18 مستودعات
Frameworks and auditing tools designed to secure agent configurations and prevent vulnerabilities in automated systems.
Distinguishing note: Focuses on security auditing specifically for agentic architectures rather than general application security.
Explore 18 awesome GitHub repositories matching security & cryptography · Agent Security. Refine with filters or upvote what's useful.
ECC هو إطار عمل لأوركسترا وكلاء LLM ومجموعة أدوات ذكاء اصطناعي عبر المنصات مصممة لتنسيق سير العمل متعدد النماذج. يوفر نظاماً لإدارة أدوار الوكلاء المتخصصة، والمهارات القابلة لإعادة الاستخدام، والتخطيط المهيكل لتنفيذ مهام تطوير البرمجيات المعقدة عبر محررات كود مختلفة مدعومة بالذكاء الاصطناعي. يتميز المشروع كمدير لبروتوكول سياق النموذج (Model Context Protocol)، حيث يوفر طبقة تكوين لدمج الخوادم الخارجية وتدقيق تنفيذ الأدوات. كما ينفذ بيئة أمنية للوكلاء (agentic security sandbox) تقيد الوصول إلى الملفات الحساسة وتفحص تسرب الأسرار لتأمين سير العمل المستقل. يغطي إطار العمل مجالات قدرة واسعة بما في ذلك أتمتة سير عمل البرمجة بالذكاء الاصطناعي مع حواجز حماية التطوير القائم على الاختبار، وتحسين تكلفة النموذج من خلال التوجيه الذكي، وإدارة الذاكرة المعزولة الحالة. كما يتضمن أدوات لفرض معايير البرمجة الخاصة باللغة وإدارة سلوكيات الوكلاء عبر بيئات تطوير متكاملة مختلفة. تتم إدارة النظام من خلال واجهة سطر أوامر تتعامل مع تثبيت الأدوات، وإصلاح التكوين، ونشر إعدادات الأدوات المسبقة.
Provides a security layer that scans for secret leakage and restricts file access in autonomous workflows.
Everything Claude Code هو إطار عمل وكيل مصمم لتنسيق سير عمل تطوير البرمجيات المعقدة من خلال تفويض الوكلاء الفرعيين المتخصصين. يعمل كطائرة تحكم تدير سلوك الوكيل، والوصول إلى الأدوات، وكفاءة نافذة السياق، مما يسمح للمطورين بتقسيم المهام الكبيرة إلى عمليات فرعية مركزة ومحددة النطاق تمنع تحميل النظام الزائد. يتميز إطار العمل بطبقة أمن وأتمتة قوية تتضمن التحليل الثابت الآلي واختبار الاختراق العدائي لتدقيق تكوينات الوكيل. وهو يتيح إنشاء أنماط سلوكية قابلة لإعادة الاستخدام وتسلسلات أتمتة، والتي يمكن مشاركتها عبر البيئات كمهارات معيارية. من خلال مزامنة التكوينات الخاصة بالمشروع وتعليمات الدردشة، فإنه يضمن بقاء معايير البرمجة وقيود الأمان متسقة عبر كل من سطر الأوامر وبيئات التطوير المتكاملة. بعيداً عن قدرات الأوركسترا الأساسية، يوفر المشروع أدوات شاملة لإدارة التكاليف التشغيلية أثناء الجلسات طويلة الأمد. يتضمن آليات لتحسين الرموز الديناميكي، وإدارة حالة الجلسة، والخطافات القائمة على الأحداث التي تطلق نصوص التحقق أو فرض الجودة. يدعم النظام أيضاً استخراج الأنماط المتكررة من تاريخ التحكم في الإصدار لتوليد مجموعات مهارات متخصصة، مما يزيد من تبسيط مهام التطوير المتكررة.
A set of automated tools and validation hooks designed to audit agent configurations and prevent vulnerabilities during development.
Awesome Copilot is a comprehensive framework for autonomous software development, providing the infrastructure to orchestrate multi-agent teams and automate complex coding workflows. It functions as a centralized platform for managing AI-driven development, enabling developers to deploy specialized agents that interact with local files, terminal commands, and external APIs to execute end-to-end software delivery tasks. The project distinguishes itself through its focus on governance and extensibility, offering a suite of security controls, policy-based execution guardrails, and audit trails t
Checks agent-based systems against industry security standards to identify vulnerabilities and ensure compliance.
