Memory Browser
Explore and manage your AI's knowledge base visually.
The Memory Browser provides a visual interface to explore, search, and manage all stored memories in the Qdrant vector database.
Search
🔍 Semantic Search
Natural language queries find related content via vector similarity.
📁 Category Filter
Filter by architecture, coding-rules, anti-patterns,
service-context.
🏷️ Tag Filter
Search by specific tags for precise results.
Categories & Types
| Category | Purpose | Examples |
|---|---|---|
architecture | System design decisions | "Use PostgreSQL for relational data" |
coding-rules | Code style and conventions | "Always use TypeScript strict mode" |
anti-patterns | Things to avoid | "Never use any type" |
service-context | Project-specific knowledge | "Auth service uses JWT with refresh tokens" |
| Type | Purpose |
|---|---|
rule | Enforced coding or architecture rule |
memory | General project knowledge |
anti-pattern | Known bad practice to avoid |
guide | How-to or reference |
decision | Recorded design decision |
Managing Memories
Store memories via the desktop chat, IDE, or MCP tools:
Store in memory: Our API uses rate limiting of 100 req/min per user.
Tag it as: api, rate-limiting, infrastructure
Category: service-contextClick any memory to view its contents, category, tags, and metadata.
Select memories and delete them. Use delete_memory with IDs for batch deletion via MCP.