
pocketflow a2a
Use pocketflow to implement a2a protocal
Repository Info
About This Server
Use pocketflow to implement a2a protocal
Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.
Documentation
PocketFlow Agent with A2A Protocol
I modified Pocketflow cookbook to make the the LLM calling from client side available, and be able to communicate between client and server.
TL;DR The LLM flow from client side will decide which agent to consult and send task to execute, then decide whether should it answer to user.
This implementation is based on the tutorial: A2A Protocol Simply Explained: Here are 3 key differences to MCP!
Run example
Server
uv run --env-file .env python -m a2a_server
Client
# With log
uv run --env-file .env --directory examples/user_agent_talking_with_duckduckgo_agent python -m a2a_client.chat
# Without log
POCKETFLOW_LOG_LEVEL=REMOVE uv run --env-file .env --directory examples/user_agent_talking_with_duckduckgo_agent python -m a2a_client.chat
Quick Start
Clone the repository
git clone https://github.com/batprem/pocketflow-a2aInstall dependencies
cd pocketflow-a2a
npm installFollow the documentation
Check the repository's README.md file for specific installation and usage instructions.
Repository Details
Recommended MCP Servers
Discord MCP
Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.
Knit MCP
Connect AI agents to 200+ SaaS applications and automate workflows.
Apify MCP Server
Deploy and interact with Apify actors for web scraping and data extraction.
BrowserStack MCP
BrowserStack MCP Server for automated testing across multiple browsers.
Zapier MCP
A Zapier server that provides automation capabilities for various apps.