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
spellshift/realm
Realm is a cross-platform Red Team engagement platform designed with a strong emphasis on automation, scalability, and reliability. It is built to support engagements of any size, including those involving thousands of beacons, making it highly performant and suitable for complex offensive security operations. The platform features Eldritch, a Pythonic Domain Specific Language (DSL) based on Google Starlark, which allows users to write clear, concise, and reusable code for offensive security tasks. Eldritch is natively compiled to Rust, providing a performant abstraction for low-level system interactions. Realm simplifies multi-host management, enabling operators to control agents across numerous machines simultaneously during engagements. It offers native integration with Google Cloud Platform (GCP), allowing users to leverage cloud scalability and services directly within their red team operations. The platform employs a stateless server architecture, supporting deployment in various environments through a stateless Docker container. The project consists of several components: the Agent (imix), written in Rust and supporting MacOS, Linux, and Windows, which handles long-running tasks and real-time output reading; the Server (tavern), which provides a web interface, group actions, a GraphQL backend for API access, OAuth login support, and cloud-native deployment capabilities; and the built-in interpreter (eldritch), which includes features like reflective DLL loading, port scanning, and remote execution over SSH. Realm prioritizes reliability through extensive testing and rigorous code review, ensuring operators can focus on engagements without spending excessive time troubleshooting. The platform is well-documented, with clear guides for getting started, deployment, and development contributions. It encourages community involvement through Discord and GitHub, offering support for bug reports, feature requests, and feedback. Overall, Realm is a comprehensive and robust framework tailored for red team professionals seeking an automated, scalable, and reliable offensive security toolset.
https://github.com/spellshift/realm
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.
romanz/trezor-agent
romanz/trezor-agent is a hardware-based SSH, GPG, and age agent that securely manages cryptographic keys on supported hardware devices, enhancing security by keeping keys off the computer.