Açık kaynak radarı

Havuz

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

repo · sayfa 1 / 2

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 agent-security

1
NVIDIA/SkillSpector önem 67gpt6-luna uyum 48gpt6-luna 23.875
SkillSpector, AI agent skills paketlerini yüklemeden önce güvenlik riskleri açısından tarayan bir Python aracıdır.
Neden yükseliyor · AI agent skills ekosistemindeki güvenlik ihtiyacına doğrudan yanıt veriyor ve NVIDIA Verified Skills pipeline'ıyla bağlantılı. 191 günlük bir repo için 18.391 yıldızın yanı sıra son 28 günde 144 commit ve 24 farklı yazar, dikkat çekmenin yalnızca README iddialarına dayanmadığını gösteriyor.
105,6/gün ort. +151 son gün +158,3 son 30g 914 commit 27 yazar Python 21 Mar 2026 güncellendi dün
agent-security agent-skills agentic-ai ai-security claude-code mcp prompt-injection security-scanner
23.875
2
Asymptote-Labs/agent-beacon 2.983
The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu
17,1/gün ort. +7 son gün +41,3 son 30g 939 commit 6 yazar Go 12 May 2026 güncellendi dün
security-tools agent-ai-cli agent-security mobile-device-management security-information-and-event-management security ci cloud
2.983
3
uber/ADR önem 70gpt6-luna uyum 24gpt6-luna 2.091
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.
10,6/gün ort. +1 son gün +15,7 son 30g 56 commit 6 yazar Python 19 Nis 2026 güncellendi 3 gün önce
agent-security ai-agents ai-security benchmark llm-security mcp model-context-protocol prompt-injection
2.091
4
Cygnux-Labs/Tracekit 360
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
9,7/gün ort. +1 son gün +14 son 16g 1.684 commit 19 yazar Python 26 Eyl 2026 güncellendi dün
agent-security ai-agents ai-safety audit-log audit-trail claude-code guardrails hacktoberfest
360
5
hashgraph-online/hol-guard 1.051
Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugi
4,8/gün ort. +7 son gün +11,2 son 30g 3.148 commit 6 yazar Python 28 Mar 2026 güncellendi dün
mcp security agent-security ai-agent-security ai-agents ai-security claude-code cursor
1.051
6
guardana/guardana 291
Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for
2,7/gün ort. +3 son gün +5,5 son 30g 204 commit 8 yazar Python 18 Tem 2026 güncellendi dün
agent-security ai-agents ai-red-teaming ai-safety ai-security devsecops llm-security mcp
291
7
NVIDIA/SkillEvaluator 620
Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation,
4,7/gün ort. +3 son gün +2,9 son 30g 96 commit 14 yazar Python 24 Haz 2026 güncellendi dün
agent-evaluation agent-plugins agent-security agent-skills agentic-ai benchmark claude-code codex
620
8
decionis/agent-safe-pipeline önem 52gpt6-luna uyum 18gpt6-luna 672
AgentSafe, agent veya API isteklerini hedefe iletmeden önce yetkilendirme kontrolünden geçiren bir HTTP execution gateway’idir.
Neden yükseliyor · 45 günlük yaşına karşılık 589 yıldız ve son 28 günde 126 commit dikkat çekiyor; ancak commit’lerin yalnızca 3 farklı yazardan gelmesi, aktivitenin geniş bir katkıcı tabanına yayıldığını göstermiyor. Yıldızların nedeni verilerden kesin olarak çıkarılamaz.
8,3/gün ort. +0 son gün +2,8 son 30g 57 commit 2 yazar TypeScript 13 Ağu 2026 güncellendi dün
agent-security ai-agents ai-governance api-gateway audit-trail authorization aws azure
672
9
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 +2,5 son 30g 0 commit 0 yazar TypeScript 25 Ağu 2026 güncellendi 26 gün önce
agent-security ai-agents ai-security dify fastgpt guardrails llm-evaluation llm-security
277
10
agentbaseline/agentbaseline 114
Six security outcomes an enterprise must achieve to run AI agents, and the controls that evidence them. A draft for public comment.
1,2/gün ort. +1 son gün +2,4 son 30g 137 commit 2 yazar Python 28 Tem 2026 güncellendi 20 gün önce
agent-security ai-agent-security ai-agents security-controls security-framework
114
11
Nikita3005/taintgate 90
Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK enforcement.
