memory_search and memory_add. Memory stays off until a provider is configured under Settings → Memory, an admin turns memory on for the tenant, and an agent enables it.
Supported providers
The list comes from the shipped
memory-catalog.yaml. Self-hosted deployments can override the catalog.
Configure a provider
- Open Settings → Memory and choose the Zep preset.
- Paste your Zep API key. Leave Server URL blank for Zep Cloud, or enter the URL of a self-hosted Zep.
- Save.
Turn memory on for the tenant
Settings → Memory → Allow memory is the tenant-wide switch, and it is on by default. Agents keep their own memory setting while it is off, so turning the switch back on restores memory for them without editing each agent. In TrueFoundry mode this switch is per tenant. See Turning memory off for what changes while it is off.Enable memory on an agent
Once memory is available, the UI turns the toggle on for new agents. Agents created through the API keep the schema default,
{ "enabled": false }, until you set the field. Chats started from New Chat, without a saved agent, use the user’s general memory whenever the tenant allows memory.
The Memory toggle is hidden until a provider is configured, and can’t be turned on while Allow memory is off; through the API, both cases return a
422. An agent that already has memory on keeps working if memory later becomes unavailable, just without memory; see Turning memory off.What the agent gets
- Memory at the start of a chat. When a chat starts, the agent gets a short summary of what it remembers about the user. If memory is slow to load, the chat starts without it.
memory_searchlooks up details about the user in natural language, such as preferences, ongoing work, or people they mention, and returns the matching facts.memory_addsaves something the user asks the agent to remember. The agent doesn’t save on its own initiative.
How memory works
When memory is enabled, chats are processed in the background, and relevant details become available in later chats. This happens asynchronously and can take some time, so something mentioned in a chat may not be remembered right away. To make sure something is remembered, ask the agent to remember it in the chat, for example:Remember that I prefer answers in metric units.The agent saves it with
memory_add, and it is used in future chats once saved. Agents only save when asked.
Memory is per user. A user’s New Chat memory and their memory on each agent are kept separate, and one user never reads another’s. Agent-builder chats and scheduled runs aren’t remembered.
Turning memory off
Memory can be turned off for the whole tenant with Allow memory, or for one agent with its Memory toggle. Unlike web search and the sandbox, where chats that already use a capability keep it, turning memory off takes effect in existing chats too:- The agent stops reading memory from previous chats, including in chats started while memory was on.
- The agent can no longer save anything new to memory.
- Chats are no longer processed for memory.
Manage memory through the API
GET /api/v1/settings/memory-providersreads the provider, with the key redacted.PUT /api/v1/settings/memory-providerscreates, replaces, or rotates the key.GET /api/v1/catalogs/memory-providerslists the presets.PATCH /api/v1/settings/configurationwith{ "manifest": { "memory": { "enabled": true } } }turns memory on for the tenant.GET /api/v1/capabilitiesreports whether memory is available.