Mimir LangGraph Integration

Drop-in persistent long-term memory for LangGraph agents via Mimir.

Install

Install from source (not yet published to PyPI):

pip install langgraph
pip install -e integrations/langgraph/

Quick Start

from mimir_langgraph import MimirStore

# Create a Mimir-backed store
store = MimirStore(
    binary="mimir",  # or /usr/local/bin/mimir
    db_path="~/.mimir/data/mimir.db",
)

# Use as a drop-in BaseStore replacement
store.put(("users", "123"), "preferences", {"theme": "dark", "language": "en"})

item = store.get(("users", "123"), "preferences")
print(item.value)  # {"theme": "dark", "language": "en"}

# Search across namespaces
results = store.search(("users",), query="preferences theme")
for r in results:
    print(r.key, r.value, r.score)

Integration with LangGraph Agents

from langgraph.graph import StateGraph
from langgraph.store.base import BaseStore
from mimir_langgraph import MimirStore

# Use MimirStore as your long-term memory
store = MimirStore()

# Build your graph with store
graph = (
    StateGraph(AgentState)
    .add_node("agent", agent_node)
    .compile(store=store)
)

The store persists across sessions. Agents can retrieve context from previous interactions using store.search().

Configuration

How It Works

LangGraph's BaseStore interface maps cleanly onto Mimir's entity model:

Requirements

• Mimir v1.0.0+ installed (curl -sSL https://raw.githubusercontent.com/Perseus-Computing-LLC/mimir/main/scripts/bootstrap.sh | bash)
• LangGraph >= 0.2.0
• Python 3.10+