Agent Stack Server SDK
Python SDK for packaging agents for deployment to Agent Stack infrastructure.
Overview
The agentstack-sdk provides Python utilities for wrapping agents built with any framework (LangChain, CrewAI, BeeAI Framework, etc.) for deployment on Agent Stack. It handles the A2A (Agent-to-Agent) protocol implementation, platform service integration, and runtime requirements so you can focus on agent logic.
Key Features
- Framework-Agnostic Deployment - Wrap agents from any framework for Agent Stack deployment
- A2A Protocol Support - Automatic handling of Agent-to-Agent communication
- Platform Service Integration - Connect to Agent Stack's managed LLM, embedding, file storage, and vector store services
- Context Storage - Manage data associated with conversation contexts
Installation
uv add agentstack-sdk
Quickstart
import os
from a2a.types import (
Message,
)
from a2a.utils.message import get_message_text
from agentstack_sdk.server import Server
from agentstack_sdk.server.context import RunContext
from agentstack_sdk.a2a.types import AgentMessage
server = Server()
@server.agent()
async def example_agent(input: Message, context: RunContext):
"""Polite agent that greets the user"""
hello_template: str = os.getenv("HELLO_TEMPLATE", "Ciao %s!")
yield AgentMessage(text=hello_template % get_message_text(input))
def run():
try:
server.run(host=os.getenv("HOST", "127.0.0.1"), port=int(os.getenv("PORT", 8000)))
except KeyboardInterrupt:
pass
if __name__ == "__main__":
run()
Run the agent:
uv run my_agent.py
Available Extensions
The SDK includes extension support for:
- Citations - Source attribution (
CitationExtensionServer,CitationExtensionSpec) - Trajectory - Agent decision logging (
TrajectoryExtensionServer,TrajectoryExtensionSpec) - Settings - User-configurable agent parameters (
SettingsExtensionServer,SettingsExtensionSpec) - LLM Services - Platform-managed language models (
LLMServiceExtensionServer,LLMServiceExtensionSpec) - Agent Details - Metadata and UI enhancements (
AgentDetail) - And more - See Documentation
Each extension provides both server-side handlers and A2A protocol specifications for seamless integration with Agent Stack's UI and infrastructure.
Resources
Contributing
Contributions are welcome! Please see the Contributing Guide for details.
Support
Developed by contributors to the BeeAI project, this initiative is part of the Linux Foundation AI & Data program. Its development follows open, collaborative, and community-driven practices.
4 maintainers
Metadata
4 maintainers
Release files for agentstack-sdk 0.7.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| agentstack_sdk-0.7.1.tar.gz | 57.5 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| agentstack_sdk-0.7.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 157.0 kB
Release files / agentstack_sdk-0.7.1.tar.gz
| Download URL | agentstack_sdk-0.7.1.tar.gz |
|---|---|
| Size | 57.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
34021bb4a818a16b3417c9924a4579a822b6b3ad736af1824871a255d7d9ce8b
|
|
BLAKE2b-256 checksum How to use checksums |
260fa2af11afde107b9877ccaa3d2338e7a45280e627216e2f313c9e9c85c5bf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 30, 2026.
Transparency logRelease files / agentstack_sdk-0.7.1-py3-none-any.whl
| Download URL | agentstack_sdk-0.7.1-py3-none-any.whl |
|---|---|
| Size | 99.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e32eede7de6b478a1c760c75b736793019fe9c05adc1f50bbc897e78f8d378b3
|
|
BLAKE2b-256 checksum How to use checksums |
2f2331cb0507a11a9092e49ce48a15428e18b1493fbd85029b99dbc0228ab805
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 30, 2026.
Transparency log
