A library for easily evaluating machine learning models and datasets
Universal SEO skill for Claude Code
Advanced LLM-powered brute-force tool combining AI intelligence
Library to facilitate federated learning research
Open-source AI hackers to find and fix your app’s vulnerabilities
A Python library powered by Language Models (LLMs)
An Efficient Agentic Model for Computer Use
Open Agent Harness with a built-in personal agent, Ohmo
An end-to-end Data Scientist
Language Model Reinforcement Learning Environments frameworks
AI agent framework for black-box security testing
How Claude Fable 5 worked, distilled into skills
A benchmark built to evaluate and improve agent capabilities
Open-source MCP server that gives your coding agent
Full-stack AI Red Teaming platform
Deep Research framework, combining language models with tools
OpenCompass is an LLM evaluation platform
Public opinion analysis system
Curated collection of Amazing Python scripts
OpenFieldAI is an AI based Open Field Test Rodent Tracker
Provide an input CSV and a target field to predict, generate a model
Code for "Improving Language Understanding by Generative Pre-Training"
The Pokemon Go Bot, baking with community
Technologies for automating food production on various scales