A · leads
deepseek-harness
97.4
282,805 stars · MIT
AI Agents
deepseek-harness leads by 9.6 · clear
A · leads
97.4
282,805 stars · MIT
B
87.8
71,615 stars · CC0-1.0
deepseek-harness versus system_prompts_leaks 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; system_prompts_leaks is written mainly in Python. The composite score is 97.4 for deepseek-harness and 87.8 for system_prompts_leaks.
deepseek-harness has 282,805 GitHub stars to system_prompts_leaks's 71,615, a gap of 211,190 (3.95×). Forks are 35,041 for deepseek-harness and 11,525 for system_prompts_leaks. On the log scale used inside this pair, adoption is 100 versus 89, and the fork community is 100 versus 89.
Push history: deepseek-harness was last pushed on 13 November 2026 (4 days ago), and system_prompts_leaks was last pushed on 16 November 2026 (1 day ago). Open issues stand at 0 for deepseek-harness (0.000 per star) and 26 for system_prompts_leaks (0.000 per star). Issue-health scores are 96 and 96; 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. system_prompts_leaks is listed as CC0-1.0, which this catalog treats as custom terms. A public repository is not itself permission to embed the code. License scores in this pair are 96 for deepseek-harness and 45 for system_prompts_leaks. This is a procurement signal, not legal advice.
In AI Agents, both deepseek-harness (282,805 stars) and system_prompts_leaks (71,615 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, system_prompts_leaks is open source.
The lead is split. deepseek-harness is furthest ahead on license flexibility (96 to 45), while system_prompts_leaks 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 system_prompts_leaks at 87.8, a 9.6 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 | deepseek-harness | system_prompts_leaks |
|---|---|---|
| GitHub stars | 282,805 | 71,615 |
| Forks | 35,041 | 11,525 |
| Open issues | 0 | 26 |
| Adoption | 100 | 89 |
| Activity | 92 | 100 |
| Community | 100 | 89 |
| Issue health | 96 | 96 |
| License | 96 | 45 |
| Self-hosting | 100 | 100 |
| Composite | 97.4 | 87.8 |
DeepSeek Harness: Everything is a Plugin.
Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, MiniMax, Cursor, Perplexity, DeepSeek and 30+ others. Updated daily.
deepseek-harness has more GitHub stars: 282,805 versus 71,615 for system_prompts_leaks. The gap is 211,190 stars.
system_prompts_leaks was pushed more recently: 16 November 2026 versus 13 November 2026 for deepseek-harness. That is 3 days apart.
Yes. This catalog marks both deepseek-harness and system_prompts_leaks 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. system_prompts_leaks is listed as CC0-1.0, which this catalog treats as custom terms. A public repository is not itself permission to embed the code. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
deepseek-harness scores 97.4 and system_prompts_leaks scores 87.8. This page calls that a clear lead for deepseek-harness.