Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.sxth.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Storage

sxth-mind supports pluggable storage backends for persisting cognitive state.

​
Available Backends

​
Memory (Default)

In-memory storage. Data is lost when the process exits. Good for development and testing. 
from sxth_mind import Mind
from examples.sales import SalesAdapter

# Memory storage is the default
mind = Mind(adapter=SalesAdapter())

​
SQLite

Persistent storage using SQLite. Good for single-server deployments. 
pip install sxth-mind[sqlite]

from sxth_mind import Mind
from sxth_mind.storage import SQLiteStorage
from examples.sales import SalesAdapter

mind = Mind(
    adapter=SalesAdapter(),
    storage=SQLiteStorage("mind.db"),
)
The SQLite storage automatically creates these tables:
  • user_minds — User-level state
  • project_minds — Project-specific state
  • memories — Conversation history
  • nudges — Proactive suggestions

​
Custom Storage

Implement the BaseStorage interface for custom backends (Redis, PostgreSQL, MongoDB, etc.): 
from sxth_mind.storage.base import BaseStorage
from sxth_mind.schemas import UserMind, ProjectMind, ConversationMemory, Nudge

class MyStorage(BaseStorage):
    async def initialize(self) -> None:
        """Initialize the storage (create tables, connections, etc.)."""
        pass

    async def close(self) -> None:
        """Clean up resources."""
        pass

    # UserMind operations
    async def get_user_mind(self, user_id: str) -> UserMind | None:
        ...

    async def save_user_mind(self, user_mind: UserMind) -> None:
        ...

    async def delete_user_mind(self, user_id: str) -> None:
        ...

    # ProjectMind operations
    async def get_project_mind(self, user_id: str, project_id: str) -> ProjectMind | None:
        ...

    async def save_project_mind(self, project_mind: ProjectMind) -> None:
        ...

    async def get_project_minds_for_user(self, user_id: str) -> list[ProjectMind]:
        ...

    async def delete_project_mind(self, user_id: str, project_id: str) -> None:
        ...

    # Memory operations
    async def get_memory(self, project_mind_id: str) -> ConversationMemory | None:
        ...

    async def save_memory(self, memory: ConversationMemory) -> None:
        ...

    # Nudge operations
    async def get_pending_nudges(self, user_id: str) -> list[Nudge]:
        ...

    async def save_nudge(self, nudge: Nudge) -> None:
        ...
Then use it: 
mind = Mind(adapter=SalesAdapter(), storage=MyStorage())

​
Storage Lifecycle

When using the HTTP API, storage is initialized and closed automatically via FastAPI’s lifespan: 
from sxth_mind.api import create_app

app = create_app(
    adapter=SalesAdapter(),
    storage=SQLiteStorage("mind.db"),  # Initialized on startup, closed on shutdown
)
For direct usage, initialize manually if needed: 
storage = SQLiteStorage("mind.db")
await storage.initialize()

mind = Mind(adapter=SalesAdapter(), storage=storage)

# ... use mind ...

await storage.close()

​
Data Model

All storage backends persist these entities:
EntityDescriptionKey
UserMindUser-level stateuser_id
ProjectMindProject-specific state(user_id, project_id)
ConversationMemoryMessage historyproject_mind_id
NudgeProactive suggestionsid
Data is serialized as JSON using Pydantic’s model_dump_json() and deserialized with model_validate_json().