Search Results for "stack"
Sort By:
Showing 195 open source projects for "stack"
View related business solutions-
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.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
Llama Stack
Composable building blocks to build Llama Apps
Llama-Stack is an open-source framework designed to facilitate the deployment and fine-tuning of large language models (LLMs) for various natural language processing tasks. -
2
Agent Stack
Deploy and share agents with open infrastructure
...It also offers multi-model, multi-provider support (OpenAI, Anthropic, Gemini, IBM WatsonX, Ollama etc.), letting users compare performance and cost across models. For developers and organizations building AI-agent products or automations, Agent Stack gives a scaffold that handles the “plumbing”, so they can focus on logic and domain. -
3
agentic-stack
One brain, many harnesses. Portable .agent/ folder
...It may include abstractions for memory, planning, and tool usage, reflecting modern agentic AI design patterns. The stack is intended to accelerate development by providing reusable building blocks for complex AI systems. Overall, it represents an infrastructure layer for creating autonomous or semi-autonomous AI applications. -
4
Full Stack FastAPI and PostgreSQL
Full stack, modern web application generator
Generate a backend and frontend stack using Python, including interactive API documentation. Production ready Python web server using Uvicorn and Gunicorn. Very high performance, on par with NodeJS and Go (thanks to Starlette and Pydantic). Great editor support. Completion everywhere. Less time debugging. Designed to be easy to use and learn. Less time reading docs. -
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
Superstaq
Quantum software platform that is optimized across the quantum stack
This repository is the home of the Superstaq development team's open-source work. Our quantum software platform is optimized across the quantum stack and enables users to write quantum programs in Cirq or Qiskit and target a variety of quantum computers and simulators. -
6
DeepSpec
A full-stack codebase for training and evaluating speculative decoding
DeepSpec is a full-stack codebase for training and evaluating draft models used in speculative decoding. It provides the components needed to prepare data, train draft models, and measure acceptance behavior against target models. The workflow starts with data preparation, including prompt download, target answer regeneration, and target cache construction. -
7
web2py
Free and open source full-stack enterprise framework
Free open source full-stack framework for rapid development of fast, scalable, secure and portable database-driven web-based applications. Written and programmable in Python (version 3 and 2.7). Everything you need in one package including fast multi-threaded web server, SQL database and web-based interface. No third-party dependencies but works with third-party tools. -
8
TurboGears
Python web framework with full-stack layer
TurboGears is a hybrid web framework able to act both as a Full Stack framework or as a Microframework. TurboGears helps you get going fast and gets out of your way when you want it! TurboGears can be used both as a full stack framework or as a microframework in single-file mode. TurboGears 2 is built on top of the experience of several next-generation web frameworks including TurboGears 1 (of course), Django, and Rails. -
9
Instill Core
Instill Core is a full-stack AI infrastructure tool for data
Instill Core is an open-source, full-stack AI infrastructure platform designed to orchestrate data pipelines, machine learning models, and unstructured data processing into a unified, production-ready system. It provides an end-to-end solution that enables developers to build, deploy, and manage AI-powered applications without needing to manually stitch together multiple tools across the data and model lifecycle. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
ZenML
Build portable, production-ready MLOps pipelines
A simple yet powerful open-source framework that scales your MLOps stack with your needs. Set up ZenML in a matter of minutes, and start with all the tools you already use. Gradually scale up your MLOps stack by switching out components whenever your training or deployment requirements change. Keep up with the latest changes in the MLOps world and easily integrate any new developments. Define simple and clear ML workflows without wasting time on boilerplate tooling or infrastructure code. ... -
11
LocalStack
Develop and test your cloud apps offline
LocalStack is a fully functional local AWS cloud stack that enables you to develop and test your cloud and serverless apps offline. It spins up an easy-to-use testing environment on your local machine that has the same APIs and works the same way as the real AWS cloud environment. It can spin up a number of different core Cloud APIs on your local machine, including API Gateway, Kinesis, DynamoDB, Firehose, Lambda and many others. -
12
dm_control
DeepMind's software stack for physics-based simulation
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo. DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo physics. The MuJoCo Python bindings support three different OpenGL rendering backends: EGL (headless, hardware-accelerated), GLFW (windowed, hardware-accelerated), and OSMesa (purely software-based). -
13
Mistral Vibe CLI
Minimal CLI coding agent by Mistral
...It aims to take developers out of repetitive boilerplate and let them stay “in the flow”: you can ask the tool to generate functions, refactor code, search across the codebase, manipulate files, commit changes via Git, or run commands — all from a unified CLI interface. Behind the scenes, it leverages Mistral’s coding-optimized LLM stack (including models tuned for code understanding and generation), with project-wide context awareness: it scans your file structure, Git status, and recent history to inform suggestions so that generated code aligns with existing context. -
14
Harbor LLM
Run a full local LLM stack with one command using Docker
Harbor is an open source, containerized toolkit designed to simplify running local large language model (LLM) environments. It combines a CLI and companion app to launch backends, frontends, and supporting services with minimal setup. With a single command, users can start preconfigured tools like Ollama and Open WebUI, enabling chat, workflows, and integrations immediately. Harbor supports multiple inference engines, including llama.cpp and vLLM, and connects them seamlessly to user... -
