The Smarter Project v0.15.0-alpha.7 Documentation
The Smarter Project is an open source, cloud-native platform and developer framework for building, deploying, and governing AI applications. It runs wherever you do — a single Docker container to get started, or natively on Kubernetes via the Smarter Helm chart for production. There’s no managed-service dependency and no vendor lock-in: you own the deployment, the data, and the infrastructure it runs on.
Every capability in Smarter — from calling a model, to running a tool, to storing a credential — is expressed as a declarative Resource, and every Resource is created and managed the same way: by applying a Smarter Manifest (SAM), a plain YAML file that declares its desired state. There’s no resource-specific SDK to learn and no separate API convention to memorize — an Account, a Secret, an LLMClient, an Orchestrator coordinating a multi-agent workflow, a Plugin reaching into an external database — all of it is created, versioned, diffed, and reviewed like any other infrastructure-as-code. Because SAM files are plain, human-readable YAML, they can be understood by non-developers — business analysts and product managers — not just by the engineers who apply them.
Resources compose into four layers — Access & Governance, Model Connectivity, Extensibility & Trust, and Conversation (see the full Resource Reference) — so a single Prompt can be traced end to end: back through the guardrail checks, tool calls, and model connection that produced it, back through any Orchestrator run that coordinated it, to the account and budget that authorized it in the first place. This layered, fully auditable design is what lets Smarter scale from a single AI assistant to large, governed, multi-agent applications without changing how you work with it.
The project combines three complementary capabilities. The Smarter Platform provides authoring & administration, deployment, operations, and governance. Smarter Resources define the building blocks of AI applications, including LLM providers, prompts, agents, orchestrators, plugins, connections, secrets, vectorstores, and integrations. The Smarter Development Framework — the same framework Smarter itself is built on and ships as open source — provides APIs, SDKs, command-line tools, React components, and developer tooling for building enterprise AI applications on top of the platform.
Whether you are deploying a single AI assistant, integrating AI into existing business systems, or building large-scale multi-agent applications, Smarter provides a unified framework for managing AI resources throughout their entire lifecycle.
From scratch | Quick Start Guide | Prerequisites | Trouble Shooting & FAQ | Tutorial
Platform
A proxy server that facilitates secure, governed, auditable access to AI providers and resources without exposing secrets or direct access to the underlying vendor accounts.
Helps you manage all your AI resources using easy YAML files (like how Kubernetes works).
Simple Docker installation. Run on Kubernetes with the Smarter Helm chart.
Manage AI resources with the web dashboard, the REST API, and the command-line interface.
Keeps track of logs, safety checks, costs, and security so nothing gets lost or misused.
AI Resource Management
Works with many AI model providers — OpenAI, Google AI, Meta AI, DeepSeek, and others — or self-hosted models you deploy and manage yourself.
Lets you organize and version your prompts, and see how they change over time.
Coordinates multiple models into multi-agent workflows with Orchestrator — sequential, parallel, supervisor/worker, routing, and voting/debate strategies — so you can build bigger, smarter tasks.
Secure integrations to external data sources like databases and APIs.
Developer Application Framework
Built on Django, Django REST Framework, Pydantic.
Automated AWS cloud infrastructure and Kubernetes management.
ReactJS component-based UI integration solution that works for any web page.
Build AI tools that connect to enterprise resources like Sql databases and REST APIs.
Prompt engineer workbench for testing prompts and workflows before you deploy.
Vibrant developer community: PyPI, NPM, VS Code extensions, and more.
Usage
1. Create a Smarter manifest
apiVersion: smarter.sh/v1
kind: LLMClient
metadata:
name: stackademy_sql
description: Stackademy University course catalogue inquiries using the Stackademy SQL plugin.
version: 1.0.0
tags:
- stackademy
- sql
- llm_client
annotations:
- smarter.sh/llm-client/stackademy-sql/creator: QA Team
- smarter.sh/llm-client/stackademy-sql/purpose: llm_client for Stackademy course catalogue inquiries
- smarter.sh/llm-client/stackademy-sql/release-date: 2024-06-15
- smarter.sh/llm-client/stackademy-sql/backward-compatibility: true
- smarter.sh/llm-client/stackademy-sql/note: |
Uses SQL plugin to answer course catalogue questions.
Very fast and accurate when the database is well-structured.
Leverages cache for improved performance.
spec:
config:
deployed: false
provider: openai
defaultModel: gpt-4o-mini
defaultSystemRole: >
You are a helpful assistant. When given the opportunity to utilize
function calling, you should always do so. This will allow you to
provide the best possible responses to the user. DO NOT GUESS. IF
YOU DON'T KNOW THE ANSWER, RESPOND THAT YOU DON'T KNOW.
defaultTemperature: 0.5
defaultMaxTokens: 1024
appName: Stackademy
appAssistant: Stanley
appWelcomeMessage: Welcome to Stackademy! How can I help you today?
appExamplePrompts:
- "Do you offer any courses on AI?"
- "My budget is $1,000. What courses can I take?"
- "I want to study programming. What do you suggest?"
appPlaceholder: "Ask me anything about Stackademy courses..."
appInfoUrl: https://stackademy.edu/online-courses
plugins:
- stackademy_sql
functions: []
2. Apply the Manifest
smarter apply -f stackademy-llm_client-sql.yaml
3. Interact
Table of Contents