pluto

Pluto provides a unified programming interface that allows you to seamlessly tap into cloud capabilities and develop your cloud and AI applications.

Stars: 90

Visit

Pluto is a development tool dedicated to helping developers **build cloud and AI applications more conveniently** , resolving issues such as the challenging deployment of AI applications and open-source models. Developers are able to write applications in familiar programming languages like **Python and TypeScript** , **directly defining and utilizing the cloud resources necessary for the application within their code base** , such as AWS SageMaker, DynamoDB, and more. Pluto automatically deduces the infrastructure resource needs of the app through **static program analysis** and proceeds to create these resources on the specified cloud platform, **simplifying the resources creation and application deployment process**.

README:

English | 简体中文

Pluto is a development tool dedicated to helping developers build cloud and AI applications more conveniently, resolving issues such as the challenging deployment of AI applications and open-source models.

Developers are able to write applications in familiar programming languages like Python and TypeScript, directly defining and utilizing the cloud resources necessary for the application within their code base, such as AWS SageMaker, DynamoDB, and more. Pluto automatically deduces the infrastructure resource needs of the app through static program analysis and proceeds to create these resources on the specified cloud platform, simplifying the resources creation and application deployment process.

⚠️ Caution: Pluto is still in its early stages, please consider it for production environments with caution.

🌟 Example

Let's develop a text generation application based on GPT2, where the user input is processed by the GPT2 model to generate and return text. Below is how the development process with Pluto looks:

AWS SageMaker is utilized as the model deployment platform, and AWS Api Gateway and Lambda support the application's HTTP services. The deployed application architecture, as shown in the top right graphic ↗️, comprises two route handling functions: one to receive user input, invoke the SageMaker model, and return generated text, and another to provide the endpoint URL of the SageMaker model.

The top left graphic ↖️ captures a fragment of the application code, with the complete code accessible here. In the TypeScript code development process using Pluto, by creating a new SageMaker instance using new SageMaker(), you can directly interact with the SageMaker model using methods like sagemaker.invoke() and obtain the model endpoint URL using sagemaker.endpointUrl(). Establishing an Api Gateway requires only creating a new variable router with new Router(), and the function arguments within the methods of router, such as router.get(), router.post(), etc., will automatically be converted into Lambda functions. The same application could be implemented in Python as well.

Once the application code has been written, executing pluto deploy allows Pluto to deduce the application's infrastructure needs and automatically provision around 30 cloud resources, which includes instances such as SageMaker, Lambda, Api Gateway, along with setups like triggers, IAM roles, and policy permissions.

Finally, Pluto hands back the URL of the Api Gateway, providing direct access to use the application.

Interested in exploring more examples?

TypeScript applications:
Python applications:

🚀 Quick Start

Online Experience:CodeSandbox offers an online development environmentwhere we've set up Pluto templates in both Python and TypeScript. This allows you to explore Pluto directly in your browser. To create your own project, simply open the template and click the "Fork" button in the top right corner. The environment comes pre-configured with AWS CLI, Pulumi, and Pluto's basic dependencies, adhering to the README for operations.

Alternatively, you can also enjoy an online development experience by clicking

Container Experience: We offer a container image plutolang/pluto:latest for application development, which contains essential dependencies like AWS CLI, Pulumi, and Pluto, along with Node.js 20.x and Python 3.10 environments pre-configured. If you are interested in developing only TypeScript applications, you can use the plutolang/pluto:latest-typescript image. You can partake in Pluto development within a container using the following command:

docker run -it --name pluto-app plutolang/pluto:latest bash

Local Experience: For local use, please follow these steps for setup:

1. Install Pluto

npm install -g @plutolang/cli

2. Deploy your application with Pluto

pluto new        # Interactively create a new project, allowing selection of TypeScript or Python
cd <project_dir> # Enter your project directory
npm install      # Download dependencies

# If it's a Python project, in addition to npm install, Python dependencies must also be installed.
pip install -r requirements.txt

pluto deploy     # Deploy with one click!

⚠️ Note:

If the target platform is AWS, Pluto attempts to read your AWS configuration file to acquire the default AWS Region, or alternatively, tries to fetch it from the environment variable AWS_REGION. Deployment will fail if neither is set.
If the target platform is Kubernetes, Knative must firstly be installed within K8s and the scale-to-zero feature should be deactivated (as Pluto doesn't yet support Ingress forwarding to Knative serving). You can configure the required Kubernetes environment following this document.

