Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.maximem.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Install

pip install maximem-synap-semantic-kernel

​
What’s included

ClassPurpose
SynapPluginSemantic Kernel plugin with search_memory and store_memory kernel functions

​
Quick start

from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion
from synap_semantic_kernel import SynapPlugin

kernel = Kernel()
kernel.add_service(OpenAIChatCompletion(service_id="default"))

kernel.add_plugin(
    SynapPlugin(sdk=sdk, user_id="alice", customer_id="acme"),
    plugin_name="synap",
)

result = await kernel.invoke_prompt(
    "{{synap.search_memory query='project priorities'}} What are my top priorities?"
)

​
Plugin functions

search_memory(query: str, max_results: int = 5) -> str Searches Synap for memories matching query. Returns a formatted string of results for direct use in prompt templates. store_memory(content: str, memory_type: str = 'fact') -> str Stores a new memory. Returns "Memory stored successfully." on success.

​
Using with auto function calling

Register the plugin and enable auto function calling so the kernel invokes Synap tools automatically: 
from semantic_kernel.connectors.ai import FunctionChoiceBehavior

settings = kernel.get_prompt_execution_settings_from_service_id("default")
settings.function_choice_behavior = FunctionChoiceBehavior.Auto()

kernel.add_plugin(SynapPlugin(sdk=sdk, user_id="alice"), plugin_name="synap")

chat_history = ChatHistory()
chat_history.add_user_message("What do you remember about my travel preferences?")

response = await kernel.invoke_stream(
    function=kernel.get_function("chat", "chat"),
    settings=settings,
    chat_history=chat_history,
)

​
Next steps

Microsoft Agent Framework

Context and history providers for MAF agents.

OpenAI Agents

Function tools for the OpenAI Agents SDK.