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.
Awesome AI Agents › Post-Exploitation Agents
PromtEngineer/localGPT
LocalGPT is an open-source project designed to enable users to chat with their documents locally on their own devices using GPT models, ensuring complete privacy as no data leaves the user's device. It supports a variety of open-source language models and embeddings, allowing users to integrate models from HuggingFace, GPTQ, GGML, and GGUF formats. The system uses LangChain tools to parse documents and create embeddings stored in a local vector database (Chroma), enabling efficient similarity searches to provide contextually relevant answers. LocalGPT offers a graphical user interface with two options: one that uses an API and another standalone interface based on Streamlit. It supports multiple hardware platforms including GPU (CUDA), CPU, Intel Gaudi HPU, and Apple MPS, making it versatile for different environments. The project emphasizes privacy and security by running all processes locally without sending data to external servers. It also features chat history within sessions and an API for building retrieval-augmented generation (RAG) applications. The repository includes detailed setup instructions, support for various document formats (txt, md, py, pdf, csv, xls, xlsx, docx, doc), and options for running via Conda or Docker. The project was inspired by privateGPT and leverages technologies like LangChain, HuggingFace LLMs, InstructorEmbeddings, LLAMACPP, ChromaDB, and Streamlit. It is suitable for users who want to securely interact with their documents using advanced language models without compromising data privacy.
https://github.com/PromtEngineer/localGPT
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.