Beads - A memory upgrade for your coding agent

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

Anthropic's Interactive Prompt Engineering Tutorial

A Micro-benchmarking Framework for Python Type Inference Tools

Python wrapper for isl, an integer set library

Meta fork of the OG Jemalloc project

A JSON report of your mypy output that helps you push towards full type coverage of your project.

Lightweight coding agent that runs in your terminal

Print stack traces from running processes, or core files. Supports aarch64, x86_64, and i386

Project showing how to develop NKI kernels for Llama 3.2 1B inference

A high-throughput and memory-efficient inference and serving engine for LLMs

The web framework for content-driven websites. ⭐️ Star to support our work!

Port of OpenAI's Whisper model in C/C++

Scalene web GUI

structured outputs for llms

Add-in for Excel that finds formula errors

Production-ready platform for agentic workflow development.

A conda-smithy repository for scalene.

Excel add-in library

🙌 OpenHands: AI-Driven Development

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

A cross-platform command-line utility that creates projects from cookiecutters (project templates), e.g. Python package projects, C projects.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…