For detailed steps, refer to the Getting Started Guide.

Currently, Pluto only supports single-file configurations. Inside each handler function, access is provided to literal constants and plain functions outside of the handler's scope; however, Python allows direct access to classes, interfaces, etc., outside of the scope, whereas TypeScript requires encapsulating these within functions for access.

🤯 Pain Points

Here you can find out why Pluto was created. To put it simply, we aim to address several pain points you might often encounter:

High learning curve: Developing a cloud application requires mastery of both the business and infrastructure skills, and it often demands significant efforts in testing and debugging. Thus, developers spend a considerable amount of energy on aspects beyond writing the core business logic.
High cognitive load: With cloud service providers offering hundreds of capabilities and Kubernetes offering nearly limitless possibilities, average developers often lack a deep understanding of cloud infrastructure, making it challenging to choose the proper architecture for their particular needs.
Poor programming experience: Developers must maintain separate codebases for infrastructure and business logic or intertwine infrastructure configuration within the business logic, leading to a sub-optimal programming experience that falls short of the simplicity of creating a local standalone program.
Vendor lock-in: Coding for a specific cloud provider can lead to poor flexibility in the resulting code. When it becomes necessary to migrate to another cloud platform due to cost or other factors, adapting the existing code to the new environment can require substantial changes.

💡 Features

No learning curve: The programming interface is fully compatible with TypeScript, Python, and supports the majority of dependency libraries such as LangChain, LangServe, FastAPI, etc.
Focus on pure business logic: Developers only need to write the business logic. Pluto, via static analysis, automatically deduces the infrastructure requirements of the application.
One-click cloud deployment: The CLI provides basic capabilities such as compilation and deployment. Beyond coding and basic configuration, everything else is handled automatically by Pluto.
Support for various runtime environments: With a unified abstraction based on the SDK, it allows developers to migrate between different runtime environments without altering the source code.

🔧 How Does Pluto Work?

Overall, the Pluto deployment process comprises three stages—deduction, generation, and deployment:

Deduction Phase: The deducer analyzes the application code to derive the required cloud resources and their interdependencies, resulting in an architecture reference. It also splits user business code into business modules, which, along with the dependent SDK, form the business bundle.
Generation Phase: The generator creates IaC code that is independent of user code, guided by the architecture reference.
Deployment Phase: Depending on the IaC code type, Pluto invokes the corresponding adapter, which, in turn, works with the respective IaC engine to execute the IaC code, managing infrastructure configuration and application deployment.

Components such as the deducer, generator, and adapter are extendable, which allows support for a broader range of programming languages and platform integration methods. Currently, Pluto provides deducers for Python and TypeScript, and a generator and adapter for Pulumi. Learn more about Pluto's processes in detail in this document.

🤔️ Differences from Other Projects?

Pluto distinguishes itself from other offerings by leveraging static program analysis techniques to infer resource dependencies directly from application code and generate infrastructure code that remains separate from business logic. This approach ensures infrastructure configuration does not intrude into business logic, providing developers with a development experience free from infrastructure concerns.

Compared to BaaS (Backend as a Service) products like Supabase or Appwrite, Pluto assists developers in creating the necessary infrastructure environment within their own cloud account, rather than offering managed components.
Differing from PaaS (Platform as a Service) offerings like Fly.io, Render, Heroku, or LeptonAI, Pluto does not handle application hosting. Instead, it compiles application into finely-grained compute modules, and integrates with rich cloud platform capabilities like FaaS, GPU instances, and message queues, enabling deployment to cloud platforms without requiring developers to write extra configurations.
In contrast to scaffolding tools such as the Serverless Framework or Serverless Devs, Pluto does not impose an application programming framework specific to particular cloud providers or frameworks, but instead offers a uniform programming interface.
Unlike IfC (Infrastructure from Code) products based purely on annotations like Klotho, Pluto infers resource dependencies directly from user code, eliminating the need for extra annotations.
Different from other IfC products that rely on dynamic analysis, like Shuttle, Nitric, and Winglang, Pluto employs static program analysis to identify application resource dependencies, generating independent infrastructure code without having to execute user code.

You can learn more about the differences with other projects in this document.

👏 Contributing

Pluto is still in its infancy, and we warmly welcome contributions from those who are interested. Any suggestions or ideas about the issues Pluto aims to solve, the features it offers, or its code implementation can be shared and contributed to the community. Please refer to our project contribution guide for more information.

