Search Results for "masmt runtime engine" - Page 3
Sort By:
Showing 184 open source projects for "masmt runtime engine"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
1
Matrix
Multi-Agent daTa geneRation Infra and eXperimentation framework
Matrix is a distributed, large-scale engine for multi-agent synthetic data generation and experiments: it provides the infrastructure to run thousands of “agentic” workflows concurrently (e.g. multiple LLMs interacting, reasoning, generating content, data-processing pipelines) by leveraging distributed computing (like Ray + cluster management). The idea is to treat data generation as a “data-to-data” transformation: each input item defines a task, and the runtime orchestrates asynchronous, peer-to-peer agent workflows, avoiding global synchronization bottlenecks. ... -
2
PicoLM
Run a 1-billion parameter LLM on a $10 board with 256MB RAM
PicoLM is an open-source inference framework designed to run large language models on extremely constrained hardware environments such as inexpensive single-board computers and embedded systems. The project focuses on enabling efficient local inference by optimizing memory usage, computation, and system dependencies so that relatively large models can operate on devices with minimal RAM. It is written primarily in C and designed with a minimalist architecture that removes unnecessary... -
3
Containerization (Apple)
Containerization is a Swift package for running Linux containers
...The emphasis is on clarity and standards alignment rather than building a production-grade engine, which makes the code ideal for learning and experimentation. -
4
QuadRay-engine
Realtime raytracer using SIMD on ARM, MIPS, PPC and x86
QuadRay engine is a realtime raytracing project aimed at full SIMD utilization on ARM, MIPS, POWER and x86 architectures. The efficient use of SIMD is achieved by processing four rays at a time to match SIMD register width (hence the name). The rendering core of the engine is written in a unified SIMD assembler allowing single assembler code to be compatible with different processor architectures, thus reducing the need to maintain multiple parallel versions. At present, Intel... -
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
5
WASTE
Run the full 2.78-trillion-parameter Kimi K3 model
...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. -
6
Ungoogled Chromium
A lightweight approach to removing Google web service dependency
In descending order of significance (i.e. most important objective first), ungoogled-chromium is Google Chromium, sans dependency on Google web services, ungoogled-chromium retains the default Chromium experience as closely as possible. Unlike other Chromium forks that have their own visions of a web browser, ungoogled-chromium is essentially a drop-in replacement for Chromium. ungoogled-chromium features tweaks to enhance privacy, control, and transparency. However, almost all of these... -
7
mllm
Fast Multimodal LLM on Mobile Devices
...The system supports multiple optimization techniques including quantization, pruning, and speculative decoding to improve performance while reducing computational overhead. It also provides tools to convert models from popular formats like PyTorch checkpoints into optimized runtime formats that can be executed on supported hardware platforms. -
8
LiteRT
LiteRT, successor to TensorFlow Lite
LiteRT is Google's next-generation on-device machine learning framework and the successor to TensorFlow Lite, designed for high-performance AI and generative AI deployment across edge devices. It provides efficient model conversion, optimization, and runtime execution while leveraging hardware acceleration from CPUs, GPUs, and NPUs. LiteRT supports a wide range of platforms, including Android, iOS, Linux, macOS, Windows, web environments, and IoT devices. The framework simplifies on-device... -
9
Rehype Pretty Code
Beautiful code blocks for Markdown or MDX
Rehype Pretty Code is a Rehype plugin powered by the Shiki syntax highlighter that provides beautiful code blocks for Markdown or MDX. It works on both the server at build-time (avoiding runtime syntax highlighting) and on the client for dynamic highlighting. Enjoy the accuracy and granularity of VS Code’s syntax highlighting engine and the popularity of its themes ecosystem - use any VSCode theme you want. -
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.
-
10
Planck.js
2D JavaScript Physics Engine
Planck.js is a JavaScript rewrite/port of the physics engine Box2D, designed to provide 2D rigid-body physics simulation usable directly in web contexts or any JavaScript environment. By offering collision detection, rigid-body dynamics, joints, and simulation capabilities, Planck.js makes it possible for developers to build physically realistic 2D games, simulations, or visualizations in browsers or Node.js without relying on native code. Its API mirrors Box2D’s concepts — bodies, fixtures,... -
11
JUnit 5
Programmer-friendly testing framework for Java and the JVM
The 5th major version of the programmer-friendly testing framework for Java and the JVM. JUnit 5 is the next generation of JUnit. The goal is to create an up-to-date foundation for developer-side testing on the JVM. This includes focusing on Java 8 and above, as well as enabling many different styles of testing. Official CI build server for JUnit 5. Used to perform quick checks on submitted pull requests and for build matrices including the latest released OpenJDK and early access builds of... -
12
EVE OS
EVE is Edge Virtualization Engine
EVE is an open-source, secure, and container-optimized operating system for edge computing, developed by the LF Edge foundation. It enables enterprises to deploy and manage edge applications on heterogeneous hardware platforms using a zero-trust architecture. EVE supports virtual machines, containers, and unikernels while being hardware-agnostic, making it suitable for industrial gateways, edge clusters, and IoT devices. With its remote provisioning, lifecycle management, and built-in... -
13
Stremio Core
Types, addon system, UI models, core logic
