A · leads
deepseek-harness
97.4
282,805 stars · MIT
AI Agents
deepseek-harness leads by 24.6 · decisive
A · leads
97.4
282,805 stars · MIT
B
72.8
18,258 stars · Apache-2.0
deepseek-harness versus openfang is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. deepseek-harness is written mainly in TypeScript; openfang is written mainly in Rust. The composite score is 97.4 for deepseek-harness and 72.8 for openfang.
deepseek-harness has 282,805 GitHub stars to openfang's 18,258, a gap of 264,547 (15.49×). Forks are 35,041 for deepseek-harness and 2,283 for openfang. On the log scale used inside this pair, adoption is 100 versus 78, and the fork community is 100 versus 74.
Push history: deepseek-harness was last pushed on 13 November 2026 (4 days ago), and openfang was last pushed on 02 July 2026 (138 days ago). Open issues stand at 0 for deepseek-harness (0.000 per star) and 136 for openfang (0.007 per star). Issue-health scores are 96 and 84; activity scores are 92 and 36.
deepseek-harness 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. openfang 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 deepseek-harness and 96 for openfang. This is a procurement signal, not legal advice.
In AI Agents, both deepseek-harness (282,805 stars) and openfang (18,258 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: deepseek-harness is open source, openfang is open source.
deepseek-harness is ahead on every scored dimension that is not level. Level dimensions: license flexibility, self-hosting. The widest gap is recent activity at 56 points (92 vs 36), and the tightest is self-hosting at 0 points (100 vs 100).
deepseek-harness finishes ahead at 97.4 against openfang at 72.8, a 24.6 point decisive 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 | deepseek-harness | openfang |
|---|---|---|
| GitHub stars | 282,805 | 18,258 |
| Forks | 35,041 | 2,283 |
| Open issues | 0 | 136 |
| Adoption | 100 | 78 |
| Activity | 92 | 36 |
| Community | 100 | 74 |
| Issue health | 96 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.4 | 72.8 |
DeepSeek Harness: Everything is a Plugin.
Open-source Agent Operating System
deepseek-harness has more GitHub stars: 282,805 versus 18,258 for openfang. The gap is 264,547 stars.
deepseek-harness was pushed more recently: 13 November 2026 versus 02 July 2026 for openfang. That is 134 days apart.
Yes. This catalog marks both deepseek-harness and openfang as self-hostable. Confirm each project's deploy docs before you plan a migration.
deepseek-harness 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. openfang 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.
deepseek-harness scores 97.4 and openfang scores 72.8. This page calls that a decisive lead for deepseek-harness.