A
agency-agents-zh
89.2
22,145 stars · MIT
AI Agents
deepseek-harness leads by 8.2 · clear
A
89.2
22,145 stars · MIT
B · leads
97.4
282,805 stars · MIT
agency-agents-zh versus deepseek-harness is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. agency-agents-zh is written mainly in Shell; deepseek-harness is written mainly in TypeScript. The composite score is 89.2 for agency-agents-zh and 97.4 for deepseek-harness.
deepseek-harness has 282,805 GitHub stars to agency-agents-zh's 22,145, a gap of 260,660 (12.77×). Forks are 3,555 for agency-agents-zh and 35,041 for deepseek-harness. On the log scale used inside this pair, adoption is 80 versus 100, and the fork community is 78 versus 100.
Push history: agency-agents-zh was last pushed on 14 November 2026 (3 days ago), and deepseek-harness was last pushed on 13 November 2026 (4 days ago). Open issues stand at 2 for agency-agents-zh (0.000 per star) and 0 for deepseek-harness (0.000 per star). Issue-health scores are 96 and 96; activity scores are 100 and 92.
Both agency-agents-zh and deepseek-harness 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 agency-agents-zh (22,145 stars) and deepseek-harness (282,805 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: agency-agents-zh is open source, deepseek-harness is open source.
The lead is split. agency-agents-zh is furthest ahead on recent activity (100 to 92), while deepseek-harness is furthest ahead on fork community (100 to 78). Choose the dimension a rollout cannot compromise on.
deepseek-harness finishes ahead at 97.4 against agency-agents-zh at 89.2, a 8.2 point clear 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 | agency-agents-zh | deepseek-harness |
|---|---|---|
| GitHub stars | 22,145 | 282,805 |
| Forks | 3,555 | 35,041 |
| Open issues | 2 | 0 |
| Adoption | 80 | 100 |
| Activity | 100 | 92 |
| Community | 78 | 100 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 89.2 | 97.4 |
🎭 277 个即插即用的 AI 专家角色 — 支持 Claude Code/Cursor/Copilot 等 20 种工具,覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体(小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计)。搭配编排器 agency-orchestrator,一句话即可让多位专家按 DAG 自动协作。
DeepSeek Harness: Everything is a Plugin.
deepseek-harness has more GitHub stars: 282,805 versus 22,145 for agency-agents-zh. The gap is 260,660 stars.
agency-agents-zh was pushed more recently: 14 November 2026 versus 13 November 2026 for deepseek-harness. That is 1 days apart.
Yes. This catalog marks both agency-agents-zh and deepseek-harness as self-hostable. Confirm each project's deploy docs before you plan a migration.
agency-agents-zh 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. 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. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
deepseek-harness scores 97.4 and agency-agents-zh scores 89.2. This page calls that a clear lead for deepseek-harness.