15
Modular Platform
The Modular Platform (includes MAX & Mojo)
Modular is a high-performance AI infrastructure company repository focused on building next-generation compute and software tools for machine learning workloads. The project centers on enabling developers to run AI models faster and more efficiently by rethinking the traditional ML software stack. It is closely associated with the Mojo programming language and related tooling that aims to combine Python usability with systems-level performance. Modular’s ecosystem is designed to simplify deployment of AI workloads across heterogeneous hardware while maximizing throughput. The repository reflects an effort to modernize the AI development pipeline from compilation to runtime execution. ... -
16
Werkzeug
The comprehensive WSGI web application library
...Werkzeug doesn’t enforce any dependencies. It is up to the developer to choose a template engine, database adapter, and even how to handle requests. Includes an interactive debugger that allows inspecting stack traces and source code in the browser with an interactive interpreter for any frame in the stack. Includes a full-featured request object with objects to interact with headers, query args, form data, files, and cookies. Includes a response object that can wrap other WSGI applications and handle streaming data. Includes a routing system for matching URLs to endpoints and generating URLs for endpoints, with an extensible system for capturing variables from URLs. ... -
17
Sentry
Cross-platform application monitoring and error tracking software
...The most users and logs will have to provide are the clues, and Sentry provides the answers. Sentry offers enhanced application performance monitoring through information-laden stack traces. It lets you build better software faster and more efficiently by showing you all issues in one place and providing the trail of events that lead to errors. It also provides real-time monitoring and data visualization through dashboards. Sentry’s server is in Python, but its API enables for sending events from any language, in any application. ... -
18
SaltStack
Automate the management and configuration of any infrastructure
...The Salt Project is an approach to infrastructure management built on a dynamic communication bus. Salt can be used for data-driven orchestration, remote execution for any infrastructure, configuration management for any app stack, and much more. Running commands on remote systems is the core function of Salt. Salt can execute commands across thousands of systems in seconds. Salt is built around an event infrastructure that can drive reactive provisioning, configuration, and management across all systems in your infrastructure. Salt contains a robust and flexible configuration management framework that allows effortless, simultaneous configuration of tens of thousands of systems. ... -
19
FastUI
Build better UIs faster
FastUI is a library that lets developers build interactive user interfaces for FastAPI applications using Pydantic models. It automatically generates frontend components based on data schemas and endpoint logic, reducing the need for manual UI development. Designed to be type-safe, reactive, and fast, FastUI streamlines the creation of web dashboards, admin panels, and internal tools within a FastAPI backend. -
20
Notte
Opensource browser using agents
Notte is an open-source browser framework that enables the development and deployment of web-based AI agents. It introduces a perception layer that transforms web pages into structured, navigable maps described in natural language, allowing agents to interact with the internet more effectively. Notte is designed for building scalable and efficient browser-based AI applications. -
21
Awesome LLM Apps
Collection of awesome LLM apps with AI Agents and RAG using OpenAI
...The list spans a wide range of categories including productivity tools, creative assistants, utilities, education platforms, research frameworks, and niche vertical apps, showcasing how generative models are being used across domains. Each entry includes a brief description, language model dependencies, technology stack notes, and sometimes links to demos or source code, making it easy to explore ideas and reuse concepts for your own projects. Because the landscape of LLM-powered applications changes quickly, the repository is designed to be updated regularly through community contributions, ensuring it stays current with new tools and releases. -
22
Anna’s Archive
Comprehensive search engine for books, papers, comics, magazines
Anna’s Archive is a large-scale open-source search engine and data aggregation platform designed to index and provide access to a vast collection of books, academic papers, comics, magazines, and other digital texts through a unified interface. The project includes all the infrastructure required to run a full instance locally or in production, combining web servers, databases, and search indexing systems into a scalable architecture. It relies heavily on technologies such as Elasticsearch... -
23
WordOps
Install and manage a high performance WordPress stack
An essential toolset that eases WordPress site and server administration. -
24
ZML
Any model. Any hardware. Zero compromise
ZML is a high-performance machine learning inference stack designed to run AI models efficiently across heterogeneous hardware environments using a modern systems programming approach. Built with technologies such as Zig, MLIR, and Bazel, it focuses on production-grade deployment where performance, portability, and scalability are critical. The system allows models to be compiled and executed across multiple types of accelerators, including GPUs and TPUs, even when distributed across different machines or locations. ... -
25
CoreNet
CoreNet: A library for training deep neural networks
...Its distributed runtime manages synchronization, load balancing, and mixed-precision computation to maximize throughput while minimizing communication bottlenecks. CoreNet integrates tightly with Apple’s proprietary ML stack and hardware, serving as the foundation for research in computer vision, language models, and multimodal systems within Apple AI. The framework includes monitoring tools, fault tolerance mechanisms, and efficient checkpointing for massive training runs.
