A
ai-engineering-from-scratch
96.3
79,233 stars · MIT
AI Agents
Dify leads by 1.6 · narrow
A
96.3
79,233 stars · MIT
B · leads
97.9
161,357 stars · Apache-2.0
ai-engineering-from-scratch versus Dify is a AI Agents 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 96.3 for ai-engineering-from-scratch and 97.9 for Dify.
Dify has 161,357 GitHub stars to ai-engineering-from-scratch's 79,233, a gap of 82,124 (2.04×). Forks are 14,142 for ai-engineering-from-scratch and 25,515 for Dify. On the log scale used inside this pair, adoption is 94 versus 100, and the fork community is 94 versus 100.
Push history: ai-engineering-from-scratch was last pushed on 17 November 2026 (0 days ago), and Dify 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 1,422 for Dify (0.009 per star). Issue-health scores are 96 and 84; activity scores are 100 and 100.
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. Dify 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. License scores in this pair are 96 for ai-engineering-from-scratch and 96 for Dify. This is a procurement signal, not legal advice.
In AI Agents, both ai-engineering-from-scratch (79,233 stars) and Dify (161,357 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, Dify is open source.
The lead is split. ai-engineering-from-scratch is furthest ahead on issue health (96 to 84), while Dify is furthest ahead on adoption (100 to 94). Choose the dimension a rollout cannot compromise on.
Dify finishes ahead at 97.9 against ai-engineering-from-scratch at 96.3, 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 | Dify |
|---|---|---|
| GitHub stars | 79,233 | 161,357 |
| Forks | 14,142 | 25,515 |
| Open issues | 68 | 1,422 |
| Adoption | 94 | 100 |
| Activity | 100 | 100 |
| Community | 94 | 100 |
| Issue health | 96 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 96.3 | 97.9 |
Learn AI Engineering! Learn it. Build it. Ship it for others.
Dify is a platform for building LLM apps: prompts, RAG pipelines, agents, and observability. It is aimed at teams that want that stack on their own machines.
Dify has more GitHub stars: 161,357 versus 79,233 for ai-engineering-from-scratch. The gap is 82,124 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both ai-engineering-from-scratch and Dify 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. Dify 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. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
Dify scores 97.9 and ai-engineering-from-scratch scores 96.3. This page calls that a narrow lead for Dify.