Açık kaynak radarı

Havuz

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

133

repo · sayfa 1 / 3

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 llm-security

1
qybaihe/bla 2.028
🛡️ BLA (Blind LLM Agents) — Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI
225,3/gün ort. +136 son gün 328 commit 2 yazar TypeScript 25 Eki 2026 güncellendi dün
adversarial-ai claude-code cursor electron-security llm-security mcp mcp-server obfuscation
2.028
2
SRN0129/Agenttrust 22
Enterprise Zero-Trust AI Security & Governance Gateway: Real-Time Prompt Injection Defense, Action Scoping, HITL Approvals, Post-Quantum Mer
2,4/gün ort. +1 son gün — commit TypeScript 25 Eki 2026 güncellendi 2 gün önce
compliance crewai cybersecurity eu-ai-act langchain llm-security zero-trust agentic-ai
22
3
lemonadesaltbagel/veil 96
Local privacy proxy for AI coding agents. Keep PII and secrets out of LLMs with deterministic pseudonymization.
7,4/gün ort. +8 son gün 50 commit 1 yazar Python 21 Eki 2026 güncellendi 4 gün önce
ai-agents data-loss-prevention data-masking data-privacy database-security llm-security local-first mcp
96
4
vasikmansuri/agentconfig-doctor 13
MCP security scanner & config linter for AI coding agents. Finds leaked secrets, risky commands, broad permissions and invalid MCP servers i
0,7/gün ort. +0 son gün — commit TypeScript 14 Eki 2026 güncellendi 2 gün önce
ai-agents claude-code cli cursor developer-tools devsecops linter mcp
13
5
motan1337/universal-bypass-for-claude-chatgpt-qwen-deepseek-llm-claude-code-codex 20
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. +2 son gün — commit 13 Eki 2026 güncellendi 6 gün önce
ai bypassing claude claude-ai claude-code claude-code-plugin claude-code-skills claude-skills
20
6
scs0209/laya-guard 37
Free local guardrail for AI coding agents: every tool_call judged on-device (regex + Laya), allow/review/block
1,6/gün ort. +2 son gün — commit Python 11 Eki 2026 güncellendi dün
ai-agents ai-safety claude-code coding-assistant fastapi guardrails llm-security local-first
37
7
mitthanmeena-ops/agent-emergency-protocol 13
Agent Emergency Protocol Incident Codes: a vendor-neutral runtime incident-code language for autonomous AI agents. Created by Mitthan Meena.
0,5/gün ort. +0 son gün — commit 06 Eki 2026 güncellendi 28 gün önce
agent-kill-switch ai-agents ai-security mitre-atlas agent-emergency incident-response llm-security agent-swarm
13
8
e2sy/jailbreak-archives 82
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 15 commit 1 yazar Roff 30 Eyl 2026 güncellendi dün
adversarial-prompts ai-red-team ai-safety chatgpt claude cybersecurity deepseek jailbreak
82
9
batrapulkit/squidbrake 18
Agents propose. People approve. Change control for AI agents: everyday work runs on its own, anything an agent can't take back waits for a t
0,5/gün ort. +1 son gün — commit Python 29 Eyl 2026 güncellendi 2 gün önce
ai-agents ai-safety approval-workflow audit-log claude-code fastapi human-in-the-loop llm-security
18
10
everafterlabs/jes 17
Open-source guardrails for AI agents powered by decision models like Jev; checks prompts, retrieved content, tool calls and responses for pr
0,5/gün ort. +0 son gün — commit Python 29 Eyl 2026 güncellendi 8 gün önce
ai-agents ai-security guardrails jailbreak langchain llm-security mcp pii-redaction
17
11
B0yko/pgwarden 23
