A · leads
ai-engineering-from-scratch
99.1
79,233 stars · MIT
AI Agents
ai-engineering-from-scratch leads by 2.5 · narrow
A · leads
99.1
79,233 stars · MIT
B
96.6
68,366 stars · MIT
ai-engineering-from-scratch versus anything-llm 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; anything-llm is written mainly in JavaScript. The composite score is 99.1 for ai-engineering-from-scratch and 96.6 for anything-llm.
ai-engineering-from-scratch has 79,233 GitHub stars to anything-llm's 68,366, a gap of 10,867 (1.16×). Forks are 14,142 for ai-engineering-from-scratch and 7,723 for anything-llm. On the log scale used inside this pair, adoption is 100 versus 99, 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 anything-llm 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 358 for anything-llm (0.005 per star). Issue-health scores are 96 and 84; activity scores are 100 and 100.
Both ai-engineering-from-scratch and anything-llm 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 anything-llm (68,366 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, anything-llm is open source.
ai-engineering-from-scratch is ahead on every scored dimension that is not level. Level dimensions: recent activity, license flexibility, self-hosting. The widest gap is issue health at 12 points (96 vs 84), and the tightest is self-hosting at 0 points (100 vs 100).
ai-engineering-from-scratch finishes ahead at 99.1 against anything-llm at 96.6, a 2.5 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 | anything-llm |
|---|---|---|
| GitHub stars | 79,233 | 68,366 |
| Forks | 14,142 | 7,723 |
| Open issues | 68 | 358 |
| Adoption | 100 | 99 |
| Activity | 100 | 100 |
| Community | 100 | 94 |
| Issue health | 96 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 99.1 | 96.6 |
Learn AI Engineering! Learn it. Build it. Ship it for others.
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
ai-engineering-from-scratch has more GitHub stars: 79,233 versus 68,366 for anything-llm. The gap is 10,867 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both ai-engineering-from-scratch and anything-llm 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. anything-llm 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 99.1 and anything-llm scores 96.6. This page calls that a narrow lead for ai-engineering-from-scratch.