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
invariantlabs-ai/invariant
Invariant Guardrails is a sophisticated rule-based guardrailing system designed to enhance the security and robustness of AI applications powered by large language models (LLMs) or multi-component processors (MCPs). It acts as an intermediary layer between the AI application and the underlying LLM or MCP servers, enabling continuous monitoring and steering of agent behavior without requiring invasive changes to the application code. The system uses Python-inspired matching rules to define guardrails that detect and prevent malicious or unintended actions by AI agents. These rules can identify complex sequences of tool calls and message content patterns, allowing developers to enforce strict behavioral constraints on AI agents. For example, rules can prevent sending emails to unknown addresses or block certain phrases in messages. Guardrails integrates transparently as a proxy for MCP or LLM requests, automatically intercepting and evaluating tool calls against the defined rules. It offers both a gateway integration for automatic rule evaluation on each request and a programmatic interface for direct rule loading and evaluation within code. The project provides extensive documentation, including a guide for writing rules, a rule reference, and an interactive playground for testing rules. It also supports local policy evaluation and remote API-based evaluation with an API key. The system is designed to be extensible and user-friendly, with a standard library of operations to facilitate rule creation. Guardrails is open source and maintained by Invariant Labs, encouraging community contributions to improve security in AI agent development. Overall, Invariant Guardrails provides a powerful framework for developers to secure AI agents by defining contextual, customizable guardrails that ensure safe and predictable agent behavior.
https://github.com/invariantlabs-ai/invariant
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.