This framework provides a development toolkit for building autonomous agents that utilize language models to solve complex, non-deterministic tasks. Its core design centers on a code-executing architecture where agents generate and run Python code snippets to perform logic, data manipulation, and tool interactions. By moving beyond structured data formats, the system enables agents to manage program flow and object state through iterative reasoning cycles. The project distinguishes itself through its focus on code-based agent implementation and secure execution environments. Developers can ch
Implements security measures and sandboxing to protect against risks associated with agent-generated code.
Pangolin is a zero-trust remote access platform designed to provide secure, identity-aware connectivity to private network resources. It functions as a cloud-native network controller that orchestrates encrypted tunnels, traffic routing, and access policies across distributed environments. By leveraging WireGuard for secure data transport, the platform enables authenticated access to internal web applications, terminal sessions, and remote desktops without exposing services to the public internet. The platform distinguishes itself through a declarative infrastructure model that synchronizes n
Enforces token-based authentication for secure data exchange between monitoring agents and the central dashboard.
This project is a comprehensive framework for developing, orchestrating, and deploying autonomous agents. It provides a structured environment for building agents that utilize reasoning loops to perform multi-step tasks, manage state through graph-based workflows, and interact with external tools. By mapping unstructured model outputs into typed schemas, the framework ensures reliable integration with downstream application logic. The platform distinguishes itself through a focus on production-grade reliability and security. It incorporates hybrid memory systems that combine vector embeddings
Implements safety protocols, input validation, and human-in-the-loop workflows to secure agent operations.
The AWS Cloud Development Kit is an infrastructure-as-code framework that enables developers to define and provision cloud resources using familiar programming languages. By utilizing construct-based synthesis, it translates high-level, object-oriented code into declarative templates, allowing for the automated management of complex cloud environments through a centralized, code-driven control plane. The framework distinguishes itself through its ability to model infrastructure as a dependency-aware resource graph, ensuring that components are provisioned and updated in the correct order. It
Manages authentication and access control for agents by integrating with existing identity providers.
CrowdSec is a collaborative, distributed security engine designed for threat detection and infrastructure protection. It functions as an intrusion detection system that parses logs and network traffic to identify malicious patterns, utilizing a bucket-based threshold detection model to aggregate events and trigger alerts. The platform is built on a modular architecture that includes a centralized local API server for managing security signals and a relational database for persistent storage of remediation decisions. What distinguishes the project is its decoupled enforcement model, which offl
Allows administrators to verify the connectivity and operational health of security agents.
This project is a JSON Web Token implementation library and toolkit for encoding, signing, and validating tokens. It provides the necessary functions to manage token claims and payloads for user authentication and authorization. The library supports both symmetric and asymmetric cryptography, allowing for the use of shared secrets or public-private key pairs. It enables the creation of signed tokens and the verification of their authenticity and integrity to prevent data tampering. The toolkit covers a broad range of identity and access control capabilities, including the embedding of custom
Decodes tokens and validates signatures to ensure payload integrity and authenticity.
mcp-agent is a framework for building AI agents that integrate with Model Context Protocol servers to execute tools and access data. It functions as a multi-agent orchestrator and protocol-compliant server, enabling the creation of agents that can discover and invoke tools from connected external servers. The project distinguishes itself through a durable workflow engine that supports long-running tasks capable of pausing, resuming, and surviving restarts. It implements complex orchestration patterns, including iterative evaluator-optimizer loops, hierarchical workflow nesting, and specialist
Handles the acquisition and storage of secure tokens to authenticate communication between agents and protocol servers.
PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo
Activates injection defense and audit logging across all agents with a single call.
