A · leads
deepseek-harness
97.4
282,805 stars · MIT
AI Agents
deepseek-harness leads by 3.2 · narrow
A · leads
97.4
282,805 stars · MIT
B
94.2
108,897 stars · Apache-2.0
deepseek-harness versus gemini-cli 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 TypeScript. The composite score is 97.4 for deepseek-harness and 94.2 for gemini-cli.
deepseek-harness has 282,805 GitHub stars to gemini-cli's 108,897, a gap of 173,908 (2.60×). Forks are 35,041 for deepseek-harness and 14,956 for gemini-cli. On the log scale used inside this pair, adoption is 100 versus 92, and the fork community is 100 versus 92.
Push history: deepseek-harness was last pushed on 13 November 2026 (4 days ago), and gemini-cli was last pushed on 17 November 2026 (0 days ago). Open issues stand at 0 for deepseek-harness (0.000 per star) and 739 for gemini-cli (0.007 per star). Issue-health scores are 96 and 84; activity scores are 92 and 100.
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. gemini-cli 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 gemini-cli. This is a procurement signal, not legal advice.
In AI Agents, both deepseek-harness (282,805 stars) and gemini-cli (108,897 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, gemini-cli is open source.
The lead is split. deepseek-harness is furthest ahead on issue health (96 to 84), while gemini-cli 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 gemini-cli at 94.2, a 3.2 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 | gemini-cli |
|---|---|---|
| GitHub stars | 282,805 | 108,897 |
| Forks | 35,041 | 14,956 |
| Open issues | 0 | 739 |
| Adoption | 100 | 92 |
| Activity | 92 | 100 |
| Community | 100 | 92 |
| Issue health | 96 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.4 | 94.2 |
DeepSeek Harness: Everything is a Plugin.
An open-source AI agent that brings the power of Gemini directly into your terminal.
deepseek-harness has more GitHub stars: 282,805 versus 108,897 for gemini-cli. The gap is 173,908 stars.
gemini-cli 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 gemini-cli 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. gemini-cli 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 gemini-cli scores 94.2. This page calls that a narrow lead for deepseek-harness.