Membase
Decentralized AI memory layer for autonomous agents
ZK-verified, long-term memory for autonomous agents — persist and sync conversations, knowledge bases, and on-chain task coordination across platforms.
Unibase Memory
Unibase's Chrome client — encrypt, own, and verify cross-AI memory. Powered by Membase; identity via Unibase Pay.
Get started
Install the Membase SDK and sync conversations, knowledge bases, or on-chain tasks from your agents. Membase can also be integrated via MCP (Model Context Protocol) and skill for agent frameworks.
pip install git+https://github.com/unibaseio/membase.git
Quick start
from membase import MembaseClient client = MembaseClient() # Sync conversations, manage knowledge bases, or coordinate on-chain tasks client.sync_conversation(session_id="my-agent", messages=[...])
Or clone locally: github.com/unibaseio/membase
How to use Membase
Sync across platforms and devices
Decentralized memory layer enables cross-platform, cross-device sync of conversations. Agents retain and build on prior interactions anywhere.
Manage knowledge bases
Store and retrieve documents with embeddings. Add and query knowledge for RAG-style agent memory across platforms.
Coordinate on-chain tasks
Register, join, and complete tasks via smart contracts. Reward distribution and task state on-chain.
Architecture
Memory protocol built on Unibase DA — ZK-verified persistence for conversations, knowledge bases, and on-chain tasks. Integrates with AIP for agent communication.
Resources
Unibase stack