🐎 Roadmap

Complete implementation of the resource static deduction process
- 🚧 Resource type checking
- ❌ Conversion of local variables into cloud resources
SDK development
- 🚧 Client SDK development
- 🚧 Infra SDK development
- ❌ Support for additional resources and more platforms
Engine extension support
- 🚧 Pulumi
- ❌ Terraform
🚧 Local simulation and testing functionality

Please see the Issue list for further details.

📊 Capability Matrix

✅: Indicates that all user-visible interfaces are available
🚧: Indicates that some of the user-visible interfaces are available
❌: Indicates not yet supported

TypeScript

Resource Type	AWS	Kubernetes	Alibaba Cloud	Simulation
Router	✅	🚧	🚧	🚧
Queue	✅	✅	❌	✅
KVStore	✅	✅	❌	✅
Function	✅	✅	✅	✅
Schedule	✅	✅	❌	❌
Tester	✅	❌	❌	✅
SageMaker	✅	❌	❌	❌

Python

Resource Type	AWS	Kubernetes	Alibaba Cloud	Simulation
Router	✅	❌	❌	❌
Queue	✅	❌	❌	❌
KVStore	✅	❌	❌	❌
Function	✅	❌	❌	❌
Schedule	✅	❌	❌	❌
Tester	❌	❌	❌	❌
SageMaker	✅	❌	❌	❌

💬 Community

Join our Slack community to communicate and contribute ideas.

For Tasks:

Click tags to check more tools for each tasks

deploy cloud applications build ai applications manage cloud resources

For Jobs:

cloud developer ai engineer backend developer full-stack developer devops engineer

Alternative AI tools for pluto

Similar Open Source Tools

pluto

github

: 90

Conversation-Knowledge-Mining-Solution-Accelerator

The Conversation Knowledge Mining Solution Accelerator enables customers to leverage intelligence to uncover insights, relationships, and patterns from conversational data. It empowers users to gain valuable knowledge and drive targeted business impact by utilizing Azure AI Foundry, Azure OpenAI, Microsoft Fabric, and Azure Search for topic modeling, key phrase extraction, speech-to-text transcription, and interactive chat experiences.

github

: 255

azure-ai-document-processing-samples

This repository contains a collection of code samples that demonstrate how to use various Azure AI capabilities to process documents. The samples help engineering teams establish techniques with Azure AI Foundry, Azure OpenAI, Azure AI Document Intelligence, and Azure AI Language services to build solutions for extracting structured data, classifying, and analyzing documents. The techniques simplify custom model training, improve reliability in document processing, and simplify document processing workflows by providing reusable code and patterns that can be easily modified and evaluated for most use cases.

github

: 60

hass-ollama-conversation

The Ollama Conversation integration adds a conversation agent powered by Ollama in Home Assistant. This agent can be used in automations to query information provided by Home Assistant about your house, including areas, devices, and their states. Users can install the integration via HACS and configure settings such as API timeout, model selection, context size, maximum tokens, and other parameters to fine-tune the responses generated by the AI language model. Contributions to the project are welcome, and discussions can be held on the Home Assistant Community platform.

github

: 113

NeMo-Agent-Toolkit

NVIDIA NeMo Agent toolkit is a flexible, lightweight, and unifying library that allows you to easily connect existing enterprise agents to data sources and tools across any framework. It is framework agnostic, promotes reusability, enables rapid development, provides profiling capabilities, offers observability features, includes an evaluation system, features a user interface for interaction, and supports the Model Context Protocol (MCP). With NeMo Agent toolkit, users can move quickly, experiment freely, and ensure reliability across all agent-driven projects.

github

: 1.4k

img-prompt

IMGPrompt is an AI prompt editor tailored for image and video generation tools like Stable Diffusion, Midjourney, DALL·E, FLUX, and Sora. It offers a clean interface for viewing and combining prompts with translations in multiple languages. The tool includes features like smart recommendations, translation, random color generation, prompt tagging, interactive editing, categorized tag display, character count, and localization. Users can enhance their creative workflow by simplifying prompt creation and boosting efficiency.

