Search Results for "runtime library"
Sort By:
Showing 47 open source projects for "runtime library"
View related business solutions-
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
ByteHook
ByteHook is an Android PLT hook library
ByteHook is a ByteDance-hosted project whose name suggests a hooking or instrumentation library, likely used for hooking system calls or API calls for monitoring, sandboxing or instrumentation. The repository appears to aim at low-level hooking/injection capabilities, perhaps to support runtime introspection, behavioral monitoring, or hooking-based instrumentation (e.g. for security, tracing, sandboxing, or debugging). Because hooking is a common technique for intercepting library or system calls, Bhook likely provides abstractions to inject hooks into processes or libraries, enabling custom behavior monitoring or modification — which can be useful for building security tools, monitoring frameworks, or dynamic instrumentation. ... -
2
AsmJit
Low-latency machine code generation
AsmJit is a low-level code generation library designed for dynamically creating machine code at runtime, enabling just-in-time (JIT) compilation for performance-critical applications. It provides a high-level API that abstracts away the complexity of writing raw assembly while still allowing fine-grained control over instruction generation. The library supports multiple architectures, including x86 and x64, making it versatile for cross-platform development. -
3
whisper.cpp
Port of OpenAI's Whisper model in C/C++
whisper.cpp is a lightweight, C/C++ reimplementation of OpenAI’s Whisper automatic speech recognition (ASR) model—designed for efficient, standalone transcription without external dependencies. The entire high-level implementation of the model is contained in whisper.h and whisper.cpp. The rest of the code is part of the ggml machine learning library. The command downloads the base.en model converted to custom ggml format and runs the inference on all .wav samples in the folder samples.... -
4
ort
Fast ML inference & training for ONNX models in Rust
ort is a high-performance Rust library that provides bindings to ONNX Runtime, enabling developers to run machine learning inference and training workflows directly within Rust applications using the standardized ONNX model format. It is designed to bridge the gap between modern machine learning frameworks and systems programming by offering a safe, ergonomic API for executing models originally built in ecosystems like PyTorch, TensorFlow, or scikit-learn. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
Pi Agent
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI
Pi is an open-source AI agent toolkit and coding agent framework designed to help developers build, run, and extend intelligent AI-powered workflows. Developed by Earendil Works, the project includes a coding agent CLI, unified multi-provider LLM API, agent runtime, terminal UI library, and web UI components. Pi supports multiple AI providers such as OpenAI, Anthropic, and Google through a single consistent API layer, making it easier to integrate different models into applications and agents. The framework is built around extensibility, allowing developers to create custom tools, workflows, and autonomous coding experiences. ... -
6
VibeTensor
Our first fully AI generated deep learning system
VibeTensor is a groundbreaking open-source research system software stack for deep learning that was uniquely generated almost entirely by AI coding agents under guided human supervision, demonstrating a new frontier in AI-assisted software engineering. It implements a PyTorch-style eager tensor library with a modern C++20 core that supports both CPU and CUDA backends, giving it the ability to manage tensors, automatic differentiation (autograd), and complex computation flows similar to mainstream frameworks. What makes VibeTensor remarkable is that every major component, from core libraries and dispatch systems to CUDA runtime support, caching allocators, and language bindings, was created and validated by coding agents using automated builds and tests rather than manual line-by-line human coding. ... -
7
oneDNN
oneAPI Deep Neural Network Library (oneDNN)
This software was previously known as Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN) and Deep Neural Network Library (DNNL). oneAPI Deep Neural Network Library (oneDNN) is an open-source cross-platform performance library of basic building blocks for deep learning applications. oneDNN is part of oneAPI. The library is optimized for Intel(R) Architecture Processors, Intel Processor Graphics and Xe Architecture graphics. oneDNN has experimental support for the... -
8
React Native ExecuTorch
Declarative way to run AI models in React Native on device
