Awesome AI Agents › Runtime Analysis Tools
Impacket is a comprehensive collection of Python classes designed for working with various network protocols. It provides low-level programmatic access to network packets and includes implementations for several protocols such as Ethernet, IP, TCP, UDP, ICMP, IGMP, ARP, and both IPv4 and IPv6. Notably, it offers high-level implementations for SMB versions 1 through 3 and MSRPC version 5, supporting multiple transports including TCP, SMB/TCP, SMB/NetBIOS, and HTTP. The library supports authentication mechanisms like Plain, NTLM, and Kerberos, accommodating passwords, hashes, tickets, and keys. It also includes partial or full implementations of numerous MSRPC interfaces such as EPM, DTYPES, LSAD, LSAT, NRPC, RRP, SAMR, SRVS, WKST, SCMR, BKRP, DHCPM, EVEN6, MGMT, SASEC, TSCH, DCOM, WMI, OXABREF, NSPI, and OXNSPI. Additionally, Impacket features portions of the TDS (MSSQL) and LDAP protocols. The library is maintained by Fortra's Core Security and was originally created by SecureAuth. It is designed to facilitate the construction and parsing of network packets from raw data, with an object-oriented API that simplifies working with complex protocol hierarchies. Impacket also provides a set of example tools demonstrating its capabilities. It supports Python versions 3.8 through 3.12 and can be installed via pipx or used within Docker containers. Impacket is intended primarily for security researchers and the community to accelerate research and educational activities related to networking protocols. It is not recommended for production use without proper security development practices. The project includes comprehensive testing using pytest, tox, and coverage tools, and is licensed under a modified Apache Software License. The repository encourages contributions and provides contact information for support and security inquiries.
https://github.com/fortra/impacket
PrivateGPT is a fully private, offline-capable AI platform that enables users to interact with their documents using Large Language Models through a comprehensive API and user-friendly interface, ensuring data never leaves the user's environment.
PentAGI is a fully autonomous AI-driven penetration testing system that integrates professional security tools, multi-agent AI collaboration, and scalable microservices architecture to deliver comprehensive and automated security assessments.
VIPER is a versatile and powerful red team platform that supports adversary simulation and cybersecurity assessments across multiple operating systems, enhanced with AI-driven automation and extensive post-exploitation capabilities.
MCP-Scan is a security tool that statically and dynamically scans MCP connections to detect and prevent vulnerabilities like prompt injections, tool poisoning, and cross-origin escalations, offering real-time monitoring and customizable guardrails for enhanced protection.
OpenRecall is a fully open-source, privacy-focused digital memory tool that captures and makes searchable your digital history through screenshots, supporting Windows, macOS, and Linux with local data storage and advanced semantic search capabilities.
MCP server that exposes Cheat Engine memory reading, scanning, disassembly and debugging to AI agent clients through roughly 180 tools over a named pipe or TCP relay.
Amon is a modern, open-source server monitoring platform designed to help users track and manage server performance and uptime effectively.
Cisco AI Defense security scanner that inspects MCP servers, tools, prompts and resources for malicious behavior using YARA rules, an LLM-as-a-judge engine and the Cisco AI Defense inspect API.