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
guardrails-ai/guardrails
Guardrails is a Python framework designed to enhance the reliability and safety of AI applications, particularly those utilizing large language models (LLMs). It achieves this by implementing input and output guards that detect, quantify, and mitigate various types of risks associated with AI-generated content. The framework provides a comprehensive suite of validators, accessible through the Guardrails Hub, which can be combined to create custom guards tailored to specific validation needs. These guards intercept and validate the inputs and outputs of LLMs to ensure compliance with predefined rules and safety standards. The project supports structured data generation from LLMs by leveraging Pydantic models, enabling developers to define the expected output schema and validate the LLM responses accordingly. This structured approach helps in maintaining data integrity and consistency when interacting with AI models. Guardrails also offers a server mode, allowing it to be deployed as a standalone service with a REST API, facilitating easier integration and deployment in production environments. Installation is straightforward via pip, and the framework includes a command-line interface for configuring and managing guardrails from the Guardrails Hub. The hub itself is a curated collection of pre-built validators addressing common risks such as toxic language, competitor mentions, and regex pattern matching. Users can install these validators and combine them to enforce multiple rules simultaneously. Guardrails is actively maintained, with features like the Guardrails Index benchmark that compares the performance and latency of various guardrails, helping users choose the most effective validators for their applications. The project emphasizes safety, reliability, and structured output generation, making it a valuable tool for developers building AI applications that require robust content validation and risk mitigation.
https://github.com/guardrails-ai/guardrails
Also in Post-Exploitation Agents
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.
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.