1,2/gün ort. +0 son gün +2,4 son 30g — commit Python 18 Ağu 2026 güncellendi 19 Ağu 2026
agent-security ai-agents guardrails langchain langgraph llm-security mcp openai-agents
90
12
perplexityai/numbat önem 52gpt6-luna uyum 13gpt6-luna 1.159
numbat, AI agent etkinliğini endpoint üzerinde izleyen, yerel kurallarla değerlendiren ve desteklenen durumlarda eylem öncesi engelleme sunan bir güvenlik aracıdır.
Neden yükseliyor · AI agent güvenliği ve görünürlüğü ilgi gören bir alan; endpoint izleme ile geriye dönük incelemeyi bir araya getirmesi dikkat çekebilir. Ancak 1074 yıldız 65 günlük repo için görünür ilgiye işaret etse de son 28 günde commit ve farklı yazar olmaması, ilginin güncel geliştirme faaliyetiyle desteklendiğine dair kanıt sunmuyor. Yıldızların hangi dönemde kazanıldığına ilişkin veri yok.
11,5/gün ort. +1 son gün +2,3 son 30g 61 commit 4 yazar Go 24 Tem 2026 güncellendi 3 gün önce
agent-security ai-agent-security ai-agents
1.159
13
DorianChn/shanchuanzhi-agent-canary 74
Agent Canary 3.0: open-source MCP, SDK, and CLI security toolkit with a guarded execution gateway, decoy signals, local tests, and public ac
1,5/gün ort. +9 son gün +1,7 son 30g — commit JavaScript 12 Eyl 2026 güncellendi dün
agent-security ai-agents canary devtools honeypot llm-security mcp prompt-injection
74
14
ali-ulu/huqan 41
Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a clai
0,4/gün ort. +1 son gün +1,3 son 20g — commit JavaScript 14 Tem 2026 güncellendi dün
agent-safety agent-security agentic-workflow ai-agents ai-governance ai-safety audit-trail deterministic
41
15
SponsioLabs/Sponsio 454
Deterministic safety solutions for probabilistic AI agents
2,1/gün ort. +0 son gün +0,5 son 30g 30 commit 2 yazar Python 04 Nis 2026 güncellendi 4 gün önce
agent-guardrails agent-harness agent-runtime agent-safety agent-security agent-skills agentic-ai ai-agents
454
16
CyberSunil/LLMVault 347
An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI pe
3,2/gün ort. +0 son gün +0,5 son 30g 2 commit 2 yazar Python 15 Tem 2026 güncellendi 14 gün önce
agent-security ai-security ai-security-tool artificial-intelligence ctf docker genai good-first-issue
347
17
secureagentics/Adrian 589
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drif
3,4/gün ort. +1 son gün +0,4 son 30g 1 commit 1 yazar Python 11 May 2026 güncellendi 13 gün önce
agent-security agents ai ai-governance ai-security langchain langgraph llm-security
589
18
agentrhq/authsome 103
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see y
0,5/gün ort. +0 son gün +0,4 son 30g — commit Python 16 Nis 2026 güncellendi 25 Tem 2026
ai-agents authentication cli headless local-first mcp oauth2 agent-identity
103
19
SoupTeam/soup-wall 28
Soup Wall: open-source security for AI agents and model traffic. Local Agent, Gateway, self-hosted Console. Apache-2.0.
