Açık kaynak radarı

Havuz

Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.

repo · sayfa 1 / 1

Sırala

Yıldız/gün (hız)Son gün (★/gün)Son hafta (★/gün)Son ay (★/gün)Toplam yıldız AI önem skoru Bana uyum Commit (28g)Yazar (28g)En yeni

Konu

Tümü AI / LLM18 Veri9 Geliştirici araçları13 Diğer3 SaaS altyapı13 Web11

AI / LLM

Tümü ai-agents 5.829 llm 4.974 mcp 4.437 claude 2.860 anthropic 1.310 openai 1.009 rag 872 agents 813 prompt-engineering 807 image-generation 712 generative-ai 402 knowledge-graph 387 text-to-speech 301 semantic-search 216 speech-recognition 176 embeddings 155 vector-search 139 llmops 111

Süz

Yalnız hareketli Yalnız analizli≥ 0 ≥ 100 ≥ 500 ≥ 2.000

Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.

EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster

Sırala:

Etiketler yükleniyor…

Aktif jailbreak

1
lalipa2003-arch/JailbreakHub 239
A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.
5,7/gün ort. +17 son gün 112 commit 1 yazar Roff 27 Eyl 2026 güncellendi bugün
adversarial-attacks ai ai-agent ai-agents ai-jailbreak ai-jailbreak-2026 ai-jailbreak-collection ai-jailbreak-prompts
239
2
e2sy/jailbreak-archives 92
A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-tea
2,4/gün ort. +2 son gün 14 commit 1 yazar Roff 30 Eyl 2026 güncellendi dün
adversarial-prompts ai-red-team ai-safety chatbot chatgpt claude cybersecurity deepseek
92
3
Sekolah76/syadagentic 101
Universal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk
1,3/gün ort. +0 son gün — commit Python 24 Ağu 2026 güncellendi 26 Ağu 2026
agent-framework ai-agent automation bot-automation captcha jailbreak llm pentest
101
4
xxy0722/dsh-purge-deep 15
DeepSeek Harness 破甲深度分支：首尾夹击 + 生成层熔断 + 宿主源码级补丁。基于 YuJunZhiXue/dsh-purge (MIT) 改造，适配 dsh 桌面版 0.2.1-rc.3。仅供学习研究与红队评测。
1,2/gün ort. +0 son gün — commit JavaScript 26 Eki 2026 güncellendi 7 gün önce
ai-agent deepseek deepseek-harness dsh dsh-plugin electron jailbreak llm
15
5
rumoii/dsh-breaklimit 23
为 DeepSeek Harness 设计的破限插件：卸掉宿主的提示词限制和审批拦截，让助手照你说的做，不半路拒绝、不反复请示。补丁逐条可选，随时还原原版。 A jailbreak plugin for DeepSeek Harness: it strips the host's
1,1/gün ort. +1 son gün — commit JavaScript 18 Eki 2026 güncellendi 14 gün önce
ai-agents coding-agent deepseek deepseek-harness jailbreak llm plugin prompt-engineering
23
6
motan1337/universal-bypass-for-claude-chatgpt-qwen-deepseek-llm-claude-code-codex 25
Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus
1/gün ort. +1 son gün — commit 13 Eki 2026 güncellendi 11 gün önce
ai bypassing claude claude-ai claude-code claude-code-plugin claude-code-skills claude-skills
25
7
SantanderAI/autoguardrails 129
Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
0,9/gün ort. +0 son gün 0 commit 0 yazar Python 15 Haz 2026 güncellendi 01 Eki 2026
ai ai-safety alignment autoresearch benchmark content-moderation evaluation guardrails
129
8
wudidianzishu/dsh-purge-preset 15
DeepSeek Harness 官方通道破甲预设 · complete:true 整段替换 · 自带工具说明书 · 不改宿主 · 升级不丢
0,8/gün ort. +0 son gün — commit JavaScript 20 Eki 2026 güncellendi 18 gün önce
agent-preset ai-agent cordis deepseek deepseek-harness dsh jailbreak llm
15
9
giienew/exsala-hermes-mod 14
EXSALA HERMES MOD - streamlined execution profile + skill pack for Hermes Agent
0,8/gün ort. +1 son gün — commit Python 21 Eki 2026 güncellendi 4 gün önce
ai-agent automation github hermes hermes-agent jailbreak jailbreaks llm
14
10
francordel/myrtia 37
Myrtia — agent-native red teaming for LLMs and AI agents: a deliberating council of attacker models (propose, cross-critique, Borda vote, ch
0,8/gün ort. +1 son gün — commit Python 21 Eyl 2026 güncellendi 13 gün önce
adversarial-attacks adversarial-machine-learning agentic-ai ai-red-teaming ai-safety ai-security ares harmbench
37
11
xiaoliu07-sudo/xiaoliu-pojia 65
小liu破甲 - Codex CLI jailbreak prompt and one-click deploy tool. 基于CTF框架的Codex破甲提示词与一键部署工具
0,7/gün ort. +0 son gün 0 commit 0 yazar Python 31 Tem 2026 güncellendi 04 Ağu 2026
ai-security codex jailbreak llm prompt-engineering security-research security-research-tool security-researchers
65
12
keirsalterego/jailbreak-fable 44
High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.
0,3/gün ort. +0 son gün — commit JavaScript 12 Haz 2026 güncellendi 17 Tem 2026
adversarial-machine-learning ai-safety anthropic claude cybersecurity fable-5 jailbreak llm
44
13
matheofernandes27-lang/Dark-gpt-v1-free 17
Dark-GPT: The ultimate unrestricted AI assistant for cybersecurity research by M4TH4CK3R
0,3/gün ort. +0 son gün — commit TypeScript 09 Eyl 2026 güncellendi 20 Eyl 2026
chatbot cybersecurity cybersecurity-projects cybersecurity-tools free hack hacking ia
17
14
x-zheng16/System-Prompt-Open 45
Open database of system prompts extracted from frontier LLMs using JustAsk
0,2/gün ort. +0 son gün — commit HTML 31 Mar 2026 güncellendi 04 Nis 2026
ai-safety autoresearch claude-code jailbreak llm llm-security prompt-extraction red-teaming
45