Awesome AI Agents › Runtime Analysis Tools
LiveRecall is an open-source software project designed as an alternative to Microsoft's Recall, focusing on capturing and recalling screen snapshots through natural language queries. The core functionality of LiveRecall involves continuously capturing screenshots of the user's screen whenever changes are detected or at regular intervals. These snapshots are then indexed using semantic search technology, allowing users to retrieve specific images by describing them in natural language. This feature is particularly useful for recalling visual information such as an item seen online or a message received, without needing to remember exact details like the source or platform. The project emphasizes privacy and security by encrypting all captured images, ensuring that sensitive visual data remains protected. Although the current encryption is simple, plans for enhanced encryption methods are underway. LiveRecall is community-driven and fully transparent, encouraging contributions and improvements from developers worldwide. Installation and usage are straightforward, with instructions provided for cloning the repository, setting up dependencies, and launching the application via a web interface. Users interact with LiveRecall through a simple GUI where they can start and stop the capture process and perform searches using natural language queries. The project currently does not use a database to reduce complexity but plans to add support for PostgreSQL in the future. Additional features planned include performance improvements, a snapshot timeline, optimized storage, better encryption, and a more refined graphical user interface. The project also addresses privacy concerns explicitly, with documentation available for users to understand how their data is handled. Overall, LiveRecall offers a practical and secure tool for users who want to keep track of visual information on their screens and retrieve it easily using intuitive search methods, making it a valuable utility for personal productivity and information management.
https://github.com/VedankPurohit/LiveRecall
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.