GPU Engineering for AI Systems

K8s LoadBalancer service fullfilled by Fly Machine + frp. 🚀

High-efficiency LLM inference engine in C++/CUDA. Run Llama 70B on RTX 3090.

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Harbor is a framework for running agent evaluations and creating and using RL environments.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Python frame stack sampler for CPython

Build text-to-image generative AI models from scratch with Python and PyTorch. Focus on two methods: Diffusion models, which iteratively denoise to generate image conditional on text prompt, and vi…

Just enough Kubernetes for you to fly

Embeddable library or single binary for indexing and searching 1B vectors

Serverless full-text search with Cloudflare Workers, WebAssembly, and Roaring Bitmaps

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!

Renderer for the harmony response format to be used with gpt-oss

Open source, zero webhooks payment provider

Simple and efficient DeepSeek V3 SFT using pipeline parallel and expert parallel, with both FP8 and BF16 trainings

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

All-in-one text de-duplication

Agent Engineering course files

An extremely fast Python package and project manager, written in Rust.

Face detection and biometric identification in the browser

A toolkit enabling delightful AI interactions across platforms

nyc is so back

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.