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

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 prompt-injection

1
buryusu/All-AI-Jailbreaks 98
Curated archive of jailbreak and prompt-injection experiments for AI model robustness research, red-teaming, and defensive evaluation.
1,2/gün ort. +2 son gün 0 commit 0 yazar Batchfile 18 Ağu 2026 güncellendi 09 Eyl 2026
adversarial-prompts ai-robustness ai-safety jailbreak-research llm-security model-evaluation prompt-engineering prompt-injection
98
2
chaomazo-OCR/OCRgenius 16
Document extraction and validation for logistics companies.
0,2/gün ort. +0 son gün — commit TypeScript 05 Ağu 2026 güncellendi 05 Eyl 2026
ai-security jailbreak-detection llm llm-security monitoring openai owasp prompt-injection
16
3
flankerhqd/cyvisguard 60
Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP
0,6/gün ort. +0 son gün 0 commit 0 yazar TypeScript 22 Tem 2026 güncellendi 27 Tem 2026
agent-security ai-agents ai-security claude-code llm-security mcp model-context-protocol prompt-injection
60
4
Ali-hey-0/ai-runtime-lab 182
Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, m
1,6/gün ort. +0 son gün 0 commit 0 yazar Python 20 Tem 2026 güncellendi 21 Tem 2026
agent-architecture agent-memory agentic-ai ai-agents ai-security dag durable-execution finite-state-machine
182
5
guardana/guardana 203
Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for
1,8/gün ort. +0 son gün 155 commit 5 yazar Python 18 Tem 2026 güncellendi dün
ai-red-teaming ai-safety ai-security llm-security ml-security mlsecops model-security owasp-llm
203
6
CyberSunil/LLMVault 352
An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI pe
3/gün ort. +1 son gün 1 commit 1 yazar Python 15 Tem 2026 güncellendi 19 gün önce
agent-security ai-security ai-security-tool docker genai owasp owasp-llm-top-10 penetration-testing
352
7
tracebit-com/context-bombs 163
Context bomb strings
1,3/gün ort. +0 son gün 0 commit 0 yazar 10 Tem 2026 güncellendi 14 Eyl 2026
canarytokens guardrails killswitch prompt-injection threat-detection ai ai-agents ai-safety
163
8
ByteBunny777/Docguard 35
Concurrent Go CLI that detects hidden prompt-injection content in documents — invisible Unicode, homoglyphs, hidden HTML, and known trigger
0,3/gün ort. +0 son gün — commit Go 07 Tem 2026 güncellendi 08 Tem 2026
ai-security concurrency devsecops go golang llm llm-security prompt-injection
35
9
openguardrails/OpenGuardrailsBench 60
OpenGuardrailsBench (OGB): an open, reproducible benchmark for AI guardrails across safety, security, privacy and policy
0,5/gün ort. +0 son gün — commit Python 30 Haz 2026 güncellendi 2 gün önce
ai-safety guardrails prompt-injection benchmark content-moderation evaluation huggingface leaderboard
60
10
gl0di/clawseccheck 59
🦞 Local, read-only security audit for your OpenClaw agent. Finds config, prompt-injection and supply-chain risks, watches for drift, and ve
0,4/gün ort. +0 son gün — commit Python 19 Haz 2026 güncellendi dün
agent-security ai-agents ai-security cli llm-security mcp openclaw owasp
59
11
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 alignment guardrails llm ai-safety autoresearch benchmark content-moderation
129
12
samarailly51-pixel/claimpilot-harness 22
Crash-test insurance claim AI agents before production.
