Awesome AI Agents › Runtime Analysis Tools
PrivateGPT is a production-ready AI project designed to enable users to interact with their documents using the power of Large Language Models (LLMs) while ensuring complete privacy. The key feature of PrivateGPT is that it operates 100% privately, with no data leaving the user's execution environment, making it ideal for privacy-sensitive domains such as healthcare and legal sectors. It supports offline usage, allowing users to ask questions about their documents without requiring an internet connection. The project provides a comprehensive API that follows and extends the OpenAI API standard, supporting both normal and streaming responses. The API is divided into two main parts: a high-level API that abstracts the complexity of a Retrieval Augmented Generation (RAG) pipeline, handling document ingestion, parsing, splitting, metadata extraction, embedding generation, and storage; and a low-level API for advanced users to implement custom pipelines, including embeddings generation and contextual chunk retrieval. PrivateGPT includes a Gradio UI client for testing the API and offers various tools such as bulk model download scripts, ingestion scripts, and document folder monitoring. The architecture is built using FastAPI and leverages LlamaIndex for the RAG pipeline, with a modular design that allows easy extension and adaptation. Key architectural principles include dependency injection, decoupling components, and simplicity. The project is actively maintained with a focus on evolving into a gateway for generative AI models and primitives, making it easier for developers to build private, context-aware AI applications. It is supported by partners like Qdrant, Fern, and LlamaIndex, and encourages community contributions through a public project board and Discord channel. Overall, PrivateGPT addresses the critical need for privacy in AI applications by providing a robust, extensible, and fully private platform for document-based AI interactions.
https://github.com/zylon-ai/private-gpt
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.
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.