Awesome GitHub RepositoriesSensitive Data Identification

Ruflo is an AI agent orchestration platform and workflow automation tool designed to decompose high-level goals into executable action plans. It functions as a manager for multi-agent swarms, organizing autonomous entities into collaborative topologies that utilize shared consensus to complete complex tasks. The framework distinguishes itself through a retrieval-augmented generation layer and knowledge graphs for reasoning over linked data. It incorporates a trajectory-based learning loop that analyzes previous execution paths to refine cognitive patterns and improve future reasoning accuracy

Danswer is an LLM application framework and RAG engine that provides a self-hosted interface for connecting large language models to private data. It serves as an enterprise AI chat interface and agent orchestrator, enabling the creation of specialized assistants with custom instructions and knowledge bases. The platform differentiates itself through an observability dashboard for tracking query history and token consumption, as well as a white-labeled interface for customized branding. It includes a multi-step research workflow for producing long-form reports and a sandboxed environment for

This project is a state management inspector and debugging tool for Redux. It provides a browser-based interface for inspecting and modifying application state and actions in real time, serving as an action logger and time travel debugger to troubleshoot application logic. The tool allows users to navigate a chronological history of state changes to replay previous versions of the application or skip specific actions. It also functions as a remote monitoring bridge, streaming Redux state and actions from non-browser environments to a centralized debugging interface. The capability surface in

k8sgpt es un conjunto de herramientas centradas en Kubernetes diseñadas para la depuración impulsada por IA, diagnósticos de clúster y auto-reparación. Funciona como un analizador y depurador automatizado que utiliza modelos de lenguaje grandes (LLM) para explicar errores de clúster, sugerir pasos de remediación e identificar fallos de recursos. El proyecto se distingue por un framework de análisis extensible que admite plugins de diagnóstico personalizados y un servidor de Model Context Protocol, que expone los diagnósticos del clúster como herramientas para asistentes de IA. Incluye un agente de auto-reparación capaz de generar y aplicar automáticamente correcciones para anomalías detectadas, así como middleware de anonimización de datos para enmascarar información sensible antes de que se transmita a proveedores de IA externos. El conjunto de herramientas cubre una amplia gama de capacidades operativas, incluyendo monitoreo continuo de salud mediante un operador, auditoría de cumplimiento frente a motores de políticas y orquestación multi-clúster para identificar patrones de fallo generalizados. También proporciona características de observabilidad como exportación de resultados de diagnóstico, integración de métricas de observabilidad y resolución de problemas de fallos en pods.

pyWhat is a Python-based data extraction tool designed to scan files and text for sensitive identifiers, credentials, and network artifacts using regular expressions. It functions as a pattern matching engine and PII scanner capable of identifying personal identifiers and sensitive data patterns across directories and binary files. The project specializes in the identification of unknown data formats through file signatures and the extraction of high-value identifiers, such as URLs, IP addresses, and phone numbers, from network capture files. It utilizes a rarity-based filtering system and sp

Presidio is a PII detection and anonymization framework designed to identify and mask personally identifiable information in text. It functions as a PII recognition pipeline and a data masking engine, using a combination of machine learning, regular expressions, and rule-based logic to locate sensitive entities. The system acts as an NER model orchestrator, allowing for the integration of external named entity recognition models and PII detectors to support multi-language privacy scrubbing. It employs a plugin-based recognizer architecture that can be extended with custom recognizers, deny-li

Proxyman is a cross-platform HTTP debugging proxy that captures, inspects, and modifies HTTP, HTTPS, and WebSocket traffic. It functions as a man-in-the-middle proxy, decrypting SSL/TLS traffic to allow real-time inspection and modification of encrypted requests and responses. The tool is designed for debugging web and mobile applications, with capabilities for API mocking and simulation, scriptable traffic modification, and team collaboration on network logs. What distinguishes Proxyman is its deep integration with mobile and cross-platform development workflows. It provides automated certif

Superagent is a framework for AI assistant orchestration and agent security. It provides the tools to build intelligent assistants that integrate external APIs and maintain conversation memory to automate complex tasks. The project focuses on AI agent security through adversarial testing, red teaming, and the detection of prompt injections and malicious tool calls. It includes automated vulnerability patching, which scans codebases and configurations for security flaws and generates pull requests with fixes. The platform supports retrieval augmented generation by connecting language models t

Superagent is an AI safety platform that protects applications from prompt injections, data leaks, and harmful outputs through built-in guardrails. It functions as a prompt injection detection system, data redaction tool, and red team testing tool, automatically removing personally identifiable information and protected health data from AI inputs and outputs while scanning image uploads with vision AI to detect visual prompt injection attacks before processing. The platform routes every prompt through a sequential pipeline of safety checks including injection detection, data redaction, and co

