Kade Heckel's starred repositories
Scrapegraph-ai
Python scraper based on AI
lm-evaluation-harness
A framework for few-shot evaluation of language models.
promptfoo
Test your prompts, agents, and RAGs. Redteaming, pentesting, vulnerability scanning for LLMs. Improve your app's quality and catch problems. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.
executorch
On-device AI across mobile, embedded and edge for PyTorch
distilabel
⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.
granite-code-models
Granite Code Models: A Family of Open Foundation Models for Code Intelligence
DataDreamer
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
prometheus-eval
Evaluate your LLM's response with Prometheus and GPT4 💯
awesome-rust-security
Curated list of awesome projects and resources related to Rust and computer security
Awesome-LLM4Cybersecurity
An overview of LLMs for cybersecurity.
Shellcode_IA32
Shellcode_IA32 is a dataset consisting of challenging but common assembly instructions, collected from real shellcodes, with their natural language descriptions. The dataset can be used for neural machine translation tasks to automatically generate software exploits from natural language.
ExploitFlow
A library to produce cybersecurity exploitation routes (exploit flows). Inspired by TensorFlow.
Cyber-Range-Framework
Extendable Cyber Range Framework that easily deploys scenarios that aim to improve the knowledge of the cyber defense workforce. It uses an approach heavily reliant on DevOps and IaC and is featured with Linux and Windows-based vulnerabilities related to Apache Log4j, Ransomware and Active Directory.
ExploitGen
ExploitGen is a template-augmented Exploit Code generation method based on CodeBERT, which accepted in JSS.
violent-python
This repo contains a manually curated dataset, where a sample contains a piece of Python code from an offensive software, and its corresponding description in natural language (plain English).