Starred repositories
Allows you to emulate an Android native library, and an experimental iOS emulation
Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
This repository contains low-bit quantization papers from 2020 to 2026 on top conference.
Multi-agent racing tournament on MetaDrive
learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen
mHC-lite: You Don’t Need 20 Sinkhorn-Knopp Iterations
A minimal PyTorch re-implementation of Qwen 3.5
Claude code to help you do lead research and qualification
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
Sandbox your local AI agents so they can read/write only what they need
An agentic skills framework & software development methodology that works.
Re-imagining code collaboration for humans and agents
A lightweight, lightning-fast, in-process vector database
This application collects Grad Schools data from https://www.usnews.com and gives output in an excel file
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Enable Opencode to authenticate against Antigravity (Google's IDE) via OAuth so you can use Antigravity rate limits and access models like gemini-3-pro and claude-opus-4-5-thinking with your Google…
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
OpenF1 API - Real-time and historical Formula 1 data
An interactive Formula 1 race visualisation and data analysis tool built with Python! 🏎️
Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.
Detection of Google SynthID watermarks using frequency-domain feature engineering in the LAB a channel. A lightweight, interpretable signal processing approach
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.