Stremio Core is the Rust engine that powers Stremio’s apps by centralizing all reusable logic behind discovery, catalogs, metadata, streams, add-ons, and user/library state. It exposes a clean set of modules—types, addon_transport, and state_types—so apps can talk to add-ons, model UI state, and react to events without duplicating code. The architecture is inspired by Elm: immutable state, message-driven updates, and explicit side-effects (“effects”) keep behavior predictable and testable.... -
14
DynamoRIO
Dynamic Instrumentation Tool Platform
DynamoRIO is a runtime code manipulation system that supports code transformations on any part of a program, while it executes. DynamoRIO exports an interface for building dynamic tools for a wide variety of uses: program analysis and understanding, profiling, instrumentation, optimization, translation, etc. Unlike many dynamic tool systems, DynamoRIO is not limited to insertion of callouts/trampolines and allows arbitrary modifications to application instructions via a powerful... -
15
Emscripten
Emscripten: An LLVM-to-WebAssembly Compiler
Emscripten is a complete open-source compiler toolchain that transforms C, C++, and other LLVM-based source code into WebAssembly (and JavaScript), enabling native‑like applications to run in web browsers, Node.js, and other Wasm environments. While Emscripten mostly focuses on compiling C and C++ using Clang, it can be integrated with other LLVM-using compilers (for example, Rust has Emscripten integration, with the wasm32-unknown-emscripten and asmjs-unknown-emscripten targets). Emscripten... -
16
Porcupine
On-device wake word detection powered by deep learning
Build always-listening yet private voice applications. Porcupine is a highly-accurate and lightweight wake word engine. It enables building always-listening voice-enabled applications. It is using deep neural networks trained in real-world environments. Compact and computationally-efficient. It is perfect for IoT. Cross-platform. Arm Cortex-M, STM32, PSoC, Arduino, and i.MX RT. Raspberry Pi, NVIDIA Jetson Nano, and BeagleBone. Android and iOS. Chrome, Safari, Firefox, and Edge. ... -
17
ClawRouter
Smart LLM router
ClawRouter is a flexible networking and routing framework designed to support AI-oriented distributed systems and agent ecosystems by managing how messages, requests, and responses are routed between components. It provides a programmable router abstraction that can handle complex traffic patterns, enabling dynamic message forwarding, load balancing, and custom routing logic based on content, context, or policy rules. Because distributed AI systems often involve many services, agents, and... -
18
tigerbeetle
The financial transactions database designed for mission critical safe
TigerBeetle is production-ready on Linux and seamlessly integrated with major programming languages. TigerBeetle is a financial transactions database designed for mission-critical safety and performance to power the next 30 years of OLTP. TigerBeetle redesigns the distributed database storage engine and consensus protocol for the OLTP workload. This solves the problem of OLTP write contention to unlock three orders of magnitude more performance than a general purpose (OLGP) database. The... -
19
Hurl
Hurl, run and test HTTP requests with plain text
Hurl is a command line tool that runs HTTP requests defined in a simple plain text format. It can chain requests, capture values and evaluate queries on headers and body responses. Hurl is very versatile: it can be used for both fetching data and testing HTTP sessions. Hurl makes it easy to work with HTML content, REST / SOAP / GraphQL APIs, or any other XML / JSON-based APIs. Hurl can run HTTP requests but can also be used to test HTTP responses. Different types of queries and predicates... -
20
zero-native
Build desktop + mobile apps with Zig and web UI
...Its Zig foundation enables fast native rebuilds and direct access to platform SDKs, native libraries, codecs, and local integrations. The app model includes a manifest for metadata, icons, windows, frontend assets, engine selection, security policy, bridge permissions, and packaging inputs. It is still pre-release, but it provides a promising path for developers who want web UI productivity with a leaner native runtime than heavier desktop frameworks. -
21
jawsm
JavaScript to WASM compiler
...Its design is motivated by the desire to reduce runtime overhead and binary size compared to interpreter-based solutions, especially in environments where performance and portability are critical. -
22
Nestia
NestJS Helper + AI Chatbot Development
Nestia is a high-performance toolkit and ecosystem built on top of NestJS that enhances backend development by introducing strongly typed APIs, automated SDK generation, and advanced tooling for scalable server applications. It is designed to eliminate much of the boilerplate typically associated with API development by leveraging pure TypeScript types to automatically generate validation logic, API documentation, and client SDKs. One of its defining advantages is its focus on performance... -
23
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... -
24
Apache Flink
Stream processing framework with powerful stream
Apache Flink is a distributed engine for stateful computations over data streams and batches, designed for low-latency processing at scale. Its core runtime executes dataflow graphs with fine-grained backpressure and checkpointing, allowing applications to recover consistently from failures. Flink’s event-time model and watermarks enable accurate out-of-order processing, windowing, and complex time semantics that typical real-time systems struggle with. -
25
Tilt
Define dev environment as code for microservice apps on Kubernetes
...Understand & orchestrate your services, work smarter & faster wherever you are, and team-based productivity. See all the pieces of your app, and trigger custom workflows like seeding databases or creating infrastructure. Our engine starts the whole app and runs automated rebuilds as you edit in your IDE. Get a continuous feedback loop with your logs, broken builds, and runtime errors. Work with Kubernetes without needing to be an expert. And if you are an expert, no more 20 questions with kubectl. Tilt responsively handles the tedious and repetitive parts of your workflow and gives you peripheral vision so you find errors faster. ...