Empire is a post-exploitation command-and-control (C2) framework designed for red team operations. It deploys and manages agents written in PowerShell, Python, C#, Go, and C across Windows, Linux, and macOS, using encrypted communication channels over HTTP, HTTPS, and SMB. The framework executes over 400 built-in modules for reconnaissance, privilege escalation, credential theft, and lateral movement, and provides a modular engine for authoring custom attack modules. What sets Empire apart is its multi-language agent deployment system, which allows operators to choose implants that suit each
Establishes encrypted communications between the control server and agents using a two-stage key exchange.
agent-governance-toolkit هو إطار عمل لفرض سياسات الأمان، وإدارة هويات الثقة الصفرية، وعزل تنفيذ وكلاء الذكاء الاصطناعي المستقلين. يوفر طبقة حوكمة مصممة للتحكم في سلوك الوكلاء من خلال استخدام محرك سياسات الأمان، وإدارة الهوية التشفيرية، وبيئة عزل تنفيذ وقت التشغيل. يتميز المشروع بنظام حلقة امتياز متعدد المستويات وشبكة هوية تشفيرية تؤمن الاتصال بين الكيانات المستقلة. ينفذ آلية تسجيل ثقة قائمة على التحلل لتتبع موثوقية الكيان ويستخدم سجلات تدقيق مشفرة ومضادة للتلاعب للحفاظ على تاريخ قابل للتحقق من التنفيذ. تغطي مجموعة الأدوات مجموعة واسعة من مجالات القدرات، بما في ذلك أمان المطالبات للدفاع ضد هجمات الحقن، ورسم خرائط الامتثال الآلي مقابل المعايير التنظيمية، وتنظيم سير العمل المستقل باستخدام أنماط الملحمة (Saga). كما يتميز بمراقبة الأسطول لتتبع الصحة وحدود الإنفاق، بالإضافة إلى عزل تنفيذ الأدوات لتقييد الوصول غير المصرح به للموارد. يتم توفير واجهة سطر أوامر لإرسال إشارات التحكم، والتحقق من سياسات الحوكمة، وإدارة تثبيت الامتدادات.
Identifies and mitigates vulnerabilities in AI agents based on industry standards like the OWASP Agentic Top 10.
This project is an educational curriculum and architectural framework for building autonomous AI agents and multi-agent systems. It provides a structured learning path focused on the development of independent software components capable of planning, executing tasks, and utilizing external tools to achieve high-level goals. The framework emphasizes multi-agent system orchestration through distributed architectures where specialized agents collaborate using standardized communication protocols. It details specific design patterns such as dual-memory systems for maintaining short-term plans and
Implements token and API key authentication to verify agent identity and authorize requests.
Velociraptor is a digital forensics and incident response platform, endpoint detection and response system, and visibility tool. It provides a query engine and remote forensic collector used to hunt for indicators of compromise and perform triage across a fleet of hosts. The system is distinguished by its specialized query language for interrogating host state and parsing binary files. It features a notebook environment that combines markdown documentation with executable query cells to standardize investigative workflows and enable collaborative reporting. The platform covers a wide range o
Provides utilities to purge stale or inactive endpoint registrations from the server based on age thresholds.
vibe-vibe is an LLM agent engineering framework and toolchain optimizer designed for orchestrating multi-agent systems. It serves as a comprehensive guide and methodology for transforming conceptual ideas into deployed applications through agentic software engineering. The project focuses on the orchestration of specialized AI agent roles with defined collaboration boundaries and iterative feedback loops. It provides frameworks for toolchain optimization, including the selection and evaluation of protocols that extend model capabilities and the design of standardized tool interfaces. The sys
Determines appropriate isolation levels across tool and execution layers to secure autonomous agent systems.
Kimi-code is a command-line interface and orchestration framework designed to integrate autonomous AI agents into software development workflows. It functions as a terminal-based assistant that manages multi-step coding tasks, including planning, file system modifications, shell command execution, and test running, all while maintaining conversational context within a local development environment. The project distinguishes itself through a focus on secure, autonomous agent orchestration and granular control over AI interactions. It enforces strict security by requiring explicit user approval
Verifies agent identity using secure tokens for authorized operations on external platforms.
This project provides a comprehensive framework for building, deploying, and orchestrating autonomous agents within a decentralized network. It serves as a collection of patterns and examples for developing intelligent software entities capable of performing complex tasks, making decisions, and interacting with other agents to achieve shared goals. The framework distinguishes itself through its focus on multi-agent orchestration and decentralized communication. It enables the coordination of specialized agent teams that collaborate on workflows through structured messaging protocols, allowing
Secures agentic architectures by restricting public exposure to a primary orchestrator while keeping workers local.