Local Memory
Local Memory
Section titled “Local Memory”Local memory
What it does
Section titled “What it does”Maintains conversation history locally for AI agents to reference previous messages.
The history is stored in your browser (IndexedDB), under the conversation you pick. It survives across runs and browser restarts.
How messages are read and saved
Section titled “How messages are read and saved”Local Memory doesn’t save anything by itself — the agent it’s connected to does:
- Before calling the model, the agent loads the conversation’s earlier messages from the memory and adds them to the prompt as chat history.
- It saves the incoming message as a
usermessage. - After the model (and any tools) answer, it saves the reply as an
assistantmessage. A structured reply from an output parser is saved as JSON text.
Each save notifies any open view of that conversation (the chat memories page, a Chat Trigger window), so they update right away.
When to use it
Section titled “When to use it”Connect this to AI agents that need to remember context across multiple interactions in a conversation. It’s also the usual memory for a Chat Trigger: connect the same Local Memory to the trigger and to the agent, and the chat window shows this conversation.
Inputs and settings
Section titled “Inputs and settings”| Setting | Notes |
|---|---|
| Memory | The conversation to read from and save to. Pick an existing conversation or create one. Required — the agent fails with “Conversation ID is required” if it’s empty. |
Outputs
Section titled “Outputs”Returns a memory dependency for conversational AI workflows.
Dependencies and credentials
Section titled “Dependencies and credentials”- No explicit credential or node dependency is declared in the node description.
Example workflow
Section titled “Example workflow”Connect Local Memory to an AI agent or dependency input that accepts this dependency type, then run the agent with data from previous nodes.
Troubleshooting
Section titled “Troubleshooting”- Check that a conversation is selected in Memory.
- If several agents use the same Local Memory, each one saves its own user message and reply to the same conversation.
- Local Memory vs Persistent Chat Memory: both store history the same way. Local Memory points to a conversation you pick; Persistent Chat Memory uses a text key you type, which is easier to reuse across workflows.
- If the node uses browser page data, run it on the target tab after the page has loaded.
- If it calls an external service, verify credentials, permissions, and rate limits.
- This node has source tests; use them as the reference for edge-case behavior during maintenance.