Skip to main content
POST
https://memorymachines-core-api-mvp-gateway-6v1lw71z.uc.gateway.dev
/
v1
/
memories
/
ask
curl -X POST https://memorymachines-core-api-mvp-gateway-6v1lw71z.uc.gateway.dev/v1/memories/ask \
  -H "x-api-key: YOUR_API_KEY" \
  -F "text=What did we decide about the product launch timeline?"

{
  "response": "Based on your meeting notes from January 15th, the team decided to push the product launch to end of February. Sarah recommended the delay to ensure the authentication feature is fully tested. Mike agreed, noting that rushing could hurt user trust. The new target date is February 28th, with a beta release planned for February 15th."
}
Query your memories using natural language and receive an AI-synthesized response based on relevant memories.
​
text
string
required
Your question or query. Max 1,000 characters.
curl -X POST https://memorymachines-core-api-mvp-gateway-6v1lw71z.uc.gateway.dev/v1/memories/ask \
  -H "x-api-key: YOUR_API_KEY" \
  -F "text=What did we decide about the product launch timeline?"

{
  "response": "Based on your meeting notes from January 15th, the team decided to push the product launch to end of February. Sarah recommended the delay to ensure the authentication feature is fully tested. Mike agreed, noting that rushing could hurt user trust. The new target date is February 28th, with a beta release planned for February 15th."
}

​
How It Works

  1. Your query is embedded using the same model as your memories
  2. Semantic search finds the most relevant memories
  3. GPT synthesizes an answer based on the retrieved context
  4. The response is personalized to your data

​
Tips for Better Results

“What did Sarah say about the deadline?” works better than “What happened?”
“What did we discuss in last week’s planning meeting?” gives the AI helpful constraints
If the first answer isn’t complete, ask a more specific follow-up question