github

: 180

Transtation-KMP

Transtation is an easy-to-use and powerful translation software for Android/Desktop based on Kotlin Multiplatform + Compose Multiplatform. It allows users to translate one item using multiple engines simultaneously, utilize advanced Large Language Models for translation, chat with LLMs for translation, translate long text, support plugin development, image translation, and screen translation. The application is designed for Chinese users and serves as a reference for learning Jetpack Compose or Compose Multiplatform. It features Kotlin Multiplatform, Compose Multiplatform, MVVM, Kotlin Coroutine, Flow, SqlDelight, synchronized translation with multiple engines, plugin development, and makes use of Kotlin language features like lazy loading, Coroutine, sealed classes, and reflection. The application gradually adapts to Android13 with features like setting application language separately and supporting Monet icon.

github

: 106

venice

Venice is a derived data storage platform, providing the following characteristics: 1. High throughput asynchronous ingestion from batch and streaming sources (e.g. Hadoop and Samza). 2. Low latency online reads via remote queries or in-process caching. 3. Active-active replication between regions with CRDT-based conflict resolution. 4. Multi-cluster support within each region with operator-driven cluster assignment. 5. Multi-tenancy, horizontal scalability and elasticity within each cluster. The above makes Venice particularly suitable as the stateful component backing a Feature Store, such as Feathr. AI applications feed the output of their ML training jobs into Venice and then query the data for use during online inference workloads.

github

: 564

llm.mojo

This project is a port of Andrej Karpathy's llm.c to Mojo, currently in beta. It is under active development and subject to changes. Users should expect to encounter bugs and unfinished features.

github

: 174

rlhf_trojan_competition

This competition is organized by Javier Rando and Florian Tramèr from the ETH AI Center and SPY Lab at ETH Zurich. The goal of the competition is to create a method that can detect universal backdoors in aligned language models. A universal backdoor is a secret suffix that, when appended to any prompt, enables the model to answer harmful instructions. The competition provides a set of poisoned generation models, a reward model that measures how safe a completion is, and a dataset with prompts to run experiments. Participants are encouraged to use novel methods for red-teaming, automated approaches with low human oversight, and interpretability tools to find the trojans. The best submissions will be offered the chance to present their work at an event during the SaTML 2024 conference and may be invited to co-author a publication summarizing the competition results.

github

: 93

helix-db

HelixDB is a database designed specifically for AI applications, providing a single platform to manage all components needed for AI applications. It supports graph + vector data model and also KV, documents, and relational data. Key features include built-in tools for MCP, embeddings, knowledge graphs, RAG, security, logical isolation, and ultra-low latency. Users can interact with HelixDB using the Helix CLI tool and SDKs in TypeScript and Python. The roadmap includes features like organizational auth, server code improvements, 3rd party integrations, educational content, and binary quantisation for better performance. Long term projects involve developing in-house tools for knowledge graph ingestion, graph-vector storage engine, and network protocol & serdes libraries.

github

: 2.4k

neuro-san-studio

Neuro SAN Studio is an open-source library for building agent networks across various industries. It simplifies the development of collaborative AI systems by enabling users to create sophisticated multi-agent applications using declarative configuration files. The tool offers features like data-driven configuration, adaptive communication protocols, safe data handling, dynamic agent network designer, flexible tool integration, robust traceability, and cloud-agnostic deployment. It has been used in various use-cases such as automated generation of multi-agent configurations, airline policy assistance, banking operations, market analysis in consumer packaged goods, insurance claims processing, intranet knowledge management, retail operations, telco network support, therapy vignette supervision, and more.

github

: 197

CogVideo

CogVideo is an open-source repository that provides pretrained text-to-video models for generating videos based on input text. It includes models like CogVideoX-2B and CogVideo, offering powerful video generation capabilities. The repository offers tools for inference, fine-tuning, and model conversion, along with demos showcasing the model's capabilities through CLI, web UI, and online experiences. CogVideo aims to facilitate the creation of high-quality videos from textual descriptions, catering to a wide range of applications.

github

: 11.0k

OpenContracts

OpenContracts is an Apache-2 licensed enterprise document analytics tool that supports multiple formats, including PDF and txt-based formats. It features multiple document ingestion pipelines with a pluggable architecture for easy format and ingestion engine support. Users can create custom document analytics tools with beautiful result displays, support mass document data extraction with a LlamaIndex wrapper, and manage document collections, layout parsing, automatic vector embeddings, and human annotation. The tool also offers pluggable parsing pipelines, human annotation interface, LlamaIndex integration, data extraction capabilities, and custom data extract pipelines for bulk document querying.

