Agent memory
Store, search, and forget memories for your agents, semantic recall on your own namespace, no vector DB to run.
POST/v1/memory
The example in the published schema
charged 00 credits
- auth (bearer key)
- per-key throttle
- validate body
- balance precheck
- run the capability
- charge credits ON SUCCESS ONLY
- JSON
The request body/v1/memory
{ "op": "search", "namespace": "agent-42", "query": "what does the customer prefer for delivery?", "limit": 3 }
The responsepublished example
// sending the call
// 0 credits charged so farcurl https://api.thecompound.tech/v1/memory \
-H "Authorization: Bearer $COMPOUND_API_KEY" \
-H "Content-Type: application/json" \
-d '{"op":"search","namespace":"agent-42","query":"what does the customer prefer for delivery?","limit":3}'Scored
7 of 7 field checks passed when the eval suite last ran against production, on 2026-07-08. Every endpoint's score
The Media & agents guide has this endpoint with its example response. The reference has every parameter.
More from Media & agents
Transcription pausedAn audio recording → accurate text with speakers and paragraph timestamps. Meetings, calls, voice notes.Image generation $0.10/imageA prompt → a production-ready image. Marketing visuals, product scenes, and consistent brand imagery.Text to speech $0.05/clipText → natural speech audio, ready to embed. Voice notes, IVR lines, narration.