Metadata-Version: 2.4
Name: sa-assistant
Version: 0.2.5
Summary: SA Assistant - AWS Solutions Architect Professional Agent with Multi-Agent Architecture
Author-email: onesuit <wltks2155@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/onesuit/SaAssistant
Project-URL: Repository, https://github.com/onesuit/SaAssistant
Project-URL: Issues, https://github.com/onesuit/SaAssistant/issues
Keywords: aws,solutions-architect,ai-agent,llm,bedrock,claude,multi-agent
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: aws-opentelemetry-distro>=0.10.0
Requires-Dist: bedrock-agentcore>=1.0.3
Requires-Dist: botocore[crt]
Requires-Dist: mcp>=1.19.0
Requires-Dist: prompt-toolkit>=3.0.0
Requires-Dist: python-dotenv>=1.2.1
Requires-Dist: pyyaml>=6.0
Requires-Dist: rich>=13.0.0
Requires-Dist: strands-agents>=1.13.0
Requires-Dist: strands-agents-tools>=0.2.16
Requires-Dist: textual>=0.85.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: ruff>=0.1.0; extra == "dev"

This is a project generated by the agentcore create --template basic CLI tool!

# Layout

There are two directories generated, `src/` and `test/`. At the root, there is a `.gitignore` file, a `.bedrock_agentcore.yaml` file
which is used for other `agentcore` commands like `deploy`, `dev`, and `invoke`.

## src/

The main entrypoint to your app is defined in `src/main.py`. Using the AgentCore SDK `@app.entrypoint` decorator, this file defines a Starlette ASGI app with the chosen Agent framework SDK
running within.

`src/mcp_client/client.py` implements an MCP client using the library from your chosen Agent framework SDK.

`src/model/load.py` instantiates your chosen model provider.

## test/

Tests are not defined by default. Add your own pytest definitions here.

# Developing locally

If installation was successful, a virtual environment is already created with dependencies installed.

Run `source .venv/bin/activate` before developing.

`agentcore dev` will start a local server on 0.0.0.0:8080.

In a new terminal, you can invoke that server with:

`agentcore invoke --dev "What can you do"`

# Deployment

If you want to customize your project, you can first run `agentcore configure` before deploying. Otherwise, the default project settings
will work out of the box.

After providing credentials, `agentcore deploy` will deploy your project into Amazon Bedrock AgentCore.

Use `agentcore invoke` to invoke your deployed agent.
