Vector Memory

Vector Memory

Long-term memory that persists across sessions. Store facts, decisions, lessons, preferences — recall them later via semantic search.

Vector memory is a retrieval layer, not a source of truth. Files and code are the source of truth; vector memory helps you find relevant context fast.

References

• [tools-reference.md](references/tools-reference.md) — All MCP tools with full parameter docs
• [retrieval-internals.md](references/retrieval-internals.md) — Hybrid pipeline, Weibull decay model (load when debugging retrieval)

---

When to Store

| Signal | Category | Example | |--------|----------|---------| | User states a preference | preference | "I prefer tabs over spaces" | | A fact is established | fact | "The API uses OAuth 2.0 with PKCE" | | A decision is made with rationale | decision | "Chose PostgreSQL over MongoDB because..." | | A mistake was made and corrected | lesson | "CSS not applying → check for syntax errors above" | | An important entity is introduced | entity | "Acme Corp is the client, contact: jane@acme.com" | | A reusable technique is learned | skill | "Remotion animations use interpolate()" |

When NOT to Store

• Temporary task state (use files)
• Things already in committed code or docs
• Conversation summaries ("today we discussed X") — store the extracted knowledge, not the summary
• Obvious facts the user can easily re-state

---

Memory Hygiene

1. Short and atomic — Each memory ` | Agent-private (default) |

| project: | Project-scoped | | user: | User-scoped |

memory_store(text: "...", scope: "project:acme")
memory_recall(query: "...", scope: "project:acme")

---

Quick Reference

Store

memory_store(text: "...", category: "fact", importance: 0.7)

Recall

memory_recall(query: "database migration strategy", category: "decision", limit: 5)

Good queries describe the situation, not the exact stored text. Vector search finds semantic matches.

Update

memory_update(memoryId: "a0e8d0fb", text: "Updated: now using OAuth 2.1")

For preference and entity, text changes create a new version (supersede) — history is preserved.

Merge

memory_merge(primaryId: "a0e8d0fb", secondaryId: "3c31e862", mergedText: "Combined memory")

Forget

memory_forget(memoryId: "a0e8d0fb")
memory_forget(query: "outdated migration plan")

History

memory_history(memoryId: "a0e8d0fb", direction: "both")

---

Setup

Requires @cablate/memory-lancedb-mcp — see [mcp.example.json](../../mcp.example.json) for configuration.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: cablate
• Source: cablate/ai-toolkit
• License: MIT

Install and usage instructions live in the source repository linked above.