0,5/gün ort. +0 son gün +0,4 son 30g — commit Python 06 Eyl 2026 güncellendi dün
agent-security ai-agents ai-security appsec claude-code firewall llm-proxy llm-security
28
20
GeckoVision/gecko-surf 22
The knowledge graph for APIs your agent can trust. Maps any API — even messy, paywalled, or on-chain ones — into a verified graph your agent
0,2/gün ort. +0 son gün +0,4 son 20g — commit Python 28 Haz 2026 güncellendi 12 gün önce
agent-security agent-tools ai-agents anchor api-integration knowledge-graph llm-tools mcp
22
21
ByteYellow/AgentProvenance 65
Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidenc
0,4/gün ort. +0 son gün +0,3 son 30g — commit Go 10 Haz 2026 güncellendi 8 gün önce
agent-observability agent-security ai-agents ai-security application-security causality-graph digital-forensics ebpf
65
22
minervacomputing/harness 27
Governed AI agents for sensitive data and business-critical apps. Agents never hold credentials: a gateway checks every call against per-res
0,8/gün ort. +0 son gün +0,3 son 22g — commit TypeScript 29 Eyl 2026 güncellendi 7 gün önce
agent-security ai-agents django llm openai-compatible permissions react sandbox
27
23
ANetResearch/ANet 14
Agent interoperability and security, out of the box. The network layer underneath A2A: reachable, end-to-end sealed and payable agents witho
0,1/gün ort. +1 son gün +0,3 son 3g — commit Go 16 Tem 2026 güncellendi dün
a2a a2a-protocol agent-network agent-security ai-agents claude-code codex dsh-plugin
14
24
hackwither/reap 45
reconnaissance for agent attack surfaces
0,5/gün ort. +0 son gün +0,2 son 30g — commit Go 26 Tem 2026 güncellendi 26 Eyl 2026
agent-security agent-security-tools ai-security mcp-security pentesting reconnaissance red-team bugbounty
45
25
NVDLI/NemoClawDLI 26
Free NVIDIA DLI course: build, coordinate, and secure AI agents with NemoClaw and OpenShell. Browser-based, no GPU required. Available in En
0,2/gün ort. +0 son gün +0,2 son 30g — commit Python 03 Tem 2026 güncellendi dün
agent-security ai-agents free-course llm-security nemoclaw nvidia nvidia-dli openclaw
26
26
responsibleai/agent-hooks 23
Framework-neutral control contract for AI agents: eight interception points, three verdicts, and a conformance kit.
0,2/gün ort. +0 son gün +0,2 son 30g — commit Rust 19 Haz 2026 güncellendi 3 gün önce
agent-security ai-agents conformance-testing dotnet golang guardrails policy-enforcement python
23
27
invarislabs/invaris-agentsec 20
Adversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression tes
0,5/gün ort. +0 son gün +0,2 son 20g — commit Python 20 Eyl 2026 güncellendi 2 gün önce
adversarial-testing agent-security ai-agents ai-security devsecops github-actions langchain llm-security
20
28
antgroup/agent-aegis 201
AgentAegis is a lightweight plugin providing full-lifecycle runtime protection for OpenClaw.
0,9/gün ort. +0 son gün +0,1 son 30g — commit TypeScript 31 Mar 2026 güncellendi 14 Tem 2026
agent agent-security llm openclaw openclaw-plugin security skills
201
29
permit0-ai/permit0 192
Stop AI agents from doing things they shouldn't. The action authorization layer — pre-execution, deterministic, policies included. Drop in.
0,9/gün ort. +0 son gün +0,1 son 30g — commit Rust 01 Nis 2026 güncellendi 22 Haz 2026
agent-authorization ai-agents ai-safety audit-trail compliance eu-ai-act mcp policy-engine
192
30
LuD1161/agentjail 99
Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.
0,7/gün ort. +0 son gün +0,1 son 30g — commit Go 04 Haz 2026 güncellendi 24 Eyl 2026
agent-security ai-agents claude-code codex cursor devsecops golang guardrails
99
31
Lelu-ai/lelu 71
Open source authorization engine for AI agents. Confidence-aware gating · Human-in-the-loop review · Policy-as-code · Full audit trail
0,3/gün ort. +1 son gün +0,1 son 30g — commit TypeScript 06 Mar 2026 güncellendi 8 gün önce
ai ai-agents authorization token agent-security ai-guardrails guardrails langchain
71
32
flankerhqd/cyvisguard 59
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 +0,1 son 30g — commit TypeScript 22 Tem 2026 güncellendi 27 Tem 2026
agent-security ai-agents ai-security claude-code llm-security mcp model-context-protocol prompt-injection
59
33
OWASP/Agent-Security-Regression-Harness 56
Executable security regression testing for agentic applications and MCP-integrated systems.
0,3/gün ort. +0 son gün +0,1 son 30g — commit Python 24 Nis 2026 güncellendi 27 Tem 2026
agent-security ai-security appsec llm-security mcp owasp python regression-testing
56
34
ArmorerLabs/Armorer-Guard 45
Public SDKs and integration contracts for Armorer Guard.
0,2/gün ort. +0 son gün +0,1 son 30g — commit Python 12 Nis 2026 güncellendi 10 gün önce
ai-agents guardrails agent-security ai-security mcp-security langgraph python sdk
45
35
sylvesterkaczmarek/agent-boundary-check 43
Verify what AI coding agents can actually read, write, execute and reach using synthetic canaries.