Governed Postgres access for AI assistants: an MCP gateway with OAuth 2.1 and OIDC login, one Postgres role per person, database-enforced re
0,6/gün ort. +0 son gün — commit Python 28 Eyl 2026 güncellendi 8 gün önce
ai-security audit-log cloud-run data-governance fastapi llm-security mcp model-context-protocol
23
12
Cygnux-Labs/Tracekit 360
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
9,5/gün ort. +0 son gün 1.702 commit 17 yazar Python 26 Eyl 2026 güncellendi bugün
agent-security ai-agents ai-safety audit-log audit-trail certificate-transparency claude-code guardrails
360
13
Justinuse1/pojia-breaker 49
Chinese-first LLM jailbreak benchmark & red-team toolkit | 中文LLM安全评测框架 | by POJIA.AI
1,2/gün ort. +1 son gün — commit JavaScript 24 Eyl 2026 güncellendi 27 Eyl 2026
ai-safety benchmark chinese-nlp deepseek jailbreak llm-evaluation llm-security prompt-injection
49
14
guardana/control 14
Observe AI agent runs and control consequential actions. Signed policies, exact-action approvals, AuthZEN API vetoes and evidence. MCP gatew
0,4/gün ort. +0 son gün — commit Go 24 Eyl 2026 güncellendi 2 gün önce
agent-observability agent-security agentic-ai ai-agents ai-governance ai-security audit-trail authorization
14
15
rudratoshs/buried-injections 30
🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Repro
0,7/gün ort. +0 son gün — commit Python 23 Eyl 2026 güncellendi 11 gün önce
agentdojo ai-agents benchmark llm-security mcp prompt-guard prompt-injection
30
16
francordel/myrtia 33
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. +0 son gün — commit Python 21 Eyl 2026 güncellendi 8 gün önce
adversarial-attacks adversarial-machine-learning agentic-ai ai-red-teaming ai-safety ai-security ares harmbench
33
17
invarislabs/invaris-agentsec 21
Adversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression tes
0,5/gün ort. +1 son gün — commit Python 20 Eyl 2026 güncellendi 3 gün önce
adversarial-testing agent-security ai-agents ai-security devsecops github-actions langchain llm-security
21
18
Continuum-AI-Corp/Orca-AI-Incident-Archive 30
An open database of real-world AI agent incidents.
0,7/gün ort. +1 son gün — commit HTML 18 Eyl 2026 güncellendi 2 gün önce
agentic-ai ai-agents ai-governance ai-incidents ai-safety ai-security cve cybersecurity
30
19
agent-chaperone/agent-chaperone 22
Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a clien
0,5/gün ort. +0 son gün — commit TypeScript 18 Eyl 2026 güncellendi 14 gün önce
agent-security ai-agent-security ai-agents ai-security claude-code guardrails jev jev-ai
22
20
serkankorkut/mask2ai 21
PII redaction for ChatGPT, claude.ai and Claude Code. Masks names, emails, phone numbers, cards, IBANs and IDs before they leave your machin
0,5/gün ort. +0 son gün — commit JavaScript 18 Eyl 2026 güncellendi 19 gün önce
anonymization chatgpt chatgpt-extension chrome-extension claude claude-ai claude-code claude-code-plugin
21
21
kulchankas/paranoid 48
Your app is guilty until proven secure: an agent skill whose /hack-me breaks into your own running app, proves each bug with a real request,
1/gün ort. +0 son gün — commit Python 15 Eyl 2026 güncellendi 9 gün önce
agent-skills ai-agents appsec claude-code codex cursor dast devsecops
48
22
awarexone/AXguard 25
Open-source AI security tool to scan and fix vulnerabilities in your vibe-coded projects before you ship. AXguard by AwareXone.
