Awesome AI Agents › Runtime Analysis Tools
Aetherius AI Assistant is a locally-operated, private AI assistant and multi-agent framework designed to provide users with a highly customizable and secure AI experience. It leverages open-source large language models (LLMs) and incorporates a sophisticated long-term memory system that mimics human memory for realistic recall and thought formation. The system uses Qdrant as a vector database to manage memory retrieval efficiently. Aetherius supports real-time data access, allowing it to search the web or user data in agent mode, thus providing up-to-date information beyond the base model's knowledge. The framework is modular and supports the creation of sub-agents tailored to specific tasks or use cases, which can also trigger Python scripts for extended functionality. This multi-agent capability enables complex workflows and enhances the assistant's versatility. Aetherius also includes features such as a reflective journal for personal feedback, learning tools for deep knowledge exploration, data analysis assistance, and content generation based on files or web scraping. Privacy and control are central to Aetherius, as it operates entirely locally, ensuring that no external entity can access or alter the user's data without consent. This approach addresses concerns about trust and data security prevalent in cloud-based AI solutions. The assistant integrates with various open-source LLMs through APIs like AetherNode, Oobabooga Text-UI, KoboldCpp, and can also interface with OpenAI's ChatGPT. The project is under active development, with ongoing refactoring to improve code structure and compatibility with modern models. Recent updates include enhanced prompt engineering, support for new LLM formats, integration of GPT-4 Vision for image understanding, and added tools for web scraping, text-to-speech, and voice input. The architecture supports distributed computing by offloading tasks to multiple machines, increasing computational efficiency. Aetherius is inspired by philosophical ideas about human cognition and free will, aiming to emulate human-like cognitive processes through advanced memory and agent orchestration. It is an experimental research project that encourages user involvement and adaptation through forks and backups due to its evolving nature and potential bugs.
https://github.com/libraryofcelsus/Aetherius_AI_Assistant
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.
Impacket is a Python library offering low-level programmatic access and implementations for various network protocols, focusing on security research and educational use.
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.