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
HXSecurity/DongTai-agent-java
DongTai-agent-java is a Java application probe designed for DongTai IAST (Interactive Application Security Testing) that collects method invocation data during the runtime of Java applications through dynamic hooks. It operates by rewriting class bytecode to gather necessary data, which is then sent to the dongtai-OpenAPI service for cloud-based processing to detect potential security vulnerabilities. The project is composed of several key components: agent.jar, which manages the agent's lifecycle and configuration; dongtai-core.jar, responsible for bytecode manipulation, data collection, preprocessing, reporting, and third-party component management; dongtai-inject.jar, which injects into the BootStrap ClassLoader to invoke data collection methods; and dongtai-servlet.jar, which captures application requests and responses for data display and request replay. This tool is particularly useful in DevOps environments, security testing before deployment, third-party component management, code auditing, and zero-day vulnerability discovery. It supports Java versions 1.8 and above and is compatible with popular middleware such as Tomcat, Jetty, WebLogic, WebSphere, and SpringBoot. The project provides a quick start guide and encourages contributions, with detailed instructions for forking, building with Maven, and running the agent alongside Java applications. Overall, DongTai-agent-java enhances application security by enabling real-time vulnerability detection through dynamic instrumentation and comprehensive data analysis.
https://github.com/HXSecurity/DongTai-agent-java
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.
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.
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.