0,5/gün ort. +1 son gün +0,1 son 30g — commit Python 09 Ağu 2026 güncellendi 25 gün önce
agent-security ai-agents ai-safety coding-agents developer-tools least-privilege permissions python
43
36
bluerock-io/bluerock 36
Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as str
0,2/gün ort. +0 son gün +0,1 son 30g — commit Python 31 Mar 2026 güncellendi 5 gün önce
ai-agents ai-security mcp python rust agent-security code-execution llm-security
36
37
CTRLRun/ctrlrun 27
The execution safety layer for AI agents.
0,5/gün ort. +0 son gün +0,1 son 30g — commit Python 03 Eyl 2026 güncellendi 2 gün önce
agent-control-standard agent-security agentic-ai ai-agents ai-safety audit-log human-in-the-loop langgraph
27
38
norviq-dev/norviq 27
Runtime security platform for LLM agent tool calls on Kubernetes
0,2/gün ort. +0 son gün +0,1 son 30g — commit Python 28 May 2026 güncellendi 2 gün önce
agent-security ai-agents ai-safety devsecops kubernetes langchain llm-security mcp
27
39
aveproject/ave 24
AVE - Agentic Vulnerability Enumeration. The open behavioral classification standard for agentic AI components.
0,1/gün ort. +0 son gün +0,1 son 30g — commit Python 14 Nis 2026 güncellendi 3 gün önce
agentic-ai ave vulnerability agent-security ai-agents ai-security aivss devsecops
24
40
aegisora-ai/aegisora 22
Open-source runtime security and execution control for autonomous AI agents. ALLOW, BLOCK, ESCALATE at the execution boundary with auditable
0,2/gün ort. +0 son gün +0,1 son 30g — commit Python 28 Tem 2026 güncellendi 3 gün önce
agent-execution-control agent-runtime-security agent-security agentic-ai ai-agent-security ai-agents ai-governance ai-safety
22
41
0xSteph/patient-zero 20
Supply-chain attack scanner for the agent era. Triage in 30s with `npx patient-zero`, block malicious installs before postinstall runs, or d
0,1/gün ort. +0 son gün +0,1 son 30g — commit JavaScript 14 May 2026 güncellendi dün
agent-security cli ioc-scanner javascript mcp npm pypi security
20
42
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 +0,1 son 30g — commit TypeScript 04 Eyl 2026 güncellendi 2 gün önce
agent-security ai-agents ai-security claude-code codex coding-agents cursor developer-tools
19
43
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 +0,1 son 23g — commit Python 13 Ağu 2026 güncellendi 18 gün önce
agent-security agentic-ai ai-agents ai-security developer-tools llm-security mcp python
17
44
DobermanCore/Doberman-Core 277
Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they exe
1,9/gün ort. +0 son gün +0 son 30g 60 commit 9 yazar Python 07 Haz 2026 güncellendi 5 gün önce
agent-security ai-agents ai-safety authorization guardrails llm llm-security mcp
277
45
jnMetaCode/shellward 139
AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源
0,6/gün ort. +0 son gün +0 son 30g — commit TypeScript 12 Mar 2026 güncellendi 29 Eyl 2026
openclaw prompt-injection security ai-agent ai-security llm-security shellward pii-detection
139
46
christiangrey922/multi-agent-workflow-lab 85
Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.
1/gün ort. +0 son gün +0 son 30g 0 commit 0 yazar TypeScript 12 Ağu 2026 güncellendi 14 Ağu 2026
agent-orchestration agent-security agent-testing ai-agent ai-agents ai-security mcp model-context-protocol
85
47
hugoii/llm-agent-audit 62
Trace-backed Agent Authorization Reviews for tool-using AI agents. Staging-only evidence for payment, record-change, access, and export acti
0,4/gün ort. +0 son gün +0 son 30g — commit Python 04 Haz 2026 güncellendi 11 Tem 2026
access-control agent-security ai-agents authorization llm-security payment-security security-review transaction-authorization
62
48
gl0di/clawseccheck 58
🦞 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 +0 son 30g — commit Python 19 Haz 2026 güncellendi dün
agent-security ai-agents ai-security cli llm-security mcp openclaw owasp
58
49
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 +0 son 30g — commit Python 05 Nis 2026 güncellendi 8 gün önce
ai ai-agent ai-agents hermes hermes-agent llm llms security
49
50
christopherkarani/ryk 42
Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.
0,2/gün ort. +0 son gün +0 son 30g — commit Zig 06 May 2026 güncellendi 20 Ağu 2026
agent-security ai-agents claude-code codex developer-tools plugins redteam runtime
42