Collected molecules will appear here. Add from search or explore.
Search and evaluate GitHub repos, arXiv papers, and HuggingFace models — scored for defensibility, threat profile, and composability.
High-performance, distributed SQL query engine designed for fast interactive analytics on large-scale datasets from multiple sources.
Official NVIDIA high-performance inference optimization library for Large Language Models on NVIDIA hardware, providing advanced kernels, quantization, and orchestration.
Industrial-grade whole-building energy and water consumption simulation engine used for architectural design and building code compliance.
Standardized library for applying parameter-efficient fine-tuning (PEFT) techniques like LoRA, QLoRA, and Prefix Tuning to large pre-trained models.
Distributed training and inference optimization library that enables scaling deep learning models to trillions of parameters through memory-saving techniques like ZeRO and various forms of parallelism.
Model definition, loading, and fine-tuning framework for transformer-based architectures across text, vision, audio, and multimodal domains with unified APIs for inference and training.
A high-performance LLM inference and serving framework that optimizes structured generation and throughput via RadixAttention and a specialized domain-specific language.
Official Go implementation of the Model Context Protocol (MCP) for building interoperable AI clients and servers that connect LLMs to data sources and tools.
Official Python implementation of the Model Context Protocol (MCP), enabling standardized communication between AI models and local or remote data sources and tools.
Scalable open-source IoT platform for device connectivity, data collection, processing, and visualization via various protocols (MQTT, CoAP, HTTP).
A highly modular, small-footprint WebAssembly (Wasm) runtime designed for resource-constrained devices, embedded systems, and trusted execution environments (TEE).
An open-source, neutral, and modular real-time operating system (RTOS) designed specifically for IoT applications with a wide range of hardware support.
Distributed, high-performance MQTT message broker designed for massive scale IoT and IIoT connectivity.
High-throughput, memory-efficient LLM inference and serving engine with optimized batching, KV-cache management, and multi-GPU/hardware support
Workflow orchestration platform for authoring, scheduling, and monitoring data pipelines and ETL processes
Official TypeScript implementation of the Model Context Protocol (MCP), providing a standardized interface for LLMs to interact with external tools, data sources, and prompts.
Production-grade WebAssembly runtime with JIT compilation, sandboxing, and WASI support for executing WASM modules across multiple platforms
LLM application framework providing abstractions for chaining language models, memory, retrieval, and agents with pluggable integrations across 100+ external services
High-performance Layer 1 blockchain platform using an object-centric data model and the Move programming language for parallel transaction execution.
Open-source autopilot flight control software stack for multirotor, fixed-wing, and VTOL unmanned aerial vehicles (UAVs), providing real-time control algorithms, sensor fusion, navigation, and hardware abstraction across diverse embedded platforms.
Create a free account to unlock more
