Integrations Overview

​

Three ways to add Synap

• Read-side failures degrade gracefully: a failed context fetch returns an empty result and logs an error, so your agent keeps running.
• Write-side failures surface explicitly: failed ingestion raises SynapIntegrationError (or equivalent) so callers know if memory persistence failed.
• Same scoping model everywhere: every package accepts user_id, optional customer_id, and optional conversation_id.

​

How integrations plug in

• Always-on memory: history, callback, and retriever points run on every turn without the model deciding to. This is the default for memory-augmented agents and needs no prompt changes.
• Model-driven memory: tools let the agent choose when to read or write memory. Use this when you want the model to reason about what to remember or look up, or when always-on context would be too broad.

​

Available Integrations

No-code (MCP)

Connect Gumloop, n8n, Claude, or any MCP client with just a URL and a token, no code.

LangChain

Memory, callbacks, retriever, and tools for LangChain chains and agents.

LangGraph

Checkpointer and cross-thread store for LangGraph graphs.

LlamaIndex

BaseMemory implementation and retriever for LlamaIndex pipelines.

OpenAI Agents

Search and store tools for the OpenAI Agents SDK.

Pydantic AI

Dependency dataclass and tool registration for Pydantic AI agents.

CrewAI

StorageBackend implementation for CrewAI’s unified Memory system.

AutoGen

Search and store BaseTool implementations for AutoGen agents.

Google ADK

FunctionTool factory for Google Agent Development Kit agents.

Haystack

SynapRetriever and SynapMemoryWriter pipeline components for Haystack.

Agno

Drop-in InMemoryDb replacement that routes user memories through Synap.

Semantic Kernel

Kernel plugin with search_memory and store_memory functions.

Microsoft Agent Framework

Context and history providers for the Microsoft Agent Framework.

NeMo Agent Toolkit

MemoryEditor implementation for NVIDIA NeMo Agent Toolkit workflows.

LiveKit Agents

Context preloading and turn recording for LiveKit voice agents.

Pipecat

Frame processors for memory injection and recording in Pipecat pipelines.

Strands Agents

Native MemoryStore, short-term context hook, tools, and anticipation-stream feed.

CAMEL-AI

Native AgentMemory that augments CAMEL’s history with Synap recall and persistence.

Smolagents

Memory tools and a per-step turn recorder for Hugging Face Smolagents.

deepagents

A memory backend where grep is a semantic search, plus query-conditioned recall middleware.

Claude Agent SDK

Hooks and MCP server for Anthropic’s Claude Agent SDK (Python & TypeScript).

Mastra

SynapMemory class and tools for Mastra (TypeScript).

Vercel AI SDK

Middleware that wraps any Vercel AI SDK model with automatic Synap context.

Vercel eve

Memory tools and a per-turn short-term-context resolver for eve agents.

​

Quick Comparison

​

Prerequisites

import os
from maximem_synap import MaximemSynapSDK, SDKConfig

sdk = MaximemSynapSDK(
    api_key=os.environ["SYNAP_API_KEY"],
    config=SDKConfig(cache_backend="sqlite"),
)
await sdk.initialize()

import { SynapClient } from "@maximem/synap-js-sdk";

const sdk = new SynapClient({
  apiKey: process.env.SYNAP_API_KEY!,
});
await sdk.initialize();

​

Going further

• Patterns overview: reusable memory patterns across frameworks.
• Cookbook overview: end-to-end worked examples.