Python SDK

The official Python client for SharedMemory.

pip install sharedmemory

Requires Python 3.8+.

Quick Start

from sharedmemory import SharedMemory

memory = SharedMemory(
    api_key="sm_live_...",
    volume_id="your-project-id",
)

# Store a memory
result = memory.add("User prefers dark mode and compact layout")

# Search memories
results = memory.search("user preferences")
for source in results["sources"]:
    print(source["content"], source["score"])

Configuration

Option	Type	Default	Description
api_key	str	—	Required. API key (sm_live_..., sm_agent_..., etc.)
base_url	str	https://api.sharedmemory.ai	API endpoint
volume_id	str	—	Default project (volume) for all operations
user_id	str	—	Scope memories to a specific user
agent_id	str	—	Scope memories to a specific agent

Methods

Memory

Method	Description
add(content, **opts)	Store a memory
search(query, **opts)	Search memories
add_many(items)	Store multiple memories in batch
feedback(memory_id, rating, reason?)	Submit feedback on a memory

Sessions

Method	Description
start_session(session_id, **opts)	Start a conversation session
end_session(session_id, auto_summarize?)	End session with optional summarization

Graph

Method	Description
get_entity(name)	Get entity details and relationships
get_graph()	Retrieve the full knowledge graph

Context

Method	Description
assemble_context(template_id?)	Assemble optimized context for LLM prompting

Entity Scoping

Scope memories to specific users, agents, or sessions:

memory = SharedMemory(
    api_key="sm_live_...",
    volume_id="vol-uuid",
    user_id="user-123",
    agent_id="chatbot-1",
)

# All operations are automatically scoped
memory.add("User asked about pricing", session_id="sess-abc")
results = memory.search("pricing", session_id="sess-abc")

Advanced Search

# With reranking
results = memory.search(
    "project deadlines",
    rerank=True,
    rerank_method="llm",
    include_context=True,
)

# With metadata filters
results = memory.search("preferences", filters={
    "AND": [
        {"field": "memory_class", "op": "eq", "value": "preference"},
        {"field": "score", "op": "gte", "value": 0.5},
    ]
})

Async Client

For async/await usage:

from sharedmemory import AsyncSharedMemory

memory = AsyncSharedMemory(
    api_key="sm_live_...",
    volume_id="your-project-id",
)

result = await memory.add("User prefers dark mode")
results = await memory.search("preferences")

PyPI

https://pypi.org/project/sharedmemory/

License

MIT