A · leads
ai-engineering-from-scratch
99.0
79,233 stars · MIT
AI Agents
ai-engineering-from-scratch leads by 1.6 · narrow
A · leads
99.0
79,233 stars · MIT
B
97.4
81,931 stars · MIT
ai-engineering-from-scratch versus ruflo 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; ruflo is written mainly in TypeScript. The composite score is 99.0 for ai-engineering-from-scratch and 97.4 for ruflo.
ruflo has 81,931 GitHub stars to ai-engineering-from-scratch's 79,233, a gap of 2,698 (1.03×). Forks are 14,142 for ai-engineering-from-scratch and 9,668 for ruflo. On the log scale used inside this pair, adoption is 100 versus 100, and the fork community is 100 versus 96.
Push history: ai-engineering-from-scratch was last pushed on 17 November 2026 (0 days ago), and ruflo 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 614 for ruflo (0.007 per star). Issue-health scores are 96 and 84; activity scores are 100 and 100.
Both ai-engineering-from-scratch and ruflo 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 ruflo (81,931 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, ruflo is open source.
The lead is split. ai-engineering-from-scratch is furthest ahead on issue health (96 to 84), while ruflo is furthest ahead on adoption (100 to 100). Choose the dimension a rollout cannot compromise on.
ai-engineering-from-scratch finishes ahead at 99.0 against ruflo at 97.4, a 1.6 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 | ai-engineering-from-scratch | ruflo |
|---|---|---|
| GitHub stars | 79,233 | 81,931 |
| Forks | 14,142 | 9,668 |
| Open issues | 68 | 614 |
| Adoption | 100 | 100 |
| Activity | 100 | 100 |
| Community | 100 | 96 |
| Issue health | 96 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 99.0 | 97.4 |
Learn AI Engineering! Learn it. Build it. Ship it for others.
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
ruflo has more GitHub stars: 81,931 versus 79,233 for ai-engineering-from-scratch. The gap is 2,698 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both ai-engineering-from-scratch and ruflo 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. ruflo 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 99.0 and ruflo scores 97.4. This page calls that a narrow lead for ai-engineering-from-scratch.