kevingil
Follow
Stars
Embedded durable workflows for Golang similar to DTFx/Cadence/Temporal
Supercharge Your LLM with the Fastest KV Cache Layer
You like pytorch? You like micrograd? You love tinygrad! ❤️
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
NVIDIA Isaac Sim™ is an open-source application on NVIDIA Omniverse for developing, simulating, and testing AI-driven robots in realistic virtual environments.
A high-throughput and memory-efficient inference and serving engine for LLMs
A machine learning compiler for GPUs, CPUs, and ML accelerators
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
A RL scheduler demo using Temporal Cloud and Ray RLLib
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
The glamourous AI coding agent for your favourite terminal 💘
The open-source CapCut alternative
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
Produces a serialized hardware report of the physical infrastructure for automation
Ranking LLMs on agentic tasks
Our library for RL environments + evals
Example Drogon codebase containing real world examples (CRUD, auth, advanced patterns, etc) that adheres to the RealWorld API spec.
Simple, fast, safe, compiled language for developing maintainable software. Compiles itself in <1s with zero library dependencies. Supports automatic C => V translation. https://vlang.io
Specification and documentation for the Model Context Protocol
A fast type checker and language server for Python
A project I created using react to visualize sorting and pathfinding algorithms.