github

: 803

kubeai

KubeAI is a highly scalable AI platform that runs on Kubernetes, serving as a drop-in replacement for OpenAI with API compatibility. It can operate OSS model servers like vLLM and Ollama, with zero dependencies and additional OSS addons included. Users can configure models via Kubernetes Custom Resources and interact with models through a chat UI. KubeAI supports serving various models like Llama v3.1, Gemma2, and Qwen2, and has plans for model caching, LoRA finetuning, and image generation.

github

: 873

XLearning

XLearning is a scheduling platform for big data and artificial intelligence, supporting various machine learning and deep learning frameworks. It runs on Hadoop Yarn and integrates frameworks like TensorFlow, MXNet, Caffe, Theano, PyTorch, Keras, XGBoost. XLearning offers scalability, compatibility, multiple deep learning framework support, unified data management based on HDFS, visualization display, and compatibility with code at native frameworks. It provides functions for data input/output strategies, container management, TensorBoard service, and resource usage metrics display. XLearning requires JDK >= 1.7 and Maven >= 3.3 for compilation, and deployment on CentOS 7.2 with Java >= 1.7 and Hadoop 2.6, 2.7, 2.8.

github

: 1.7k

For similar tasks

griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github

: 2.2k

AI-in-a-Box

AI-in-a-Box is a curated collection of solution accelerators that can help engineers establish their AI/ML environments and solutions rapidly and with minimal friction, while maintaining the highest standards of quality and efficiency. It provides essential guidance on the responsible use of AI and LLM technologies, specific security guidance for Generative AI (GenAI) applications, and best practices for scaling OpenAI applications within Azure. The available accelerators include: Azure ML Operationalization in-a-box, Edge AI in-a-box, Doc Intelligence in-a-box, Image and Video Analysis in-a-box, Cognitive Services Landing Zone in-a-box, Semantic Kernel Bot in-a-box, NLP to SQL in-a-box, Assistants API in-a-box, and Assistants API Bot in-a-box.

github

: 527

spring-ai

The Spring AI project provides a Spring-friendly API and abstractions for developing AI applications. It offers a portable client API for interacting with generative AI models, enabling developers to easily swap out implementations and access various models like OpenAI, Azure OpenAI, and HuggingFace. Spring AI also supports prompt engineering, providing classes and interfaces for creating and parsing prompts, as well as incorporating proprietary data into generative AI without retraining the model. This is achieved through Retrieval Augmented Generation (RAG), which involves extracting, transforming, and loading data into a vector database for use by AI models. Spring AI's VectorStore abstraction allows for seamless transitions between different vector database implementations.

github

: 6.7k

ragstack-ai

RAGStack is an out-of-the-box solution simplifying Retrieval Augmented Generation (RAG) in GenAI apps. RAGStack includes the best open-source for implementing RAG, giving developers a comprehensive Gen AI Stack leveraging LangChain, CassIO, and more. RAGStack leverages the LangChain ecosystem and is fully compatible with LangSmith for monitoring your AI deployments.

github

: 127

breadboard

Breadboard is a library for prototyping generative AI applications. It is inspired by the hardware maker community and their boundless creativity. Breadboard makes it easy to wire prototypes and share, remix, reuse, and compose them. The library emphasizes ease and flexibility of wiring, as well as modularity and composability.

github

: 327

cloudflare-ai-web

Cloudflare-ai-web is a lightweight and easy-to-use tool that allows you to quickly deploy a multi-modal AI platform using Cloudflare Workers AI. It supports serverless deployment, password protection, and local storage of chat logs. With a size of only ~638 kB gzip, it is a great option for building AI-powered applications without the need for a dedicated server.

github

: 1.9k

app-builder

AppBuilder SDK is a one-stop development tool for AI native applications, providing basic cloud resources, AI capability engine, Qianfan large model, and related capability components to improve the development efficiency of AI native applications.

github

: 503

cookbook

This repository contains community-driven practical examples of building AI applications and solving various tasks with AI using open-source tools and models. Everyone is welcome to contribute, and we value everybody's contribution! There are several ways you can contribute to the Open-Source AI Cookbook: Submit an idea for a desired example/guide via GitHub Issues. Contribute a new notebook with a practical example. Improve existing examples by fixing issues/typos. Before contributing, check currently open issues and pull requests to avoid working on something that someone else is already working on.

github

: 2.3k

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 502

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 669

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 953

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 1.3k

griptape

github

: 2.2k