A · leads
Dify
97.9
161,357 stars · Apache-2.0
AI Agents
Dify leads by 7.5 · clear
A · leads
97.9
161,357 stars · Apache-2.0
B
90.4
51,539 stars · Apache-2.0
Dify versus herdr is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. Dify is written mainly in Python; herdr is written mainly in Rust. The composite score is 97.9 for Dify and 90.4 for herdr.
Dify has 161,357 GitHub stars to herdr's 51,539, a gap of 109,818 (3.13×). Forks are 25,515 for Dify and 4,169 for herdr. On the log scale used inside this pair, adoption is 100 versus 90, and the fork community is 100 versus 82.
Push history: Dify was last pushed on 17 November 2026 (0 days ago), and herdr was last pushed on 07 November 2026 (10 days ago). Open issues stand at 1,422 for Dify (0.009 per star) and 513 for herdr (0.010 per star). Issue-health scores are 84 and 84; activity scores are 100 and 92.
Both Dify and herdr are listed as Apache-2.0. 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 Dify (161,357 stars) and herdr (51,539 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: Dify is open source, herdr is open source.
Dify is ahead on every scored dimension that is not level. Level dimensions: issue health, license flexibility, self-hosting. The widest gap is fork community at 18 points (100 vs 82), and the tightest is self-hosting at 0 points (100 vs 100).
Dify finishes ahead at 97.9 against herdr at 90.4, a 7.5 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 | Dify | herdr |
|---|---|---|
| GitHub stars | 161,357 | 51,539 |
| Forks | 25,515 | 4,169 |
| Open issues | 1,422 | 513 |
| Adoption | 100 | 90 |
| Activity | 100 | 92 |
| Community | 100 | 82 |
| Issue health | 84 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.9 | 90.4 |
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.
the runtime your coding agents live on
Dify has more GitHub stars: 161,357 versus 51,539 for herdr. The gap is 109,818 stars.
Dify was pushed more recently: 17 November 2026 versus 07 November 2026 for herdr. That is 10 days apart.
Yes. This catalog marks both Dify and herdr as self-hostable. Confirm each project's deploy docs before you plan a migration.
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. herdr 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 herdr scores 90.4. This page calls that a clear lead for Dify.