0,5/gün ort. +0 son gün — commit Python 14 Eyl 2026 güncellendi dün
ai-agent-security ai-penetration-testing ai-security application-security appsec awarexone cicd claude-code
25
23
tomiBraunn/backlight-skill 25
Claude skill that catches hidden prompt-injection text in documents before acting on them
0,5/gün ort. +0 son gün — commit 13 Eyl 2026 güncellendi 27 Eyl 2026
agent-skills ai-security claude claude-code llm-security prompt-injection
25
24
do-whilefor/Jase-CI 24
Continuous red-team + latency-benchmark CI for LLM apps — promptfoo scans, deterministic security gate, p95 budgets. One DeepSeek key runs i
0,5/gün ort. — commit Python 13 Eyl 2026 güncellendi 10 gün önce
agent llm ci-cd llm-security
24
25
Shalimov04/mcp-airlock 15
Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing
0,3/gün ort. +0 son gün — commit Python 13 Eyl 2026 güncellendi 5 gün önce
agentic-ai ai-agents ai-safety audit-log guardrails human-in-the-loop llm-security llm-tools
15
26
DorianChn/shanchuanzhi-agent-canary 81
Agent Canary 3.0: open-source MCP, SDK, and CLI security toolkit with a guarded execution gateway, decoy signals, local tests, and public ac
1,6/gün ort. +7 son gün — commit JavaScript 12 Eyl 2026 güncellendi dün
agent-security ai-agents canary devtools honeypot llm-security mcp prompt-injection
81
27
ZeroDayEvil/ai-security-tool 1.303
🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomo
24,1/gün ort. +19 son gün 149 commit 1 yazar HTML 10 Eyl 2026 güncellendi dün
ai-hacking ai-security-tool cve-scanner cybersecurity hacking-tool llm-security mcp-server mcp-tools
1.303
28
onkarbadve/agy-auto 15
Auto-permission engine for Antigravity CLI (agy): deterministic AST parser + LLM classifier
0,3/gün ort. +0 son gün — commit Python 07 Eyl 2026 güncellendi 21 Eyl 2026
agentic-ai agy ai-agents antigravity cli coding-agent guardrails llm-security
15
29
SoupTeam/soup-wall 29
Soup Wall: open-source security for AI agents and model traffic. Local Agent, Gateway, self-hosted Console. Apache-2.0.
0,5/gün ort. +1 son gün — commit Python 06 Eyl 2026 güncellendi dün
agent-security ai-agents ai-security appsec claude-code firewall llm-proxy llm-security
29
30
AGGIB/Stroq 19
Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky
0,3/gün ort. +0 son gün — commit TypeScript 04 Eyl 2026 güncellendi dün
agent-security ai-agents ai-security claude-code codex coding-agents cursor developer-tools
19
31
CTRLRun/ctrlrun 27
The execution safety layer for AI agents.
0,4/gün ort. +0 son gün — commit Python 03 Eyl 2026 güncellendi dün
agent-control-standard agent-security agentic-ai ai-agents ai-safety audit-log human-in-the-loop langgraph
27
32
Tcotl/AgentCapture 168
Deception-layer honeypot that captures & reverse-controls AI pentest agents — embedded decoys, prompt-injection counter-offense, MCP honeypo
2,7/gün ort. — commit Python 02 Eyl 2026 güncellendi dün
ai-agent deception fastapi honeypot llm-security prompt-injection python threat-intelligence
168
33
efij/AgentDFIR 13
Open-source digital forensics and incident response for AI agents (Claude Code, Codex, Cursor, Gemini, Copilot…). One command: detect → coll
0,2/gün ort. +0 son gün — commit Go 31 Ağu 2026 güncellendi 9 gün önce
agentic-security ai-agents ai-security claude-code codex copilot cursor dfir
13
34
FarzamHabibi/pre-production-checklist 15
Pre-production checklists for solo founders. 4,685 items, 88% portable to any stack, 26 stack supplements — plus AI/agent security and the b
0,2/gün ort. +0 son gün — commit JavaScript 27 Ağu 2026 güncellendi 16 gün önce
ai-security appsec checklist devsecops indiehackers llm-security prompt-injection security
15
35
takashi-ohmoto-git/CyberRiskScape 21
Visual threat modeling tool covering AI, LLM, agentic systems, and post-quantum cryptography
0,3/gün ort. +0 son gün — commit TypeScript 26 Ağu 2026 güncellendi dün
agentic-ai ai-security dfd llm-security mitre-atlas owasp post-quantum-cryptography react
21
36
dodoguardai/dodoguard 277
DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Ten
4/gün ort. +0 son gün 0 commit 0 yazar TypeScript 25 Ağu 2026 güncellendi 27 gün önce
