GitHub stars: 127,431 versus 79,233 for ai-engineering-from-scratch. The gap is 48,198 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both ai-engineering-from-scratch and orca 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. orca 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 97.8 and orca scores 93.9. This page calls that a narrow lead for ai-engineering-from-scratch.