New research from Maximem. Agentic Context Management: Agent Memory is an architecture problem. Read the paper →

Synap · Integrations

Native memory for every agent framework you ship on.

Maximem Synap ships 23 native framework integrations today — each with a dedicated docs page and, for our flagship integrations, a deep-dive blog post. Every integration is in production and verified against docs.maximem.ai/integrations.

  • LangChain

    LangChain

    Drop-in memory provider for LangChain chains and agents — replaces ConversationBufferMemory with persistent, cross-session recall.

  • LangGraph

    LangGraph

    Persistent memory across LangGraph nodes — state that survives graph reruns, checkpoints, and human-in-the-loop pauses.

  • LlamaIndex

    LlamaIndex

    Long-term agent memory for LlamaIndex query engines, workflows, and agentic retrievers.

  • OpenAI Agents

    OpenAI Agents

    Native memory tool for the OpenAI Agents SDK — drop into any agent loop without rewriting tool definitions.

  • Pydantic AI

    Pydantic AI

    Typed memory backing for Pydantic AI agents — model-validated reads and writes, no string parsing.

  • CrewAI

    CrewAI

    Shared memory across CrewAI crews and tasks — every agent in the crew sees the same evolving context.

  • AutoGen

    AutoGen

    Cross-conversation memory for AutoGen multi-agent groups — durable state outside a single GroupChat run.

  • Google ADK

    Google ADK

    Memory layer for Google Agent Development Kit agents — built for ADK sessions and tool-calling loops.

  • Haystack

    Haystack

    Persistent context for Haystack pipelines and agents — memory components that compose with existing nodes.

  • Agno

    Agno

    Memory provider for Agno agent workflows — keeps team and session memory in sync across runs.

  • Semantic Kernel

    Semantic Kernel

    Memory plugin for Microsoft Semantic Kernel — works in both the Python and .NET SDKs.

  • Microsoft Agent Framework

    Microsoft Agent Framework

    Memory backing for the Microsoft Agent Framework — drop-in for any AgentChat or Group conversation.

  • NeMo Agent Toolkit

    NeMo Agent Toolkit

    Memory toolkit for NVIDIA NeMo Agent Toolkit — integrates with NeMo agent and workflow primitives.

  • LiveKit Agents

    LiveKit Agents

    In-conversation memory for LiveKit voice agents, under 15ms at P75, with anticipatory retrieval fast enough for real-time turn-taking.

  • Pipecat

    Pipecat

    Real-time conversational memory for Pipecat pipelines — built for voice-first agent loops.

  • Claude Agent SDK

    Claude Agent SDK

    Memory tool for the Claude Agent SDK — usable from any Claude agent loop without custom glue code.

  • Mastra

    Mastra

    TypeScript memory module for Mastra agent flows — typed reads and writes from any Mastra workflow node.

  • Vercel AI SDK

    Vercel AI SDK

    Server-side memory layer for the Vercel AI SDK — wraps streamText / generateText with persistent context.

  • Vercel eve

    Vercel eve

    Memory tools plus a per-turn short-term-context resolver for Vercel eve agents, in TypeScript.

  • Strands Agents

    Strands Agents

    Native MemoryStore for Strands Agents — short-term context hook, memory tools, and a real-time anticipation feed.

  • CAMEL-AI

    CAMEL-AI

    Native AgentMemory for CAMEL-AI — long-term recall layered over the agent's own conversation history.

  • Smolagents

    Smolagents

    Memory tools and a per-step turn recorder for Hugging Face Smolagents — persistence across agent runs.

  • deepagents

    deepagents

    Backend and two middlewares for deepagents agents: persistence across runs and sub-agents.

Other ways in

Not on one of the frameworks above, or not on a framework at all. Synap works from anywhere.

Not on a framework

Python SDK (Python 3.11 and above), TypeScript SDK (Node 20 and above, native rather than a wrapper), and a REST API from any language.

SDK reference

No-code tools and coding agents

A hosted MCP endpoint, or self-host the adapter. Point any MCP-aware tool at it and it has memory.

MCP guide

From a terminal

The CLI, for provisioning and operating Synap without opening a dashboard. Install with pipx, Homebrew, or a one-line installer.

CLI guide
app.ts
const { createClient } = require('@maximem/synap-js-sdk');

const client = createClient({ apiKey: 'your-api-key' });
await client.init();

// Send the conversation as it happens. Returns immediately.
await client.conversation.recordMessage({
  conversationId: 'mon-standup',
  userId: 'alice',
  role: 'user',
  content: "I'm migrating our auth service to OAuth2 this sprint.",
});

// Ask what is known, before your agent replies.
const context = await client.fetchUserContext({
  userId: 'alice',
  query: 'what is alice working on?',
});
console.log(context.formattedContext);

Coming from another vendor

Real import jobs from other memory providers, with field mapping and read-back verification, not an export file and instructions. Migrations in the docs →

Your organisation’s context, kept current

First-party connectors that pull your organisation’s own context continuously, so agents know your product, policies and pricing, not only the user.

  • Google Drive
  • Notion
  • SharePoint
  • Slack
  • Linear
  • Mintlify
  • Zendesk

Or upload files, or send it over the API. Whatever the source, it lands at the client level of your hierarchy and reaches every agent that should see it. How scoping works →

Building on a framework we don't list yet?

The Synap SDK (Python and TypeScript) and REST API work from anywhere — and most new framework adapters land within a release. Tell us what you're shipping on.