React Native ExecuTorch is a library for running AI models directly on mobile devices from React Native. It is powered by ExecuTorch and provides a declarative approach to on-device model execution. The project supports a range of AI use cases, including large language models, computer vision, OCR, object detection, speech processing, segmentation, and embeddings. It helps React Native developers use local AI capabilities without needing deep native programming or machine learning... -
9
pyttsx3
Offline Text To Speech synthesis for python
pyttsx3 is an offline text-to-speech library for Python that wraps native speech engines instead of calling cloud APIs. It is designed to work entirely without an internet connection, making it suitable for local automation, kiosks, accessibility tools, and embedded applications. On Windows it uses SAPI5, on Linux it typically uses eSpeak or eSpeak-NG, and on macOS it can use NSSpeechSynthesizer or AVSpeechSynthesizer, giving it broad cross-platform compatibility. The library exposes a... -
One Monitoring Tool for IT, OT and Cloud | Free TrialModern infrastructure spans data centers, cloud platforms and factory floors, and every blind spot between them is a risk. PRTG supports SNMP, WMI, SSH and other standard protocols to monitor IT, OT and hybrid environments through one customizable dashboard. Build the views your team needs, from network health to application performance, without switching tools. Try PRTG free for 30 days now.
-
10
lmstudio.js
LM Studio TypeScript SDK
lmstudio.js is the official TypeScript and JavaScript SDK that enables developers to programmatically interact with LM Studio’s local AI runtime. The library exposes the same capabilities used internally by the LM Studio desktop application, allowing external apps to load models, run inference, and build autonomous AI workflows. It is designed to simplify the creation of local AI tools by handling complex concerns such as dependency management, hardware compatibility, and model configuration. ... -
11
DeepGEMM
Clean and efficient FP8 GEMM kernels with fine-grained scaling
DeepGEMM is a specialized CUDA library for efficient, high-performance general matrix multiplication (GEMM) operations, with particular focus on low-precision formats such as FP8 (and experimental support for BF16). The library is designed to work cleanly and simply, avoiding overly templated or heavily abstracted code, while still delivering performance that rivals expert-tuned libraries. -
12
TurboFieldfare
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
TurboFieldfare is a custom Swift and Metal runtime for running the instruction-tuned Gemma 4 26B-A4B model on Apple Silicon Macs with limited memory. Instead of loading the entire model, it keeps the shared core and KV cache in RAM while streaming only the routed experts required for each token from SSD. This approach reduces active memory use to roughly 2 GB while the installed model occupies about 14.3 GB of storage. -
13
Vercel AI SDK
Build AI-powered applications with React, Svelte, Vue, and Solid
The Vercel AI SDK is a library for building AI-powered streaming text and chat UIs. -
14
Google Antigravity SDK
Python library for building agents that leverages Google Antigravity
Google Antigravity SDK for Python is a Python library for building AI agents powered by Antigravity and Gemini. It provides a secure, scalable, and stateful infrastructure layer so developers can focus on agent behavior instead of manually implementing the full agent loop. The SDK includes a high-level Agent class for quick setup, as well as lower-level conversation and connection abstractions for more controlled workflows. -
15
rust-bert
Rust native ready-to-use NLP pipelines and transformer-based models
...It allows developers to run state-of-the-art NLP models like BERT, GPT-2, and DistilBERT directly within Rust applications while maintaining high performance and memory efficiency. The library integrates with Rust machine learning infrastructure using crates such as tch-rs and ONNX Runtime for model execution. It also includes tokenization utilities, model architectures, and task-specific pipelines that simplify the development of NLP applications. Because Rust is known for its safety and performance, this project enables developers to deploy modern NLP models in production systems written in Rust. -
16
TreeQuest
A Tree Search Library with Flexible API for LLM Inference-Time Scaling
TreeQuest, developed by SakanaAI, is a versatile Python library implementing adaptive tree search algorithms—such as AB‑MCTS—for enhancing inference-time performance of large language models (LLMs). It allows developers to define custom state-generation and scoring functions (e.g., via LLMs), and then efficiently explores possible answer trees during runtime. With support for multi-LLM collaboration, checkpointing, and mixed policies, TreeQuest enables smarter, trial‑and‑error question answering by leveraging both breadth (multiple attempts) and depth (iterative refinement) strategies to find better outputs dynamically -
