Sub-millisecond VM sandboxes for AI agents via copy-on-write forking

FastAPI-compatible Python framework with Zig HTTP core; 7x faster, free-threading native

Type-safe, distributed orchestration of agents, ML pipelines, and real-time inference — in pure Python with async/await.

Nsight Python is a Python kernel profiling interface based on NVIDIA Nsight Tools

Rust based high-performance Apache Uniffle shuffle-server

JAX in JavaScript – ML library for the web, running on WebGPU & Wasm

Open-Source Frontier Voice AI

🚀2.3x faster than MinIO for 4KB object payloads. RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platfor…

Autocomp: Optimize any AI kernel, anywhere.

Read-through cache for object storage

Up to 100x faster strings for C, C++, CUDA, Python, Rust, Swift, JS, & Go, leveraging NEON, AVX2, AVX-512, SVE, GPGPU, & SWAR to accelerate search, hashing, sorting, edit distances, sketches, and m…

A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …

BARCH is a local l1 + remote l2 cache with valkey and multilanguage l1 interface providing low latency ordered access

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

Official inference framework for 1-bit LLMs

MLX: An array framework for Apple silicon

Nano vLLM

Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.

Format click help output nicely with rich.

🧱 secure, local, cross-platform and programmable sandboxes for AI agents

Achieve state of the art inference performance with modern accelerators on Kubernetes

A unified inference and post-training framework for accelerated video generation.

An extremely fast Python type checker and language server, written in Rust.

Programmatic sandboxing tool

A Datacenter Scale Distributed Inference Serving Framework

Hybrid in-memory and disk cache in Rust

FastAPI framework, high performance, easy to learn, fast to code, ready for production

A lightweight data processing framework built on DuckDB and 3FS.

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

DeepEP: an efficient expert-parallel communication library