A · leads
deepseek-harness
96.7
282,805 stars · MIT
AI Agents
deepseek-harness leads by 3.9 · narrow
A · leads
96.7
282,805 stars · MIT
B
92.8
264,096 stars · MIT
deepseek-harness versus hermes-agent 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; hermes-agent is written mainly in Python. The composite score is 96.7 for deepseek-harness and 92.8 for hermes-agent.
deepseek-harness has 282,805 GitHub stars to hermes-agent's 264,096, a gap of 18,709 (1.07×). Forks are 35,041 for deepseek-harness and 59,569 for hermes-agent. On the log scale used inside this pair, adoption is 100 versus 100, and the fork community is 95 versus 100.
Push history: deepseek-harness was last pushed on 13 November 2026 (4 days ago), and hermes-agent was last pushed on 17 November 2026 (0 days ago). Open issues stand at 0 for deepseek-harness (0.000 per star) and 53,403 for hermes-agent (0.202 per star). Issue-health scores are 96 and 34; activity scores are 92 and 100.
Both deepseek-harness and hermes-agent 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 hermes-agent (264,096 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, hermes-agent is open source.
The lead is split. deepseek-harness is furthest ahead on issue health (96 to 34), while hermes-agent is furthest ahead on recent activity (100 to 92). Choose the dimension a rollout cannot compromise on.
deepseek-harness finishes ahead at 96.7 against hermes-agent at 92.8, a 3.9 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 | hermes-agent |
|---|---|---|
| GitHub stars | 282,805 | 264,096 |
| Forks | 35,041 | 59,569 |
| Open issues | 0 | 53,403 |
| Adoption | 100 | 100 |
| Activity | 92 | 100 |
| Community | 95 | 100 |
| Issue health | 96 | 34 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 96.7 | 92.8 |
DeepSeek Harness: Everything is a Plugin.
The agent that grows with you
deepseek-harness has more GitHub stars: 282,805 versus 264,096 for hermes-agent. The gap is 18,709 stars.
hermes-agent 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 hermes-agent 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. hermes-agent 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 96.7 and hermes-agent scores 92.8. This page calls that a narrow lead for deepseek-harness.