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
romanz/trezor-agent
The project "romanz/trezor-agent" is a hardware-based SSH, GPG, and age agent that leverages various hardware security devices to securely manage cryptographic keys. Instead of storing private keys on a computer, this project generates and stores keys directly on supported hardware devices, ensuring that the keys never leave the device. This approach enhances security by preventing key exposure on potentially vulnerable computers. The project supports multiple hardware devices including TREZOR One, TREZOR Model T, Keepkey, Blockstream Jade, Ledger Nano S, and OnlyKey. Users can perform cryptographic operations such as signing emails, git commits, and software packages, managing passwords with tools like pass and passage, authenticating web tunnels and file transfers, and more. The repository contains source code for a shared library called libagent and several agents tailored to interact with different hardware devices, such as trezor-agent, ledger_agent, jade_agent, keepkey_agent, and onlykey-agent. Comprehensive documentation is provided, including installation instructions, usage guides for SSH, GPG, and age, configuration for PIN entry programs, and guidance for Windows users. The project also includes links to blog posts that discuss firmware updates enabling SSH login, GPG signing, and other advanced features for supported devices. This project is particularly useful for users who prioritize security and want to leverage hardware wallets for cryptographic operations, reducing the risk of key compromise by keeping private keys isolated on hardware devices.
https://github.com/romanz/trezor-agent
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.