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
Ne0nd0g/merlin
Merlin is a sophisticated cross-platform post-exploitation Command & Control (C2) server and agent designed for advanced cybersecurity operations. Written in Go, it supports multiple C2 protocols including HTTP/1.1 clear-text, HTTP/1.1 over TLS, HTTP/2, HTTP/2 clear-text (h2c), and HTTP/3 (HTTP/2 over QUIC), providing flexible and secure communication channels between the server and agents. The system facilitates peer-to-peer (P2P) communication between agents over SMB, TCP, and UDP, enhancing its operational versatility. Merlin offers configurable data encoding and encryption transforms such as AES, Base64, gob, hex, JWE, RC4, and XOR, with advanced encryption schemes like PBES2_HS512_A256KW for secure key wrapping. It supports multiple authentication methods including none and OPAQUE, an asymmetric password-authenticated key exchange protocol, ensuring secure agent authentication. The platform also uses encrypted JWT for message authentication and configurable message padding to evade detection based on fixed message sizes. The tool allows execution of .NET assemblies either in-process or in sacrificial processes, execution of arbitrary Windows executables, and various shellcode execution techniques, making it highly adaptable for different post-exploitation scenarios. It integrates with tools like Donut, sRDI, and SharpGen for enhanced payload generation and execution. Merlin supports dynamic changes to the agent's JA3 hash for network fingerprinting evasion and integrates with the Mythic red teaming framework for collaborative operations. The project includes a command-line interface (merlin-cli) over gRPC for multi-user support and extensive documentation and community support through Slack and detailed wiki pages. Overall, Merlin is a powerful, flexible, and secure C2 framework designed for red teamers and penetration testers to conduct sophisticated post-exploitation activities across multiple platforms.
https://github.com/Ne0nd0g/merlin
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.
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.