A · level
deepseek-harness
97.4
282,805 stars · MIT
AI Agents
Too close to call · 97.4 to 97.0
A · level
97.4
282,805 stars · MIT
B · level
97.0
158,922 stars · MIT
deepseek-harness versus Open WebUI 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; Open WebUI is written mainly in Svelte. The composite score is 97.4 for deepseek-harness and 97.0 for Open WebUI.
deepseek-harness has 282,805 GitHub stars to Open WebUI's 158,922, a gap of 123,883 (1.78×). Forks are 35,041 for deepseek-harness and 23,097 for Open WebUI. On the log scale used inside this pair, adoption is 100 versus 95, and the fork community is 100 versus 96.
Push history: deepseek-harness was last pushed on 13 November 2026 (4 days ago), and Open WebUI was last pushed on 17 November 2026 (0 days ago). Open issues stand at 0 for deepseek-harness (0.000 per star) and 208 for Open WebUI (0.001 per star). Issue-health scores are 96 and 96; activity scores are 92 and 100.
Both deepseek-harness and Open WebUI 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 Open WebUI (158,922 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, Open WebUI is open source.
The lead is split. deepseek-harness is furthest ahead on adoption (100 to 95), while Open WebUI is furthest ahead on recent activity (100 to 92). Choose the dimension a rollout cannot compromise on.
Composite score: deepseek-harness 97.4, Open WebUI 97.0. The margin is under one point, so this page calls a tie. Use the dimension breakdown rather than the headline number.
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 | Open WebUI |
|---|---|---|
| GitHub stars | 282,805 | 158,922 |
| Forks | 35,041 | 23,097 |
| Open issues | 0 | 208 |
| Adoption | 100 | 95 |
| Activity | 92 | 100 |
| Community | 100 | 96 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.4 | 97.0 |
DeepSeek Harness: Everything is a Plugin.
Open WebUI is a self-hosted chat interface for local and remote language models, including Ollama. It adds users, documents, and tools around the model endpoint.
deepseek-harness has more GitHub stars: 282,805 versus 158,922 for Open WebUI. The gap is 123,883 stars.
Open WebUI 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 Open WebUI 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. Open WebUI 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.
Neither tool clears a one-point margin. deepseek-harness scores 97.4 and Open WebUI scores 97.0.