Havuz

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless re

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

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.

The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation,

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for

Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky

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.

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.

Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugi

Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open

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.

Deterministic safety solutions for probabilistic AI agents

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI pe

Proof-Carrying Messages: a protocol for AI agents whose claims carry evidence the receiver checks offline

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drif

Agent Canary 3.0: open-source MCP, SDK, and CLI security toolkit with a guarded execution gateway, decoy signals, local tests, and public ac

Micro-VM sandbox for AI agents: isolated, gated and auditable, to prove what your agents did

DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Ten

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

AgentAegis is a lightweight plugin providing full-lifecycle runtime protection for OpenClaw.

Stop AI agents from doing things they shouldn't. The action authorization layer — pre-execution, deterministic, policies included. Drop in.

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

Free, MIT-licensed MCP security testing from ClearFrame. Scan, audit, compare, and review locally; continue in the ClearFrame CLI or Mac app

Six security outcomes an enterprise must achieve to run AI agents, and the controls that evidence them. A draft for public comment.

Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see y

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.

A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.

Open source authorization engine for AI agents. Confidence-aware gating · Human-in-the-loop review · Policy-as-code · Full audit trail

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidenc

Trace-backed Agent Authorization Reviews for tool-using AI agents. Staging-only evidence for payment, record-change, access, and export acti

Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK enforcement.

Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP

🦞 Local, read-only security audit for your OpenClaw agent. Finds config, prompt-injection and supply-chain risks, watches for drift, and ve

Executable security regression testing for agentic applications and MCP-integrated systems.

Defense-in-depth security toolkit for LLM agents — taint tracking, proxy secret guard, policy engine, and red-team benchmarking

Research artifacts for provenance-bound agent authorization, signed effect evidence, and reproducible security evaluation.

Minimal Ed25519-signed activity receipts for verifiable AI agents — self-attested, offline-verifiable, no blockchain.

Public SDKs and integration contracts for Armorer Guard.

reconnaissance for agent attack surfaces

Verify what AI coding agents can actually read, write, execute and reach using synthetic canaries.

Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.

Confine an AI coding agent to one directory with a BPF-LSM program, and watch every escape it tries.

Cryptographic trust and authorization evidence for AI agents. Every action a receipt, every grant a proof.

Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as str

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human a

Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a clai

An OWASP-aligned intentionally vulnerable platform for learning and testing AI, LLM, RAG, MCP, and Agentic AI security.

Soup Wall: open-source security for AI agents and model traffic. Local Agent, Gateway, self-hosted Console. Apache-2.0.