Skip to main content
Maximem Synap gives your agents durable long-term memory and efficient short-term context across conversations, your customers, and your whole organization.

​
Synap in 90 seconds

What is Maximem Synap? Synap is a managed memory layer for AI agents. It ingests conversations and documents, extracts structured knowledge (facts, preferences, episodes, emotions, temporal events), and serves ranked, scope-aware context back to your agent at retrieval time.When should I use it?
  • You’re building an agent that needs to remember users, customers, or organizations across sessions.
  • You want structured memory (entities, preferences, episodes) without running a vector DB or building a retrieval pipeline.
  • You need multi-tenant memory scoping (per-user, per-customer, per-org) out of the box.
What languages/runtimes? Python 3.11+ (primary) and JavaScript/TypeScript on Node.js 18+. The JS SDK is a thin wrapper that spawns the Python SDK as a subprocess, so it also requires Python 3.11+ on the host and does not run on Edge Runtime, Cloudflare Workers, Bun, Deno Deploy, or AWS Lambda Node-only runtimes. See Installation. If you’re on Next.js, pin the route to runtime = "nodejs"; Edge is unsupported.Install:
pip install maximem-synap

Start the 10-minute quickstart

Install, create an instance, ingest your first memory, and retrieve it, in 10 minutes.

Try Synap in the live playground

Spin up a working memory agent in the browser. No install, no API key needed.

Quickstart

Zero to working memory in 10 minutes: install the SDK, create an instance, ingest and retrieve.

AI coding agents

Let your AI coding agent wire Synap into your stack. Works with Claude Code, Cursor, Codex, and more.

Setup & Integration

Install, authenticate, and wire Synap into FastAPI / Flask / Next.js / Django.

API Reference

Full Python SDK reference: initialization, ingestion, context fetch, compaction, error handling.

AI Integrations

Drop Synap into LangChain, LangGraph, Vercel AI SDK, CrewAI, LiveKit, MCP, and 14 more.

Guides

Hands-on walkthroughs: first integration, multi-user scoping, production checklist, migration.

Core Concepts

Memory scopes, entity resolution, the ingestion-to-retrieval lifecycle, MACA, and use-case markdown.

Dashboard

Manage instances and memory architecture from the Synap Dashboard.
Pick your stack: each tile jumps straight to the integration you’ll actually use, so you skip the raw-SDK steps you don’t need.

LangChain

LangGraph

Vercel AI SDK

OpenAI Agents

CrewAI

LiveKit

Claude Agent SDK

Pipecat

Mastra

No-code (MCP)

No framework / direct SDK

See all 19 integrations

​
Choose your path

Three common journeys through these docs. Pick the one that matches where you are.

Hobbyist / first agent

  1. Quickstart
  2. First Integration
  3. Memory Model Cheat Sheet
  4. Playground

Framework developer

  1. Choose your stack
  2. Your framework’s integration page
  3. A recipe
  4. Production Checklist

B2B platform team

  1. What is Synap?
  2. Identifiers & Scopes
  3. Multi-tenant SaaS
  4. Security & Trust

​
What can you build

Synap handles the hard parts of agent memory so you can focus on building great AI experiences:
  • Personalized chatbots that remember user preferences, past interactions, and evolving context across sessions
  • Context-aware support agents that recall customer history, previous tickets, and account details without re-asking
  • Agents that learn over time by extracting and retaining facts, preferences, emotions, and temporal events from every conversation
  • Multi-user, memory-scoped applications where each user, customer, or organization has isolated, structured memory boundaries

​
How it works

Three calls, end to end: 
# pip install maximem-synap   ·   export SYNAP_API_KEY=synap_...
from maximem_synap import MaximemSynapSDK

sdk = MaximemSynapSDK()        # reads SYNAP_API_KEY from the environment
await sdk.initialize()

# 1. Ingest a turn after it happens (B2C: user_id only)
await sdk.memories.create(
    document="User: I prefer dark mode.\nAssistant: Got it!",
    document_type="ai-chat-conversation",
    user_id="user_123",
)

# 2. Retrieve relevant memory before the next LLM call
ctx = await sdk.user.context.fetch(
    user_id="user_123",
    search_query=["user preferences"],
)

# 3. Inject ctx.facts / ctx.preferences into your system prompt. Done.
Behind those three calls, Synap categorizes the content, extracts facts, preferences, episodes, emotions, and temporal events, resolves entities across conversations, and stores everything in vector + graph engines. For the full mental model see What is Synap?.

​
Three layers

Synap three layers: your app with the SDK, Synap Cloud handling the managed pipeline and storage, and the Dashboard web UI for configuration and monitoring
ComponentRoleHow you interact
SDKRuns in your application. Handles ingestion, retrieval, auth, streaming.pip install maximem-synap
Synap CloudManaged backend. Pipeline + storage + retrieval.Fully managed, nothing to deploy
DashboardWeb UI for instances, memory architecture, monitoring.synap.maximem.ai
Synap is async-first. The SDK uses Python’s asyncio for non-blocking operations, and the ingestion pipeline processes memories asynchronously so your application stays responsive.