PromtEngineer/localGPT
LocalGPT enables secure, private conversations with your documents on your local device using various open-source GPT models and embeddings without any data leaving your computer.
Awesome AI Agents › Post-Exploitation Agents
droe/xnumon
xnumon is a monitoring agent designed for macOS systems to detect and log malicious activities and potential intrusions. It aims to provide capabilities similar to the Windows sysmon tool, focusing on monitoring system activities across potentially large fleets of macOS devices. The project produces detailed system activity logs that include various event types such as process execution changes, process access manipulations, launch daemon or agent modifications, and network socket activities including listening, accepting, and connecting. xnumon provides rich context information including executable image hashes, code signature metadata, script shebang handling, and tracks process history through syscalls rather than relying solely on parent process IDs. This approach enhances the reliability of monitoring, especially for short-lived or self-modifying executables. The project supports different log formats and hash algorithms and includes suppression mechanisms to reduce log volume at the source. It is configurable and extensible with custom log drivers. xnumon requires macOS versions 10.12 through 10.14 for full support including its optional kernel extension, though it can operate without the kernel extension on later macOS versions. Due to changes in macOS security policies, kernel extensions and audit mechanisms have been deprecated or disabled in recent macOS versions, and xnumon currently lacks support for the newer Endpoint Security and Network Extension APIs, with no roadmap for this transition yet. The project includes an installer package that sets up the daemon, control utility, default configuration, and kernel extension, with detailed instructions for installation, configuration, and enterprise deployment. It also provides debugging tools and automated tests to ensure functionality. The project is open source under the Open Software License version 3.0 and is maintained by Daniel Roethlisberger.
https://github.com/droe/xnumon
Also in Post-Exploitation Agents
guardrails-ai/guardrails
Guardrails is a Python framework that enhances AI application reliability by providing input/output guards to detect and mitigate risks and generate structured data from large language models.
fr0gger/Awesome-GPT-Agents
A curated community-driven repository compiling diverse GPT agents specialized in offensive and defensive cybersecurity tasks, providing AI-powered tools for malware analysis, threat intelligence, vulnerability assessment, and more.
Ne0nd0g/merlin
Merlin is a cross-platform post-exploitation Command & Control server and agent supporting multiple protocols and advanced encryption for secure and flexible red teaming operations.
AprilNEA/AChat
AChat is an open-source, self-hosted AI platform designed for enterprises and teams, combining local processing with remote synchronization for centralized AI conversation management and collaboration.
sauravpanda/BrowserAI
BrowserAI is an open-source platform that enables running production-ready large language models and AI functionalities directly in the browser with WebGPU acceleration, ensuring privacy, offline capability, and no server infrastructure requirements.
HXSecurity/DongTai-agent-java
DongTai-agent-java is a Java application probe for DongTai IAST that collects runtime method invocation data via dynamic bytecode instrumentation to detect security vulnerabilities.
spellshift/realm
Realm is a scalable, reliable, and automated cross-platform Red Team engagement platform featuring a Pythonic DSL, multi-host management, and native Google Cloud integration for advanced offensive security operations.