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
sauravpanda/BrowserAI
BrowserAI is an open-source project that enables running production-ready large language models (LLMs) directly within a web browser environment. It supports local execution of various LLMs such as llama, deepseek-distill, kokoro, and others, leveraging WebGPU acceleration to achieve near-native performance without the need for server infrastructure. This approach ensures complete privacy as all processing happens locally on the user's device, and it also allows offline usage after the initial model download. The project is designed to be developer-friendly, offering a simple SDK that supports multiple AI engines and pre-optimized popular models for immediate use. Key features include seamless switching between different AI engines like MLC and Transformers, support for text generation with customizable options, structured output generation using JSON schemas, and integration of speech recognition and text-to-speech capabilities. The project also supports Web Workers to maintain UI responsiveness during heavy computations and includes built-in database support for storing conversations and embeddings. BrowserAI is ideal for web developers building AI-powered applications, companies requiring privacy-conscious AI solutions, researchers experimenting with browser-based AI, hobbyists exploring AI without infrastructure overhead, and no-code platform builders creating AI tools. It offers live demos for chat, voice chat, and text-to-speech functionalities, showcasing its versatility. The project roadmap includes phases for foundational features, advanced retrieval-augmented generation (RAG) capabilities, enhanced observability, and enterprise-grade security and analytics. Contributions are welcomed, and the project is licensed under the MIT License. BrowserAI requires modern browsers with WebGPU support and hardware capable of 16-bit floating point operations for certain models. Overall, BrowserAI provides a powerful, private, and accessible platform for running sophisticated AI models directly in the browser, eliminating server costs and infrastructure complexity while maintaining high performance and usability.
https://github.com/sauravpanda/BrowserAI
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.
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.