Awesome AI AgentsAI Agents

usestrix/strix

⭐ 62274 Python added to this list on 2025-10-04 repository created 2025-08-05

Strix is an open-source project that provides autonomous AI agents designed to act like real hackers to dynamically test applications for security vulnerabilities. It is built to help developers and security teams quickly and accurately identify and validate security issues without the need for manual penetration testing or dealing with false positives common in static analysis tools. Strix offers a comprehensive hacker toolkit out of the box, including HTTP proxy capabilities, browser automation for testing cross-site scripting (XSS), cross-site request forgery (CSRF), and authentication flows, interactive terminal environments, a Python runtime for custom exploit development, reconnaissance tools for attack surface mapping, and both static and dynamic code analysis. The agents work collaboratively in teams to scale testing and share findings dynamically, enabling fast and thorough security assessments. The project supports a wide range of vulnerability detection including access control issues like IDOR and privilege escalation, injection attacks such as SQL and command injection, server-side vulnerabilities like SSRF and deserialization flaws, client-side issues including XSS and DOM vulnerabilities, business logic flaws, authentication weaknesses, and infrastructure misconfigurations. Strix can be run locally using Docker and Python, with integration for large language models (LLMs) to enhance its AI capabilities. It also offers a cloud-hosted version for users who prefer a managed service. Strix is developer-first with a command-line interface that provides actionable reports and even supports auto-fixing vulnerabilities to accelerate remediation. It is suitable for use cases such as rapid penetration testing, automated bug bounty research, continuous integration/continuous deployment (CI/CD) security testing, and compliance reporting. The project emphasizes security by running tests in sandboxed Docker containers and processing data locally to ensure privacy and control. Overall, Strix is a powerful AI-driven security testing platform that automates the discovery, validation, and remediation of application vulnerabilities, making security testing more accessible, efficient, and reliable for development and security teams.

https://github.com/usestrix/strix

access-controlagentsai-agentsartificial-intelligenceauthentication-testingautomated-bug-bountybrowser-automationbusiness-logic-flawsci/cd-securityclient-side-vulnerabilitiescode-analysiscybersecuritydeveloper-toolsdocker-sandboxdynamic-testingexploit-validationgenerative-aihttp-proxyinfrastructure-securityinjection-attacksllmopen-sourcepenetration-testingsecurity-testingserver-side-vulnerabilitiesstatic-analysisvulnerability-detection

Also in AI Agents

OpenHands/OpenHands

OpenHands is an AI-powered platform that automates software development tasks, enabling developers to code less and produce more by modifying code, running commands, browsing the web, and integrating APIs efficiently.

aaif-goose/goose

Goose is an open-source, native AI agent available as a desktop app, CLI, and API, designed for diverse tasks like code, research, writing, and automation, supporting over 15 LLM providers.

KeygraphHQ/shannon

Shannon is an autonomous AI pentester for web applications and APIs, analyzing source code, identifying attack vectors, and executing real exploits to prove vulnerabilities.

wshobson/agents

A comprehensive collection of 44 specialized AI subagents for Claude Code that enhance development workflows with domain-specific expertise across software development, infrastructure, security, data, and business domains.

agentscope-ai/agentscope

AgentScope is a transparent, modular, and customizable framework for building LLM-empowered multi-agent applications with real-time control and asynchronous execution.

iOfficeAI/OfficeCLI

OfficeCLI is an open-source command-line interface and API enabling AI agents to read, edit, and automate Word, Excel, and PowerPoint files without needing Office suite installations.

langchain-ai/deepagents

Deep Agents is an open-source agent harness built on LangChain and LangGraph that enables AI agents to plan, execute, and delegate complex long-horizon tasks using customizable tools, subagents, and human-in-the-loop workflows.

gastownhall/beads

Beads is a distributed graph issue tracker for AI agents, powered by Dolt, providing a persistent, structured memory to manage long-horizon tasks without losing context.