VCR is a Ruby library that records and replays HTTP interactions during test runs, storing them in serialized cassette files. It captures real HTTP requests and responses, then serves those recorded responses instead of making actual network calls, enabling fast and deterministic test suites that work offline. The library provides configurable request matching, allowing comparisons based on method, URI, host, path, body, or headers to find the correct recorded response. It supports scheduled cassette re-recording to automatically refresh stored interactions at a configurable interval, keeping

OpenChat es una plataforma de gestión de chatbots de IA utilizada para construir, desplegar y gestionar agentes personalizados impulsados por modelos de lenguaje grandes. Sirve como una suite de soporte al cliente omnicanal que integra automatización de modelos de lenguaje con canales de comunicación incluyendo correo electrónico, SMS, redes sociales y voz. La plataforma cuenta con un integrador de base de conocimientos de generación aumentada por recuperación (RAG) que ingiere documentos, sitios web y bases de código para proporcionar respuestas conscientes del contexto. Incluye una capa de privacidad dedicada para la detección y eliminación de información personal y de salud sensible para mantener el cumplimiento normativo. El sistema proporciona un API gateway con una interfaz REST y webhooks para gestión programática, junto con un gateway de mensajes multicanal. También incluye herramientas para sincronizar datos externos de CRM y helpdesk y un widget impulsado por JavaScript para incrustar interfaces de chat en sitios web externos.

Este proyecto es un stack de monitoreo de IA autohospedado que funciona como una plataforma de observabilidad de LLM, framework de evaluación de IA y analizador de trazas de OpenTelemetry. Está diseñado para capturar y analizar trazas, sesiones y telemetría de LLM para monitorear el rendimiento de agentes de IA. La plataforma se distingue como un servidor de Model Context Protocol, exponiendo funciones de espacio de trabajo como herramientas para agentes de codificación de IA. Permite la conversión de trazas de producción fallidas en conjuntos de datos de prueba para pruebas de regresión y utiliza clustering de sesiones basado en semántica para descubrir patrones de comportamiento de usuario emergentes. El sistema cubre áreas de capacidad amplias, incluyendo recolección de telemetría para rutas de ejecución de agentes, puntuación de evaluación automatizada para tráfico en vivo y búsqueda semántica para aislar patrones de interacción. También proporciona alertas para regresiones de señal, análisis de comportamiento para fallos de herramientas y redacción de PII para datos de telemetría. El software puede desplegarse en infraestructura privada como una instalación de un solo host o como un cluster escalable utilizando Docker Compose, Kubernetes o Helm charts.

This project is a collection of structured study notes and conceptual breakdowns designed for the AWS Certified Cloud Practitioner exam. It serves as a technical reference and study guide, organizing cloud service details and architectural principles to assist in certification preparation. The knowledge base is built using markdown files and includes curated cheat sheets and interactive mind-map visualizations. These tools map complex certification topics into visual hierarchies to enable drill-down study paths and rapid revision. The materials cover a wide range of cloud capabilities, inclu

ruby_llm is an LLM integration framework and AI agent orchestrator designed to connect applications to multiple large language model providers through a unified interface. It serves as a toolkit for building autonomous assistants with custom personas, managing structured output via JSON schemas, and implementing vector embedding engines for semantic search. The project distinguishes itself as an observability suite and multimodal toolkit. It provides specialized capabilities for tracking token usage, calculating model costs, and tracing workflows via OpenTelemetry, while supporting the proces

This project is a Git-based AI session tracker and context manager designed to record AI agent interactions, transcripts, and tool usage directly into Git repositories. It functions as a system for capturing and indexing the reasoning behind code changes, linking AI prompts and responses to specific code commits to preserve developer intent. The tool distinguishes itself by using Git as a primary storage layer for session metadata, utilizing shadow branches and checkpoints to track agent state without polluting the main commit log. It includes specialized capabilities for auditing AI contribu

LLM Guard is a security firewall and guardrail framework designed to scan and sanitize inputs and outputs for large language models. It functions as a proxy gateway and security layer to block prompt injections, toxicity, and sensitive data leakage while ensuring that model interactions remain compliant with organizational policies. The system distinguishes itself through a modular scanner pipeline that utilizes local model orchestration to eliminate external network dependencies. It supports real-time security filtering via streaming chunk analysis and implements a fail-fast execution model

Dynamiq is an agent development platform designed for building, orchestrating, and monitoring autonomous agents. It provides a framework for constructing complex, multi-step workflows using a graph-based engine that supports conditional branching, feedback loops, and iterative task execution. The platform distinguishes itself through its focus on secure, private infrastructure, allowing for the deployment of language models and orchestration services within virtual private clouds to maintain data sovereignty. It integrates retrieval-augmented generation pipelines to ground model responses in