A · leads
deer-flow
97.9
85,441 stars · MIT
AI Agents
deer-flow leads by 13.5 · clear
A · leads
97.9
85,441 stars · MIT
B
84.4
80,149 stars · MIT
deer-flow versus Prompt-Engineering-Guide is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. deer-flow is written mainly in Python; Prompt-Engineering-Guide is written mainly in MDX. The composite score is 97.9 for deer-flow and 84.4 for Prompt-Engineering-Guide.
deer-flow has 85,441 GitHub stars to Prompt-Engineering-Guide's 80,149, a gap of 5,292 (1.07×). Forks are 12,046 for deer-flow and 8,790 for Prompt-Engineering-Guide. On the log scale used inside this pair, adoption is 100 versus 99, and the fork community is 100 versus 97.
Push history: deer-flow was last pushed on 17 November 2026 (0 days ago), and Prompt-Engineering-Guide was last pushed on 11 March 2026 (250 days ago). Open issues stand at 1,117 for deer-flow (0.013 per star) and 300 for Prompt-Engineering-Guide (0.004 per star). Issue-health scores are 84 and 96; activity scores are 100 and 36.
Both deer-flow and Prompt-Engineering-Guide 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 deer-flow (85,441 stars) and Prompt-Engineering-Guide (80,149 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: deer-flow is open source, Prompt-Engineering-Guide is open source.
The lead is split. deer-flow is furthest ahead on recent activity (100 to 36), while Prompt-Engineering-Guide is furthest ahead on issue health (96 to 84). Choose the dimension a rollout cannot compromise on.
deer-flow finishes ahead at 97.9 against Prompt-Engineering-Guide at 84.4, a 13.5 point clear 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 | deer-flow | Prompt-Engineering-Guide |
|---|---|---|
| GitHub stars | 85,441 | 80,149 |
| Forks | 12,046 | 8,790 |
| Open issues | 1,117 | 300 |
| Adoption | 100 | 99 |
| Activity | 100 | 36 |
| Community | 100 | 97 |
| Issue health | 84 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.9 | 84.4 |
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.
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
deer-flow has more GitHub stars: 85,441 versus 80,149 for Prompt-Engineering-Guide. The gap is 5,292 stars.
deer-flow was pushed more recently: 17 November 2026 versus 11 March 2026 for Prompt-Engineering-Guide. That is 250 days apart.
Yes. This catalog marks both deer-flow and Prompt-Engineering-Guide as self-hostable. Confirm each project's deploy docs before you plan a migration.
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. Prompt-Engineering-Guide 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.
deer-flow scores 97.9 and Prompt-Engineering-Guide scores 84.4. This page calls that a clear lead for deer-flow.