Client

The MemoAir client is your entry point to all SDK functionality. It provides both synchronous and asynchronous interfaces.

Installation

pip install memoair

Quick Start

quickstart.pypython

1from memoair import MemoAir
2
3# Initialize with API key
4client = MemoAir(api_key="memoair_sk_...")
5
6# Or use environment variable (recommended)
7# export MEMOAIR_API_KEY="memoair_sk_..."
8client = MemoAir()
9
10# Access resources
11client.memories    # Episodic memory operations
12client.search      # Semantic search
13client.facts       # Explicit facts/triplets
14client.documents   # Document ingestion
15client.ontology    # Schema management
16client.agent       # Conversational agent

POSTMemoAir()

Initialize a new MemoAir client instance.

Parameters

api_keystr | NoneOptionalDefault: None

Your MemoAir API key. Falls back to the MEMOAIR_API_KEY environment variable if not provided.

base_urlstr | NoneOptionalDefault: None

Base URL for the MemoAir API. Falls back to MEMOAIR_BASE_URL environment variable.

graph_urlstr | NoneOptionalDefault: None

URL for the graph service. Falls back to MEMOAIR_GRAPH_URL environment variable.

timeoutfloatOptionalDefault: 30.0

Request timeout in seconds.

max_retriesintOptionalDefault: 3

Maximum number of retry attempts for failed requests.

on_requestCallable[[httpx.Request], None] | NoneOptionalDefault: None

Optional callback function called before each request.

on_responseCallable[[httpx.Response], None] | NoneOptionalDefault: None

Optional callback function called after each response.

Async Client

For async applications, use AsyncMemoAir with the same interface:

async_example.pypython

1from memoair import AsyncMemoAir
2import asyncio
3
4async def main():
5    async with AsyncMemoAir(api_key="memoair_sk_...") as client:
6        # All methods are async
7        await client.memories.add(
8            group_id="user:123",
9            messages=[...]
10        )
11
12        results = await client.search.tripartite(
13            query="What do I know about the user?",
14            user_id="user:123"
15        )
16
17asyncio.run(main())

Context Manager

Both clients support context managers for automatic resource cleanup:

1# Sync
2with MemoAir() as client:
3    client.memories.add(...)
4
5# Async
6async with AsyncMemoAir() as client:
7    await client.memories.add(...)

Available Resources

client.memories

Add and retrieve episodic memory from conversations.

client.search

Semantic search across knowledge graphs.

client.facts

Create and manage explicit facts/triplets.

client.documents

Upload and process documents.

client.ontology

Load and manage domain schemas.

client.agent

Conversational agent with tool use.