Skip to main content
Synap sits between your application and your LLM, providing a persistent memory layer

​
Key capabilities

Memory Extraction

Automatically extract structured knowledge from raw conversations and documents. Synap identifies and categorizes facts, preferences, episodes, emotions, and temporal events without any manual annotation.

Multi-Scope Memory

Isolate memories at the right boundary. Synap supports a hierarchical scope chain — User, Customer, Client, and World — so personal preferences stay personal while shared knowledge is accessible to everyone who needs it.

Configurable Storage

Memories are stored in both vector and graph storage engines. Vector storage powers semantic similarity search. Graph storage captures relationships between entities. You configure the balance through the Memory Architecture Config.

Context Compaction

Long conversations don’t need to be sent in full every time. Synap compacts conversation context into structured summaries, reducing token usage while preserving the information your agent actually needs.

Entity Resolution

References to the same person, place, or thing across different conversations are automatically resolved. “John”, “John Smith”, and “my manager” all map to a single canonical entity, building a coherent knowledge graph over time.

Real-Time Streaming

For latency-sensitive applications, Synap supports gRPC streaming. Stream memories in and context out without waiting for full HTTP round-trips.

​
Architecture at a glance

Synap follows a clean separation of concerns across three layers: 
┌─────────────────────┐     ┌─────────────────────────────────────────┐
│   Your Application  │     │             Synap Cloud                  │
│                     │     │                                         │
│  ┌───────────────┐  │     │  ┌──────────┐  ┌────────────────────┐  │
│  │   Synap SDK   │──┼─────┼─>│ Auth     │─>│ Ingestion Pipeline │  │
│  │               │  │     │  │ Gateway  │  │                    │  │
│  │  - Ingest     │  │     │  └──────────┘  │ Categorize         │  │
│  │  - Retrieve   │  │     │                │ Extract            │  │
│  │  - Stream     │  │     │                │ Chunk              │  │
│  └───────────────┘  │     │                │ Organize           │  │
│                     │     │                │ Resolve Entities   │  │
└─────────────────────┘     │                └────────────────────┘  │
                            │                         │              │
┌─────────────────────┐     │  ┌──────────┐  ┌───────┴──────────┐  │
│     Dashboard       │     │  │ Analytics│  │  Storage Layer    │  │
│                     │     │  │          │  │  - Vector Store   │  │
│  - Manage Instances │     │  │ - Metrics│  │  - Graph Store    │  │
│  - Configure Memory │     │  │ - Logs   │  │  - PostgreSQL     │  │
│  - Monitor Pipeline │     │  └──────────┘  └──────────────────┘  │
│  - Team Management  │     │                                       │
└─────────────────────┘     └───────────────────────────────────────┘
SDK lives in your application. It handles authentication, ingestion requests, retrieval queries, and optional gRPC streaming. The SDK never self-asserts identity — all authentication flows through Synap Cloud using a zero-trust model. Synap Cloud is the managed backend. It runs the multi-stage ingestion pipeline (categorize, extract, chunk, organize, resolve entities), stores memories across vector and graph engines, and serves retrieval queries. You never deploy or manage this infrastructure. Dashboard is the web management interface. Create and manage instances, configure memory architecture, monitor ingestion pipelines, manage team access, and set up webhooks.

​
Key components

ComponentWhat it isWhat it does
SDKPython library installed in your applicationProvides the programmatic interface for ingesting memories, retrieving context, and managing the memory lifecycle
DashboardWeb UI at synap.maximem.aiManage instances, configure memory architecture, monitor pipelines, and collaborate with your team
Memory Architecture Config (MACA)YAML-based configurationDefines how memory is stored, what gets extracted, retrieval strategies, and retention policies for each instance
InstancesDeployed agent memory containersEach instance is an isolated memory environment with its own configuration, storage, and scope hierarchy. Identified by inst_<hex16>
ClientsOrganization-level containersA client represents your organization or application. Contains one or more instances. Identified by cli_<hex16>
ScopesMemory isolation boundariesHierarchical boundaries (User > Customer > Client > World) that control who can access which memories

​
The memory lifecycle

Every piece of content that enters Synap follows a structured pipeline:
1

Ingestion

Raw content (conversations, documents, notes) is submitted through the SDK. Each ingestion is tagged with a scope (user, customer, etc.) and document type.
2

Categorization

The pipeline classifies the content type and determines which extraction strategies to apply based on the Memory Architecture Config.
3

Extraction

Structured knowledge is extracted: facts (“User lives in San Francisco”), preferences (“User prefers dark mode”), episodes (“User signed up last Tuesday”), emotions (“User was frustrated with billing”), and temporal events.
4

Entity Resolution

Extracted entities are resolved against the existing knowledge graph. New entities are auto-registered at the appropriate scope. The resolution follows the scope chain: User > Customer > Client > World.
5

Storage

Resolved memories are stored in both vector storage (for semantic search) and graph storage (for relationship traversal). Storage configuration is driven by MACA.
6

Retrieval

When your agent needs context, Synap retrieves and ranks relevant memories from both storage engines, respecting scope boundaries and applying the configured retrieval strategy.
The entire pipeline runs asynchronously. When you call sdk.memories.create(), the SDK returns immediately with an ingestion ID. You can track ingestion status through the SDK or Dashboard.

​
Next steps

Quickstart

Get up and running with Synap in under 10 minutes.

Installation

Detailed installation instructions, environment configuration, and dependency options.

Authentication

Understand Synap’s zero-trust authentication model, API keys, and credential management.

Core Concepts: Scopes

Deep dive into memory scoping and isolation boundaries.