Skip to main content
Organization memory lets the assistant remember things across sessions - preferences, key addresses, protocols of interest, and workflow conventions. It’s shared across all users in your org, so everyone benefits from stored context.

​
How it works

Organization memory is a persistent key-value store shared across your org. Any user can read or write entries, and the assistant proactively uses stored context to give better answers. The assistant:
  • Reads memory at the start of conversations to understand your org’s context
  • Writes memory when it learns useful patterns, preferences, or configurations
  • Asks for confirmation before storing anything

​
What to store

Key addresses

Treasury wallets, contract addresses, multisigs

Preferences

Preferred chains, default time ranges, chart styles

Protocol context

Which protocols your org tracks, naming conventions, internal terminology

Patterns

Common query patterns, known data caveats, reusable SQL snippets

​
Example usage

​
Storing context

The assistant stores these as key-value entries like:
  • treasury_wallet → 0x742d35Cc6634C0532925a3b844Bc9e7595f2bD28
  • focus_area → DeFi on Ethereum and Arbitrum - Uniswap, Aave, Compound
  • our_pools_definition → Uniswap v3 pools where treasury wallet is LP

​
Recalling context

Returns all stored entries with who last updated each one and when.
The assistant retrieves the specific key and uses it in queries automatically.

​
Using memory in analysis

Once context is stored, the assistant uses it proactively:
The assistant knows to look up 0x742d35... without you specifying the address again.
It knows “our pools” means Uniswap v3 LP positions for your treasury wallet.

​
Limits

​
What is NOT stored

  • Sensitive personal data - personal wallets, credentials, private keys
  • Session-specific context - the assistant already remembers everything within a conversation
  • Data meant for one user - memory is org-wide, not per-user
Organization memory is shared with all users in your org. Don’t store anything you wouldn’t want every team member to see.

​
Managing memory

You can manage stored entries through conversation:
The assistant asks for confirmation before any updates or deletions.