Smarter – open-source, declarative AI authoring platform (Django, K8s-inspired)

Smarter, an open-source declarative AI authoring platform developed by Smarter.sh, enables enterprises to define agents, prompts, tools, and integrations using YAML manifests inspired by Kubernetes, and deploy them via web UI, CLI, API, or Kubernetes. The platform, used as an instructional tool at the University of British Columbia, requires 20GB disk storage, 4GB memory, Python 3.13, and Docker, with a first-time setup taking about 20 minutes. It includes a React-based chat UI compatible with NPM, WordPress, Squarespace, Drupal, Office 365, SharePoint, .NET, NetSuite, Salesforce, and SAP.

Smarter is used as an instructional tool at University of British Columbia https://www.ubc.ca/ for teaching AI. Smarter is an open-source platform for building and running enterprise AI systems. Instead of writing orchestration code, you define agents, prompts, tools, and integrations using YAML manifests, then deploy them through a web UI, CLI, API, or Kubernetes. Smarter replaces scattered AI orchestration code with a single declarative system for defining, testing, and running AI workflows across environments. 1-click Quickstart https://github.com/smarter-sh/smarter-deploy deployment with Docker.- Define AI resources declaratively using YAML manifests. - Connect LLMs to APIs and SQL databases without writing custom orchestration code. command-line interface https://smarter.sh/cli for Windows, macOS, Linux and Docker rest api https://platform.smarter.sh/docs/swagger/ - web console / prompt engineer workbench SDKs https://github.com/smarter-sh/smarter-python , UI components https://www.npmjs.com/package/@smarter.sh/ui-chat , CLI tools https://smarter.sh/cli , and IDE integrations https://marketplace.visualstudio.com/items?itemName=querium.smarter-manifest for building on Smarter- publicly accessible online documentation https://platform.smarter.sh/docs/ and self onboarding resources - open source UI components for jump starting projects This setup uses Docker and takes around 20 minutes for first time installations. - Verify project requirements: Windows /smarter-sh/smarter/blob/main/setup/windows , macOS /smarter-sh/smarter/blob/main/setup/macos , Linux /smarter-sh/smarter/blob/main/setup/ubuntu operating system- 20Gib disk storage capacity - 4Gib system memory Python 3.13 https://www.python.org/ Docker https://www.docker.com/products/docker-desktop/ , Docker Compose https://docs.docker.com/compose/install/ . - Add your credentials to .env /smarter-sh/smarter/blob/main/.env.example in the root of this repo. See the inline documentation for details on the minimum environment variables that you will need to set. - Initialize, build and run the application locally. git clone https://github.com/smarter-sh/smarter make help scaffolds a .env file in the root of the repo STOP HERE Add your credentials to .env located in the project root folder. make init pulls Docker containers, creates a Python virtual environment, installs all packages, creates and initializes a local MySql database, preloads example AI resources make run runs all docker containers and starts a local web server http://localhost:9357/ - Login at http://localhost:9357/login/ http://localhost:9357/login/ with user admin@smarter.sh and password smarter . See these onboarding videos: Smarter implements a yaml manifest-based approach to managing AI resources that is inspired by the Kubernetes https://kubernetes.io/ project. It provides a unified, declarative way to define, configure, and orchestrate the disparate resources that are required for creating and managing AI resources that integrate to other enterprise resources like REST API's and Sql databases. And it gives prompt engineering teams an intuitive workbench approach to designing, prototyping, testing, deploying and managing powerful AI resources for common corporate use cases including agentic workflows, customer facing chat solutions, and more. It includes a separately managed React-based chat UI https://github.com/smarter-sh/smarter-chat that is compatible with a wide variety of front end ecosystems including NPM, Wordpress, Squarespace, Drupal, Office 365, Sharepoint, .Net, Netsuite, salesforce.com, and SAP. There is a Golang command-line interface https://github.com/smarter-sh/smarter-cli , and a PyPi package https://github.com/smarter-sh/smarter-python for integrating the API functions into your own Python projects. It is developed to support prompt engineering teams working in large organizations. Accordingly, Smarter provides common enterprise features such as credentials management, team workgroup management, role-based security, accounting cost codes, and logging and audit capabilities. Smarter provides seamless integration and interoperation between LLMs from DeepSeek, Google AI, Meta AI and OpenAI. It is LLM provider-agnostic, and provides seamless integrations to a continuously evolving list of value added services for security management, prompt content moderation, audit, cost accounting, and workflow management. Smarter is cloud native and runs on Kubernetes, on-site in your data center or in the cloud. Smarter is cost effective when running at scale. It is extensible and architected on the philosophy of a compact core that does not require customization nor forking. It is horizontally scalable. It is natively multi-tenant, and can be installed alongside your existing systems. Quickstart See ghcr.io/smarter-sh/charts/smarter https://ghcr.io/smarter-sh/charts/smarter or Artifact Hub https://artifacthub.io/packages/helm/project-smarter/smarter . Read the Docs: docs.smarter.sh https://docs.smarter.sh/ Please report bugs to the GitHub Issues Page https://github.com/smarter-sh/smarter/issues for this project. Please see the CONTRIBUTING https://docs.smarter.sh/en/latest/smarter-framework/guides/contributing.html .