A · leads
deepseek-harness
97.4
282,805 stars · MIT
AI Agents
deepseek-harness leads by 5.4 · narrow
A · leads
97.4
282,805 stars · MIT
B
92.0
78,327 stars · MIT
deepseek-harness versus dsh-our-free-model 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; dsh-our-free-model is written mainly in JavaScript. The composite score is 97.4 for deepseek-harness and 92.0 for dsh-our-free-model.
deepseek-harness has 282,805 GitHub stars to dsh-our-free-model's 78,327, a gap of 204,478 (3.61×). Forks are 35,041 for deepseek-harness and 2,206 for dsh-our-free-model. On the log scale used inside this pair, adoption is 100 versus 90, and the fork community is 100 versus 74.
Push history: deepseek-harness was last pushed on 13 November 2026 (4 days ago), and dsh-our-free-model was last pushed on 17 November 2026 (0 days ago). Open issues stand at 0 for deepseek-harness (0.000 per star) and 200 for dsh-our-free-model (0.003 per star). Issue-health scores are 96 and 96; activity scores are 92 and 100.
Both deepseek-harness and dsh-our-free-model 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 deepseek-harness (282,805 stars) and dsh-our-free-model (78,327 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, dsh-our-free-model is open source.
The lead is split. deepseek-harness is furthest ahead on fork community (100 to 74), while dsh-our-free-model is furthest ahead on recent activity (100 to 92). Choose the dimension a rollout cannot compromise on.
deepseek-harness finishes ahead at 97.4 against dsh-our-free-model at 92.0, a 5.4 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 | deepseek-harness | dsh-our-free-model |
|---|---|---|
| GitHub stars | 282,805 | 78,327 |
| Forks | 35,041 | 2,206 |
| Open issues | 0 | 200 |
| Adoption | 100 | 90 |
| Activity | 92 | 100 |
| Community | 100 | 74 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.4 | 92.0 |
DeepSeek Harness: Everything is a Plugin.
在 dsh 里装上这个插件即可,无需登录、注册或填 API Key,就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费,不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, DeepSeek V4.1 Flash and Kimi K3 among them. Completely free, with no usage cap.
deepseek-harness has more GitHub stars: 282,805 versus 78,327 for dsh-our-free-model. The gap is 204,478 stars.
dsh-our-free-model was pushed more recently: 17 November 2026 versus 13 November 2026 for deepseek-harness. That is 4 days apart.
Yes. This catalog marks both deepseek-harness and dsh-our-free-model 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. dsh-our-free-model 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.
deepseek-harness scores 97.4 and dsh-our-free-model scores 92.0. This page calls that a narrow lead for deepseek-harness.