A
dsh-our-free-model
95.9
78,327 stars · MIT
AI Agents
taste-skill leads by 1.5 · narrow
A
95.9
78,327 stars · MIT
B · leads
97.4
117,459 stars · MIT
dsh-our-free-model versus taste-skill 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 JavaScript. The composite score is 95.9 for dsh-our-free-model and 97.4 for taste-skill.
taste-skill has 117,459 GitHub stars to dsh-our-free-model's 78,327, a gap of 39,132 (1.50×). Forks are 2,206 for dsh-our-free-model and 7,858 for taste-skill. On the log scale used inside this pair, adoption is 96 versus 100, and the fork community is 86 versus 100.
Push history: dsh-our-free-model was last pushed on 17 November 2026 (0 days ago), and taste-skill was last pushed on 08 November 2026 (8 days ago). Open issues stand at 200 for dsh-our-free-model (0.003 per star) and 10 for taste-skill (0.000 per star). Issue-health scores are 96 and 96; activity scores are 100 and 92.
Both dsh-our-free-model and taste-skill 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 dsh-our-free-model (78,327 stars) and taste-skill (117,459 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: dsh-our-free-model is open source, taste-skill is open source.
The lead is split. dsh-our-free-model is furthest ahead on recent activity (100 to 92), while taste-skill is furthest ahead on fork community (100 to 86). Choose the dimension a rollout cannot compromise on.
taste-skill finishes ahead at 97.4 against dsh-our-free-model at 95.9, a 1.5 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 | dsh-our-free-model | taste-skill |
|---|---|---|
| GitHub stars | 78,327 | 117,459 |
| Forks | 2,206 | 7,858 |
| Open issues | 200 | 10 |
| Adoption | 96 | 100 |
| Activity | 100 | 92 |
| Community | 86 | 100 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 95.9 | 97.4 |
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.
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
taste-skill has more GitHub stars: 117,459 versus 78,327 for dsh-our-free-model. The gap is 39,132 stars.
dsh-our-free-model was pushed more recently: 17 November 2026 versus 08 November 2026 for taste-skill. That is 8 days apart.
Yes. This catalog marks both dsh-our-free-model and taste-skill as self-hostable. Confirm each project's deploy docs before you plan a migration.
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. taste-skill 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.
taste-skill scores 97.4 and dsh-our-free-model scores 95.9. This page calls that a narrow lead for taste-skill.