A collection of jailbreak prompts and exploit techniques for local and frontier AI models, with modern methods for Qwen3.5, Gemma 4, Llama 4, Kimi K3, GPT-OSS, GPT-5.x, Gemini 3.x and Grok 4.x. For red-teaming and AI safety research only.
Quincunx33/Ai-jailbreak has 500 GitHub stars. It gained +29 stars in the last 7 days and +90 over 13 recorded days in the last 30 days (snapshots through Oct 22, 2026).
Its biggest recent day was Oct 11, 2026, with +15 stars.
It currently ranks #46938 daily, #46907 weekly, #47373 monthly by momentum on Trending Repos; its best-ever rank is #2799.
Trending Repos first recorded it on Oct 7, 2026.
| Date | Stars gained | Total stars | Forks gained |
|---|---|---|---|
| +8 | 496 | +1 | |
| +2 | 488 | -1 | |
| +4 | 486 | 0 | |
| +3 |
| 482 |
| +1 |
| +3 | 479 | 0 |
| +5 | 476 | +1 |
| +4 | 471 | 0 |
| +7 | 467 | 0 |
| +10 | 460 | +1 |
| +7 | 450 | +2 |
| +12 | 443 | 0 |
| +15 | 431 | +2 |
| +10 | 416 | 0 |