-
RaySearch Laboratories
- Stockholm
- @neuraloverflow
Lists (16)
Sort Name ascending (A-Z)
Starred repositories
Manage your dotfiles across multiple diverse machines, securely.
An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.
Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…
A creative coding project to create pieces inspired in neoplasticism art movement assumptions
Provides automated reverse engineering assistance through the use of local large language models (LLMs) on consumer hardware.
Tools for accelerating safe exploration research.
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️
Implementation of rectified flow and some of its followup research / improvements in Pytorch
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Implementation of a transformer for reinforcement learning using `x-transformers`
Pytorch implementation of Evolutionary Policy Optimization, from Wang et al. of the Robotics Institute at Carnegie Mellon University
atong01 / nflows
Forked from bayesiains/nflowsNormalizing flows in PyTorch
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Open-source Multi-agent Poster Generation from Papers
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
SYSTEM PROMPT TRANSPARENCY FOR ALL - CHATGPT, GEMINI, GROK, CLAUDE, PERPLEXITY, CURSOR, WINDSURF, DEVIN, REPLIT, AND MORE!
Collection of extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini
A benchmark for spaced repetition schedulers/algorithms
A TTS model capable of generating ultra-realistic dialogue in one pass.