17
FLUX.2-klein-4B
Flux 2 image generation model pure C inference
...Because the implementation is in plain C and focuses on data locality and vectorized operations, flux2.c can be integrated into performance-critical code paths where control over memory layout and execution behavior matters, such as GPU kernels, embedded systems, or custom ML runtime engines. -
18
WASTE
Run the full 2.78-trillion-parameter Kimi K3 model
...A bounded cache reuses recently needed experts, while lookahead routing begins disk reads before the next layer requires them. Its main target is the full 2.78-trillion-parameter Kimi K3 model, including multimodal image input. The engine has no third-party runtime dependency on its CPU inference path and exposes both a CLI and C library. An optional server provides an OpenAI-compatible chat API with streaming, tools, structured output, and image support. Validation compares layers, logits, vision output, and prompt rendering against reference implementations. -
19
Lobe Icons
Brings AI/LLM brand logos to your React & React Native apps
Lobe Icons is an open-source icon library designed to provide developers with a comprehensive collection of logos and visual assets representing popular artificial intelligence platforms, language models, and related technologies. The project focuses on making it easy for developers to include recognizable AI brand icons in applications such as dashboards, AI tools, documentation sites, or developer portals. The library includes icons for a wide range of AI providers and models, allowing... -
20
Anthropic SDK TypeScript
Access to Anthropic's safety-first language model APIs
anthropic-sdk-typescript is the TypeScript / JavaScript client library for the Anthropic REST API, enabling backend or Node.js usage of models like Claude. It wraps API endpoints for creating messages, streaming responses, and managing parameters in a type-safe TS environment. The library is designed for server-side use, interfacing with REST, and is stable for integration in web services or backend agents. Example usage shows how to instantiate the Anthropic client, call... -
21
DragonianVoice
C++ inference library for multiple SVC/TTS
...It uses ONNX Runtime and other backends to accelerate inference, with notes on how different execution providers such as CUDA or DirectML affect operator support and numerical stability. Recent versions integrate with fish-speech via a dedicated fish-speech.cpp subproject using ggml. -
22
TensorRT
C++ library for high performance inference on NVIDIA GPUs
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for deep learning inference applications. TensorRT-based applications perform up to 40X faster than CPU-only platforms during inference. With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and deploy to hyperscale data centers,... -
23
Groq Python
The official Python Library for the Groq API
Groq Python is the official Python SDK for the Groq REST API, giving Python developers straightforward access to Groq’s LLM, chat, audio, and other AI services. Through this library, you can call Groq’s models from Python code — for example to request chat completions, code generation, transcription, or any supported endpoint — using idiomatic Python syntax. The SDK handles authentication (via environment variable or parameter), defines proper type-safe request/response data types, and... -
24
SageMaker Training Toolkit
Train machine learning models within Docker containers
...To train a model, you can include your training script and dependencies in a Docker container that runs your training code. A container provides an effectively isolated environment, ensuring a consistent runtime and reliable training process. The SageMaker Training Toolkit can be easily added to any Docker container, making it compatible with SageMaker for training models. If you use a prebuilt SageMaker Docker image for training, this library may already be included. Write a training script (eg. train.py). Define a container with a Dockerfile that includes the training script and any dependencies. -
25
CTranslate2
Fast inference engine for Transformer models
CTranslate2 is a C++ and Python library for efficient inference with Transformer models. The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. The execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many advanced optimizations: layer fusion, padding removal, batch reordering, in-place operations, caching mechanism, etc. ...
