PyPI · npm100Exceptionalhealth index

deepset-ai/haystackOpen-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
Python★ 26.1KAug 5, 2026
PyPI99Exceptionalhealth index

huggingface/transformers🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Python★ 163.3K↓ 179M/moAug 4, 2026
PyPI · crates.io99Exceptionalhealth index

vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
Python★ 88.2KAug 4, 2026
PyPI98Exceptionalhealth index
Python★ 17.4K↓ 234.4K/moAug 12, 2026
PyPI98Exceptionalhealth index
Python · Jupyter Notebook★ 4,238Aug 12, 2026
PyPI · crates.io98Exceptionalhealth index

sgl-project/sglangSGLang is a high-performance serving framework for large language models and multimodal models.
Python★ 31.3K↓ 144M/moAug 4, 2026
PyPI97Exceptionalhealth index
pytorch/aoPyTorch native quantization and sparsity for training and inference
Python · C++★ 2,909Jul 21, 2026
PyPI94Exceptionalhealth index
Python★ 13.8K↓ 1.8M/moAug 27, 2026
npm94Exceptionalhealth index
JavaScript★ 3,127↓ 337M/moAug 4, 2026
npm94Exceptionalhealth index

aws-amplify/amplify-category-api The AWS Amplify CLI is a toolchain for simplifying serverless web and mobile development. This plugin provides functionality for the API category, allowing for the creation and management of GraphQL and REST based backends for your amplify project.
TypeScript★ 95↓ 4.6M/moAug 22, 2026
npm94Exceptionalhealth index

ueberdosis/hocuspocusThe Yjs CRDT WebSocket backend for conflict-free real-time collaboration in your app.
TypeScript★ 2,573↓ 15.9M/moSep 6, 2026
PyPI88Excellenthealth index
NVIDIA/cudnn-frontendcuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
Python · C++★ 886Jul 21, 2026
PyPI81Excellenthealth index

helicalAI/helicalA framework for state-of-the-art pre-trained bio foundation models on genomics and transcriptomics modalities.
Python★ 229↓ 1,236/moAug 22, 2026
PyPI80Excellenthealth index
Python★ 23Aug 1, 2026
Packagist78Goodhealth index
PHP★ 85↓ 299.4K/moJul 20, 2026
PyPI · crates.io77Goodhealth index

ahb-sjsu/turboquant-proConsumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matryoshka + TurboQuant (27x @ 99.8% recall@10), asymmetric K/V, CUDA/Triton kernels, vLLM plugin, replayable CI-gated claims. MIT.
Python★ 25↓ 277/moSep 5, 2026
Elixir★ 1,650↓ 13.1K/moJul 17, 2026
npm · crates.io · PyPI71Goodhealth index
Rust★ 13↓ 7,573/moSep 6, 2026
Python★ 300Jul 17, 2026
JavaScript★ 90↓ 2.9M/moSep 3, 2026
PyPI63Moderatehealth index
Python★ 24.7KAug 5, 2026
npm63Moderatehealth index
arkstack-hq/resoraA structured API response layer for Node.js and TypeScript with automatic JSON responses, collection support, and pagination handling.
TypeScript★ 0↓ 5,533/moJul 15, 2026
Hex · crates.io62Moderatehealth index
elixir-volt/oxc_exElixir bindings for the OXC JavaScript toolchain — parse, transform, and minify JS/TS via Rust NIFs
Elixir · Rust★ 18↓ 3,882/moJul 17, 2026
npm62Moderatehealth index
samchon/ttscA `typescript-go` toolchain for compiler-powered plugins + type-safe execution + 800x faster linter + codegraph reducing 90% AI tokens
Go · TypeScript★ 277Jul 18, 2026
PyPI59Moderatehealth index
ai-hypercomputer/jetstreamJetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
Python★ 451Jul 18, 2026
crates.io59Moderatehealth index
Rust★ 158↓ 8,548/moAug 6, 2026
npm59Moderatehealth index
TypeScript★ 0↓ 52.9K/moAug 1, 2026
PyPI57Moderatehealth index
google/jetstreamJetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
Python★ 451Jul 18, 2026
Packagist48Weakhealth index
PHP★ 64↓ 3,210/moJul 31, 2026
mprahboamey/atomoptical attention via wave interference in holographic crystals verified to float precision. the math is done. contribute to build the hardware.star it, fork it, break it.
Python★ 54Jul 17, 2026