#
Lists (7)
Starred repositories
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Tiny MCP server with cryptography tools, sufficient to establish end-to-end encryption between LLM agents
OctoTools: An agentic framework with extensible tools for complex reasoning
Rust tool to detect cell site simulators on an orbic mobile hotspot
AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/pAbnFJrkgZ
Inofficial Qualcomm Firehose / Sahara / Streaming / Diag Tools :)
A curated list of awesome baseband research resources
A code skeleton of Samsung's Shannon5123 5G baseband modem.
WHAD protocol: an open protocol for wireless hacking tools
A U-Boot hacking toolkit for security researchers and tinkerers
QCSuper is a tool communicating with Qualcomm-based phones and modems, allowing to capture raw 2G/3G/4G radio frames, among other things.
Deploy stealthy reverse shells using advanced process hollowing with GhostStrike – a C++ tool for ethical hacking and Red Team operations.
simplest example for programming PRU on PocketBeagle
An intuitive LLM prompting framework for multifunctional agents, by explicitly constructing a complex "thought process" from simple natural language prompts.
IntroVirt is an guest introspection library for KVM
Implementing the 4 agentic patterns from scratch
Whistleblower is a offensive security tool for testing against system prompt leakage and capability discovery of an AI application exposed through API. Built for AI engineers, security researchers …
My personal work with Copilot for Security
AI in Pentest: Automated Web Scanner with AI Integration
get things from one computer to another, safely
Second Level MetaCognition Controlling Agent for LLAMA-3.1 over VLLM (Or OpenAI or whatever)
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
A tool that takes over Windows Updates to craft custom downgrades and expose past fixed vulnerabilities
Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]