agent-security ai-agents ai-security dify fastgpt guardrails llm-evaluation llm-security
277
37
omaekumiko2-create/OpenKeylet 134
OpenKeylet — Local password and credential manager for AI agents via MCP. Use passwords, API keys, SSH, and TOTP while keeping hidden plaint
1,9/gün ort. +0 son gün 6 commit 1 yazar Rust 24 Ağu 2026 güncellendi 9 gün önce
ai-agents ai-security api-key-management claude-code codex credential-manager cross-platform cursor
134
38
Hannay001/lockkeeper 18
Skill router and prompt-injection firewall for AI coding agents: gives Claude Code, Codex and Cursor the few skills, MCP servers and tools e
0,3/gün ort. +0 son gün — commit Python 24 Ağu 2026 güncellendi 18 gün önce
agent-skill agent-skills ai-agents claude-code claude-code-plugin cli codex context-window
18
39
eulogik/OpenTrustBench 14
Trust & security scanner for AI agents and MCP servers — OWASP-mapped findings, Trust Cards (A–F grades), SARIF + CI gate. Free CLI, zero te
0,2/gün ort. +0 son gün — commit HTML 24 Ağu 2026 güncellendi 2 gün önce
agent-security ai-agents ai-security compliance devsecops eu-ai-act github-actions llm-security
14
40
securetron-gh/aifw 454
AI Agent Identity and Access Management and Inference Firewall
6,2/gün ort. +0 son gün 7 commit 2 yazar Python 22 Ağu 2026 güncellendi 11 gün önce
agent-identity ai-audit ai-firewall ai-gateway ai-governance ai-security llm-security mcp
454
41
Karansingh1999/PIIFlow 104
Policy-aware static taint analysis for detecting sensitive-data flows into LLM APIs.
1,4/gün ort. +0 son gün — commit Python 20 Ağu 2026 güncellendi 20 Ağu 2026
ai-security data-flow-analysis devsecops llm-security privacy-engineering python python-ast responsible-ai
104
42
IdoGol24/weir 18
Keep your sensitive credentials out of the agents you build and the coding agent you use. Test any agent with planted fake keys, or see whic
0,2/gün ort. +0 son gün — commit Python 19 Ağu 2026 güncellendi 7 gün önce
agent-security agents ai ai-agents ai-security canary-tokens ci claude-code
18
43
buryusu/All-AI-Jailbreaks 94
Curated archive of jailbreak and prompt-injection experiments for AI model robustness research, red-teaming, and defensive evaluation.
1,2/gün ort. +1 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
94
44
Nikita3005/taintgate 90
Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK enforcement.
1,2/gün ort. +0 son gün — commit Python 18 Ağu 2026 güncellendi 19 Ağu 2026
agent-security ai-agents guardrails langchain langgraph llm-security mcp openai-agents
90
45
PerryLink/dsh-defend 25
Prompt-injection, jailbreak and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanit
0,3/gün ort. +2 son gün — commit TypeScript 16 Ağu 2026 güncellendi dün
ai-agent ai-agents cordis deepseek deepseek-harness developer-tools dsh dsh-plugin
25
46
UnboundCompute/security-agent-skills 22
Security-testing methodology as portable, tool-agnostic agent skills for Claude Code and any agent runtime: white-box bug hunting, AI-agent
0,3/gün ort. +0 son gün — commit 16 Ağu 2026 güncellendi 08 Eyl 2026
agent-skills ai-security appsec claude claude-code claude-skills llm-security mcp
22
47
MohammadThabetHassan/trustweave 17
Static security review for AI agent configs (LangGraph, CrewAI, OpenAI Agents, MCP): maps source-to-tool flows and flags untrusted input tha
0,2/gün ort. +0 son gün — commit Python 13 Ağu 2026 güncellendi 19 gün önce
agent-security agentic-ai ai-agents ai-security developer-tools llm-security mcp python
17
48
volt-l18/llm-redteam-pipeline 31
An automated, multi-turn LLM red-teaming pipeline that pits an Attacker model against a Target model to evaluate safety boundaries, featurin
0,4/gün ort. +1 son gün — commit Python 11 Ağu 2026 güncellendi 12 Ağu 2026
llm llm-red-teaming llm-security llm-tools python3 redteaming
31
49
MING-ZCH/open-thinking-replay 21
Recovering verbatim private reasoning from Claude extended-thinking signatures, with a local byte-exact verifier.
0,2/gün ort. +0 son gün — commit Python 10 Ağu 2026 güncellendi 12 Ağu 2026
ai-safety claude extended-thinking interpretability llm-security
21
50
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