0,1/gün ort. +0 son gün — commit Python 05 Haz 2026 güncellendi 24 Ağu 2026
agent-evaluation ai-agents insurance llm-evals prompt-injection python testing
22
13
securelayer7/PROMPTPurify 80
Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: an
0,5/gün ort. +0 son gün — commit TypeScript 16 May 2026 güncellendi 31 May 2026
ai-firewall ai-safety ai-security application-security ctf guardrails jailbreak-detection llm-guardrails
80
14
DaoyuanLi2816/mcp-fence 37
Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol server
0,2/gün ort. +0 son gün — commit Python 16 May 2026 güncellendi 21 Ağu 2026
fuzzer llm-security mcp model-context-protocol prompt-injection sandbox sarif scanner
37
15
secureagentics/Adrian 589
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drif
3,3/gün ort. +0 son gün 1 commit 1 yazar Python 11 May 2026 güncellendi 18 gün önce
agent-security agents ai ai-governance ai-security langchain langgraph llm-security
589
16
4vanish/AI-Pentest-Playbook 41
🛡 The reference playbook for pentesting AI chatbots & LLM-powered apps in one place. Ready-to-use payloads covering the full OWASP LLM Top 1
0,2/gün ort. +0 son gün — commit Python 10 May 2026 güncellendi 18 Haz 2026
ai-pentesting ai-security bug-bounty jailbreak llm-security mcp owasp-llm-top10 pentesting
41
17
UnplugAI/Unplug 45
Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.
0,2/gün ort. +0 son gün — commit Python 09 May 2026 güncellendi 2 gün önce
ai-safety llm prompt-injection python sdk security
45
18
kangarooking/system-prompt-skills 221
从 165 个顶级 AI 产品系统提示词中蒸馏出的 15 个可执行 Agent skill
1,2/gün ort. +0 son gün 0 commit 0 yazar 04 May 2026 güncellendi 04 May 2026
agent-design ai-agents cangjie-skill context-management prompt-engineering prompt-injection system-prompt tool-use
221
19
vincenzo-afk/hackerrank-agent 37
A terminal-based, multi-domain support-ticket triage agent grounded in a local support corpus.
0,2/gün ort. +0 son gün — commit Python 01 May 2026 güncellendi 23 Ağu 2026
agentic-ai ai-agents ai-safety cli customer-support groq hybrid-search information-retrieval
37
20
crucible-security/crucible 51
pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents
0,3/gün ort. +0 son gün — commit Python 20 Nis 2026 güncellendi 14 gün önce
ai-agents ai-security llm owasp prompt-injection python red-teaming security-testing
51
21
uber/ADR önem 70gpt6-luna uyum 24gpt6-luna 2.127
ADR, AI agent’ları keşfetmek, etkinliklerini gözlemlemek ve riskli davranışları tespit etmek için araçlar ile benchmark’lar sunan açık kaynaklı bir güvenlik sistemidir.
Neden yükseliyor · AI agent güvenliği güncel ve kurumsal ölçekte büyüyen bir ihtiyaç; Uber’in projeyi açık kaynak olarak yayımlaması, README’de üretimde kullanıldığını ve MLSys 2026’da kabul edilen bir makaleyle desteklendiğini belirtmesi ilgiyi artırıyor. 167 günde 1.620 yıldızın yanı sıra son 28 gündeki 44 commit ve 15 farklı yazar, kayda değer proje etkinliğine işaret ediyor; ancak yıldız geçmişi olmadan yükseliş hızını doğrulamak mümkün değil.
10,5/gün ort. +1 son gün 51 commit 3 yazar Python 19 Nis 2026 güncellendi 8 gün önce
agent-security ai-agents ai-security benchmark llm-security mcp model-context-protocol prompt-injection
2.127
22
CollieAi/llm-firewall 47
AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks
0,2/gün ort. +0 son gün — commit 17 Nis 2026 güncellendi 5 gün önce
ai-firewall llm-security ai-gateway guardrails prompt-injection content-moderation pii-detection hallucination-detection
47
23
killertcell428/aigis 53
Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a
0,3/gün ort. +0 son gün — commit Python 11 Nis 2026 güncellendi dün
ai-security firewall llm mcp owasp prompt-injection ai-agent compliance
53
24
KeyValueSoftwareSystems/agent-opfor 584
Open-source adversary emulation for AI agents and MCP servers.
2,7/gün ort. +0 son gün 0 commit 0 yazar TypeScript 06 Nis 2026 güncellendi 5 gün önce
adversary-emulation agentic-ai ai-agents ai-red-teaming ai-security jailbreak llm-security mcp
584
25
claudlos/hermes-katana 49
Defense-in-depth security toolkit for LLM agents — taint tracking, proxy secret guard, policy engine, and red-team benchmarking
0,2/gün ort. +0 son gün — commit Python 05 Nis 2026 güncellendi 6 gün önce
ai ai-agent ai-agents hermes hermes-agent llm llms security
49