A · leads
deepseek-harness
97.4
282,805 stars · MIT
AI Agents
deepseek-harness leads by 29.1 · decisive
A · leads
97.4
282,805 stars · MIT
B
68.3
15,923 stars · MIT
deepseek-harness versus plandex 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; plandex is written mainly in Go. The composite score is 97.4 for deepseek-harness and 68.3 for plandex.
deepseek-harness has 282,805 GitHub stars to plandex's 15,923, a gap of 266,882 (17.76×). Forks are 35,041 for deepseek-harness and 1,192 for plandex. On the log scale used inside this pair, adoption is 100 versus 77, and the fork community is 100 versus 68.
Push history: deepseek-harness was last pushed on 13 November 2026 (4 days ago), and plandex was last pushed on 03 October 2025 (409 days ago). Open issues stand at 0 for deepseek-harness (0.000 per star) and 71 for plandex (0.004 per star). Issue-health scores are 96 and 96; activity scores are 92 and 16.
Both deepseek-harness and plandex 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 plandex (15,923 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, plandex is open source.
deepseek-harness is ahead on every scored dimension that is not level. Level dimensions: issue health, license flexibility, self-hosting. The widest gap is recent activity at 76 points (92 vs 16), and the tightest is self-hosting at 0 points (100 vs 100).
deepseek-harness finishes ahead at 97.4 against plandex at 68.3, a 29.1 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 | plandex |
|---|---|---|
| GitHub stars | 282,805 | 15,923 |
| Forks | 35,041 | 1,192 |
| Open issues | 0 | 71 |
| Adoption | 100 | 77 |
| Activity | 92 | 16 |
| Community | 100 | 68 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.4 | 68.3 |
DeepSeek Harness: Everything is a Plugin.
Open source AI coding agent. Designed for large projects and real world tasks.
deepseek-harness has more GitHub stars: 282,805 versus 15,923 for plandex. The gap is 266,882 stars.
deepseek-harness was pushed more recently: 13 November 2026 versus 03 October 2025 for plandex. That is 405 days apart.
Yes. This catalog marks both deepseek-harness and plandex 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. plandex 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 plandex scores 68.3. This page calls that a decisive lead for deepseek-harness.