Skip to main content

A library for building A2A agents with routing capabilities

Project description

A2A Agent Library

A Python library for building A2A (Agent-to-Agent) agents with routing capabilities, DynamoDB-backed registry, and LangChain integration.

Features

  • StatusAgent: Base agent implementation with status tracking and structured responses
  • RoutingAgentExecutor: Agent executor with intelligent routing capabilities
  • DynamoDB Registry: Dynamic agent card registry with heartbeat mechanism
  • Server Utilities: FastAPI application builder with A2A protocol support
  • LangChain Integration: Built on LangChain for flexible model integration

Installation

pip install distributed-a2a

Quick Start

  1. Start a server with your agent application:
from distributed_a2a import load_app
from a2a.types import AgentSkill

# Define your agent's skills
skills = [
    AgentSkill(
        id='example_skill',
        name='Example Skill',
        description='An example skill',
        tags=['example']
    )
]

# Create your agent application
app = load_app(
    name="MyAgent",
    description="My specialized agent",
    skills=skills,
    api_key="your-api-key",
    system_prompt="You are a helpful assistant...",
    host="http://localhost:8000"
)
  1. Send a request with the client
from uuid import uuid4

from distributed_a2a import RoutingA2AClient

if __name__ == "__main__":
    import asyncio

    request = "Tell me the weather in Bonn"
    client = RoutingA2AClient("http://localhost:8000")
    response: str = asyncio.run(client.send_message(request, str(uuid4())))
    print(response)

Requirements

  • Python 3.10+
  • langchain
  • langchain-core
  • langchain-openai
  • langgraph
  • pydantic
  • boto3
  • a2a

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

distributed_a2a-0.1.9rc30.tar.gz (11.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

distributed_a2a-0.1.9rc30-py3-none-any.whl (12.9 kB view details)

Uploaded Python 3

File details

Details for the file distributed_a2a-0.1.9rc30.tar.gz.

File metadata

  • Download URL: distributed_a2a-0.1.9rc30.tar.gz
  • Upload date:
  • Size: 11.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.0

File hashes

Hashes for distributed_a2a-0.1.9rc30.tar.gz
Algorithm Hash digest
SHA256 e6e1284d4aa442c8a0a750a46163231e56d72cd32a6651a8db37978b154b73bc
MD5 88164ddab0129dfad88d59bae3c9569f
BLAKE2b-256 18fee5618a08756c1a962a9264dc49e73225e010e40f5ccd191391e2663554d8

See more details on using hashes here.

File details

Details for the file distributed_a2a-0.1.9rc30-py3-none-any.whl.

File metadata

File hashes

Hashes for distributed_a2a-0.1.9rc30-py3-none-any.whl
Algorithm Hash digest
SHA256 b07294a3e9bce2957d8649a33ce95c25192fd3f426af00dbebd3e426a04829c9
MD5 0e25f98a45d166dbf6c58554033d421a
BLAKE2b-256 20cef7bac84513bee05d9f02ec722462e638b53df887a8578e8f9a4f3a8bbb44

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page