A single archive of public exploit PoCs and vulnerability research
Technical principles related to large models
Optimize your code automatically with AI
SkyPilot: Run AI and batch jobs on any infra
A vector index built on TurboQuant, written in Rust with Python
Open-source, local-first memory for any tool-capable LLM agent
Good content deserves good paper
Module for automatic summarization of text documents and HTML pages
Framework for research and development of foundation models
Version-independent Codex instruction deployment
Open-source Agent OS for hardware intelligence
Open-source platform for building AI agents and serverless automation
Skills for threat modeling, scanning, triage, patching, etc.
The Modular Platform (includes MAX & Mojo)
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT method
Machine learning metrics for distributed, scalable PyTorch application
Automatically generate CLIs from absolutely any Python object
A research tool for visually exploring Bureau of Labor Statistics
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Infinite Worlds with Versatile Interactions
Temporal-Consistent Diffusion Model for Real-World Video
A full-stack codebase for training and evaluating speculative decoding
Claude Engineer is an interactive command-line interface (CLI)
A 7-layer memory operating system for Hermes Agent
AI-friendly PPT builder skill: 17 hand-polished Chinese PPTX templates