A · leads
ai-engineering-from-scratch
98.9
79,233 stars · MIT
AI Agents
ai-engineering-from-scratch leads by 1.2 · narrow
A · leads
98.9
79,233 stars · MIT
B
97.7
85,441 stars · MIT
ai-engineering-from-scratch versus deer-flow 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 98.9 for ai-engineering-from-scratch and 97.7 for deer-flow.
deer-flow has 85,441 GitHub stars to ai-engineering-from-scratch's 79,233, a gap of 6,208 (1.08×). Forks are 14,142 for ai-engineering-from-scratch and 12,046 for deer-flow. On the log scale used inside this pair, adoption is 99 versus 100, and the fork community is 100 versus 98.
Push history: ai-engineering-from-scratch was last pushed on 17 November 2026 (0 days ago), and deer-flow 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 1,117 for deer-flow (0.013 per star). Issue-health scores are 96 and 84; activity scores are 100 and 100.
Both ai-engineering-from-scratch and deer-flow 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 deer-flow (85,441 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, deer-flow is open source.
The lead is split. ai-engineering-from-scratch is furthest ahead on issue health (96 to 84), while deer-flow is furthest ahead on adoption (100 to 99). Choose the dimension a rollout cannot compromise on.
ai-engineering-from-scratch finishes ahead at 98.9 against deer-flow at 97.7, a 1.2 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 | deer-flow |
|---|---|---|
| GitHub stars | 79,233 | 85,441 |
| Forks | 14,142 | 12,046 |
| Open issues | 68 | 1,117 |
| Adoption | 99 | 100 |
| Activity | 100 | 100 |
| Community | 100 | 98 |
| Issue health | 96 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 98.9 | 97.7 |
Learn AI Engineering! Learn it. Build it. Ship it for others.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
deer-flow has more GitHub stars: 85,441 versus 79,233 for ai-engineering-from-scratch. The gap is 6,208 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both ai-engineering-from-scratch and deer-flow 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. deer-flow 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 98.9 and deer-flow scores 97.7. This page calls that a narrow lead for ai-engineering-from-scratch.