Walrus-backed LangGraph checkpoint storage on Sui. Store, retrieve, and manage agent memory across sessions — decentralised, verifiable, permanent.
Replace SqliteSaver with WalrusCheckpointer. That's it. Your agent's memory is now stored on Walrus and registered on the Sui blockchain.
from memwal.checkpoint import WalrusCheckpointer # One line — loads config from .env checkpointer = WalrusCheckpointer.from_env() # Drop-in replacement for SqliteSaver graph = builder.compile(checkpointer=checkpointer) # Agent memory is now on Walrus + Sui result = graph.invoke( {"messages": [HumanMessage(content="Hello, remember me!")]}, config={"configurable": {"thread_id": "agent-001"}} )
A complete decentralised memory layer for LangGraph agents.
Checkpoint data survives across sessions, machines, and deployments. Stored on Walrus, registered on Sui.
Store arbitrary binary data as Walrus blobs. Automatic retry with exponential backoff on transient failures.
Fetch checkpoints by thread_id via the Sui on-chain registry. Any agent instance can resume any thread.
Thread-scoped checkpoints with namespace support. Multi-agent systems share a single registry.
Thread→blob mappings stored as Sui Move dynamic fields. Verifiable, transparent, immutable.
Interactive testing environment. Send requests, inspect responses, explore memory state in real-time.
From agent input to decentralised storage and back.
From personal assistants to multi-agent orchestration systems.
Give agents persistent, verifiable memory that survives across sessions and deployments.
Build assistants that remember conversations, preferences, and context permanently.
Coordinate agents through shared on-chain state. Any agent can resume any thread.
Accumulate and retrieve structured knowledge over time with checkpoint versioning.
Long-running research tasks with durable state. Resume from any checkpoint.
Decentralised, permanent storage for agent memory. No single point of failure.
Open the interactive playground to test every API endpoint, explore memory state, and build with templates.
Open Playground