YuJunZhiXue/dsh-purge
DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐ 如要二开，请查看署名要求部分
16.7k
Stars
3.9k
Forks
77.7
Radar Score
Momentum
Scoring Breakdown
Impact92.5
Velocity74.8
Health58.0
Growth Metrics
7-Day Stars
+7.1k
30-Day Stars
+12.4k
Acceleration
1.79x
Language
JavaScript
Why it ranks
Exceptional momentum — gaining stars far faster than almost everything else tracked.
Trend signal: Rapidly gaining stars — 7079 new stars in the last 7 days (1.8x the usual pace). Above-average growth velocity. High developer adoption with 2055 new forks this week. Active in the AI Safety & Alignment category.
Popular Alternatives & Competitors
Top projects in the same category (AI Safety & Alignment) — compare side by side.
🛡️ Enterprise Readiness & Commercial Safety
Organic Growth
77%
Moderate Confidence
License
Permissive (Commercial Friendly)
Safe for commercial use, modification, and distribution.
Health Grade
A
Based on maintenance, issue response, and release cadence.
Radar Score
77.7
Composite of Impact, Velocity, and Health.
⚠️ Growth Anomaly Detected:
- Issue engagement: 8 open issues for 16,705 stars (0.0%).
Disclaimer: This is an automated heuristic assessment based on public GitHub signals. Always perform your own security audit, dependency review, and legal compliance check before production deployment.
Share & Embed
Display live Radar metrics in your documentation, website, or social profiles.