Security & Data
Semantic Memory API Reference
Read, search, delete, and clear memory entries for cross-session continuity features.
7 minUpdated 2026-02-15
Summary
Read, search, delete, and clear memory entries for cross-session continuity features.
4 deep-dive sections1 code samples
Quick Start
- Pick default retention and privacy mode.
- Set webhook secrets and verify signatures.
- Limit key scope and rotate periodically.
- Run access and data-deletion checks quarterly.
Endpoints
| Method | Path | Purpose |
|---|---|---|
| GET | /api/v1/memory?limit=20 | List recent memory entries |
| GET | /api/v1/memory/search?q=...&top_k=4&min_score=0.5 | Similarity search |
| DELETE | /api/v1/memory/{memory_id} | Delete one memory item |
| DELETE | /api/v1/memory | Clear all memory entries |
Retrieval flow
How memory is used in chat
1
User prompt
Current request text
2
Similarity lookup
Find top matching memories
3
Context injection
Attach memory summary into model input
4
Response
Improved continuity across sessions
Search call example
curl -G https://llmwise.ai/api/v1/memory/search \
-H "Authorization: Bearer mm_sk_YOUR_KEY" \
--data-urlencode "q=What decision did we make about retries?" \
--data-urlencode "top_k=4"
Zero-retention behavior
When zero-retention mode is enabled, memory APIs return disabled behavior and no persisted entries.
Privacy precedence
Privacy mode takes precedence over memory convenience. Zero-retention disables retained memory retrieval by design.
Docs Assistant
ChatKit-style guided help
Product-scoped assistant for LLMWise docs and API usage. It does not answer unrelated topics.
Sign in to ask implementation questions and get runnable snippets.
Sign in to use assistantPrevious
Privacy, Security, and Data Controls
Next
Webhooks and System Sync