smart_toy
Foundry Agent Management
Provision, update, and delete Azure AI Foundry Hosted Agents from the CLI or Python SDK. Prompt, model, and config tracked in foundry-kit.yaml.
Open Source · MIT LicensePython 3.11+ · Azure AI Foundry
foundry-kit
A Python framework for building, managing, and serving Azure AI Foundry agents. Wire Foundry Hosted Agents to Azure AI Search vector indexes and ship to production via Azure Functions — all from a single CLI and Python SDK.
terminal — quickstart
# Install the framework
$ pip install foundry-kit
Successfully installed foundry-kit
# Initialize your project
$ foundry-kit config init
→ wrote foundry-kit.yaml
# Provision a Foundry agent
$ foundry-kit agent init my-bot \
--model gpt-4o
✓ Provisioned: asst_abc123
# Serve locally & deploy
$ foundry-kit serve
→ http://127.0.0.1:8000
The Problem
Building on Azure AI Foundry shouldn't require wiring three SDKs by hand.
Azure AI Foundry, Azure AI Search, and Azure Functions are powerful individually — but connecting them for production agent deployments means juggling credentials, index schemas, async clients, and deployment configs. foundry-kit handles all of that.
closeManual wiring of Foundry, Search, and Functions SDKs
closeRe-implementing DefaultAzureCredential in every project
closeNo standard local dev server for testing agents
closeVector index creation and embedding pipeline boilerplate
Core Capabilities
Everything you need to ship an agent.
travel_explore
Vector Search (RAG)
Create HNSW indexes in Azure AI Search, embed and upsert documents, and run vector similarity queries — all without touching the Search SDK directly.
code
Python SDK
FoundryClient and SearchManager expose clean async interfaces. Bring your own FastAPI routes or use the built-in app factory to get a chat endpoint in minutes.
cloud_upload
Azure Functions Deploy
One command packages and deploys your agent as an Azure Function. No manual function.json or host.json authoring — foundry-kit generates the deployment artifacts.
Python SDK
FoundryClient and SearchManager
Thin, typed wrappers around the Azure SDKs. Chat with a Foundry agent, query a vector index, and assemble a FastAPI app — all with three imports.
check_circle
Async-first
Built on asyncio — no blocking calls in your event loop
check_circle
Config-driven
Endpoints and deployment names read from foundry-kit.yaml
check_circle
DefaultAzureCredential
Works with az login locally, service principals in CI
agent.py
from foundry_kit import FoundryClient, SearchManager,
create_app, load_config
config = load_config("foundry-kit.yaml")
client = FoundryClient(config.foundry_endpoint)
# Async chat
import asyncio
reply = asyncio.run(
client.chat("asst_abc123", "What can you do?")
)
# Vector search
search = SearchManager(
config.search_endpoint,
config.openai_endpoint
)
results = search.query("my-index", "cloud AI services")
Quickstart
From pip install to deployed agent in five steps.
download
1. Install# Requires Python 3.11+
$ pip install foundry-kit
settings
2. Configure# Scaffolds foundry-kit.yaml
$ foundry-kit config init
→ wrote foundry-kit.yaml
smart_toy
3. Create agent$ foundry-kit agent init my-bot \
--prompt "You are a helpful assistant." \
--model gpt-4o
✓ Provisioned: asst_abc123
play_circle
4. Serve locally$ foundry-kit serve
→ http://127.0.0.1:8000
# POST /chat/my-bot to test
cloud_upload
5. Deploy$ foundry-kit deploy \
--app-name my-function-app
✓ Deployed to Azure Functions
CLI Reference
All commands at a glance.
foundry-kit config init
Scaffold foundry-kit.yaml interactively
foundry-kit agent init <name>
Provision a Foundry Hosted Agent
foundry-kit agent update <name>
Update agent prompt or model
foundry-kit agent list
List all registered agents
foundry-kit agent show <name>
Show agent details and status
foundry-kit agent delete <name>
Delete agent from Foundry and config
foundry-kit index create <name>
Create an Azure AI Search HNSW index
foundry-kit index upsert
Embed and upload documents to an index
foundry-kit index query
Run a vector similarity query
foundry-kit serve
Start local FastAPI dev server at :8000
foundry-kit deploy
Deploy agents to Azure Functions
Authentication
DefaultAzureCredential — zero secrets in code.
foundry-kit uses Azure's credential chain. Set environment variables for CI/CD or run az login locally — no secrets ever touch your source.
vpn_key
Service Principal
CI/CD and production deployments
AZURE_CLIENT_IDAZURE_CLIENT_SECRETAZURE_TENANT_IDlaptop_mac
Developer Workstation
Local development — no secrets needed
az loginchecklist
Prerequisites
deployed_code
Python 3.11+cloud
Azure AI Foundry project (pre-provisioned)travel_explore
Azure AI Search resource (for RAG)functions
Azure Functions Core Tools (for deploy)Ready to build with foundry-kit?
Star the repo, open an issue, or jump straight into the enterprise platform for MCP integrations, multi-tenant isolation, and production support.