claude-mem/docs/public/architecture/search-architecture.mdx

---
title: "Search Architecture"
description: "mem-search skill with HTTP API and progressive disclosure"
---

# Search Architecture

Claude-Mem uses a skill-based search architecture that provides intelligent memory retrieval through natural language queries. This replaced the MCP-based approach in v5.4.0, saving ~2,250 tokens per session start. The skill was enhanced and renamed to "mem-search" in v5.5.0 for better scope differentiation.

## Overview

**Architecture**: Skill-Based Search + HTTP API + Progressive Disclosure

**Key Components**:
1. **mem-search Skill** (`plugin/skills/mem-search/SKILL.md`) - Auto-invoked when users ask about past work
2. **HTTP API Endpoints** (10 routes) - Fast, efficient search operations on port 37777
3. **Worker Service** - Express.js server with FTS5 full-text search
4. **SQLite Database** - Persistent storage with FTS5 virtual tables
5. **Chroma Vector DB** - Semantic search with hybrid retrieval

**v5.5.0 Enhancement**: Renamed from "search" to "mem-search" with:
- Effectiveness increased from 67% to 100%
- Concrete triggers increased from 44% to 85%
- 5+ unique identifiers for better scope differentiation
- Comprehensive documentation (17 files, 12 operation guides)

## How It Works

### 1. User Query (Natural Language)

```
User: "What bugs did we fix last session?"
```

### 2. Skill Invocation

Claude recognizes the intent and invokes the mem-search skill:
- Skill frontmatter (~250 tokens) loaded at session start
- Full skill instructions loaded on-demand when skill is invoked
- Progressive disclosure pattern minimizes context overhead
- "mem-search" naming provides clear scope differentiation from native memory

### 3. HTTP API Call

The skill uses `curl` to call the HTTP API:

```bash
curl "http://localhost:37777/api/search/observations?query=bugs&type=bugfix&limit=5"
```

### 4. FTS5 Search

Worker service queries SQLite FTS5 virtual tables:

```sql
SELECT * FROM observations_fts
WHERE observations_fts MATCH ?
AND type = 'bugfix'
ORDER BY rank
LIMIT 5
```

### 5. Results Formatted

Skill formats results and returns to Claude:

```
## Recent Bugfixes

1. [bugfix] Fixed authentication token expiry
   Date: 2025-11-08 14:23:45
   Files: src/auth/jwt.ts

2. [bugfix] Resolved database connection leak
   Date: 2025-11-08 13:15:22
   Files: src/services/database.ts
```

### 6. User Sees Answer

Claude presents the formatted results naturally in conversation.

## Architecture Change (v5.4.0)

### Before: MCP-Based Search

**Approach**: 9 MCP tools registered at session start

**Token Cost**: ~2,500 tokens in tool definitions per session
- Each tool's schema, parameters, descriptions loaded
- All 9 tools available whether needed or not
- No progressive disclosure

**Example MCP Tool**:
```json
{
  "name": "search_observations",
  "description": "Full-text search across observations...",
  "inputSchema": {
    "type": "object",
    "properties": {
      "query": { "type": "string", "description": "..." },
      "type": { "type": "array", "items": { "enum": [...] } },
      "format": { "enum": ["index", "full"] },
      // ... many more parameters
    }
  }
}
```

### After: Skill-Based Search

**Approach**: 1 mem-search skill with progressive disclosure

**Token Cost**: ~250 tokens in skill frontmatter per session
- Only skill description loaded at session start
- Full instructions loaded on-demand when skill is invoked
- HTTP API endpoints instead of MCP protocol

**Example Skill Frontmatter**:
```markdown
# Claude-Mem mem-search Skill

Access claude-mem's persistent memory through a comprehensive HTTP API.
Search for past work, understand context, and learn from previous decisions.

## When to Use This Skill

Invoke this skill when users ask about:
- Past work: "What did we do last session?"
- Bug fixes: "Did we fix this before?"
- Features: "How did we implement authentication?"
...
```

**Token Savings**: ~2,250 tokens per session start (90% reduction)

## HTTP API Endpoints

The worker service exposes 10 search endpoints:

### Full-Text Search

```
GET /api/search/observations
GET /api/search/sessions
GET /api/search/prompts
```

**Parameters**:
- `query` - FTS5 search query (required)
- `type` - Filter by type (bugfix, feature, refactor, etc.)
- `project` - Filter by project name
- `limit` - Maximum results (default: 20)
- `offset` - Pagination offset
- `format` - Response format (index or full)

**Example**:
```bash
curl "http://localhost:37777/api/search/observations?query=authentication&type=decision&limit=5"
```

### Filtered Search

```
GET /api/search/by-type
GET /api/search/by-concept
GET /api/search/by-file
```

**Parameters**:
- `type` / `concept` / `filePath` - Filter criteria (required)
- `project` - Filter by project
- `limit` - Maximum results
- `format` - Response format

**Example**:
```bash
curl "http://localhost:37777/api/search/by-file?filePath=worker-service.ts&limit=10"
```

### Context Retrieval

```
GET /api/context/recent
GET /api/context/timeline
GET /api/timeline/by-query
```

**Parameters**:
- `project` - Filter by project
- `limit` - Number of sessions/records
- `anchor` - Timeline anchor point (ID or timestamp)
- `depth_before` - Records before anchor
- `depth_after` - Records after anchor

**Example**:
```bash
curl "http://localhost:37777/api/context/recent?project=claude-mem&limit=5"
```

### Documentation

```
GET /api/search/help
```

Returns API documentation in JSON format.

## Progressive Disclosure Pattern

The mem-search skill uses progressive disclosure to minimize token usage:

### Layer 1: Skill Frontmatter (Session Start)

**What's Loaded**: Skill description and when to use it (~250 tokens)

**Purpose**: Claude can recognize when to invoke the skill

**Example**:
```markdown
# Claude-Mem mem-search Skill

Access claude-mem's persistent memory through a comprehensive HTTP API.

## When to Use This Skill
Invoke this skill when users ask about:
- Past work: "What did we do last session?"
- Bug fixes: "Did we fix this before?"
...
```

### Layer 2: Full Skill Instructions (On-Demand)

**What's Loaded**: Complete operation documentation (~2,500 tokens)

**Purpose**: Detailed instructions for each search operation

**When Loaded**: Only when Claude invokes the skill

**Example Structure**:
```
/skills/search/
├── SKILL.md (main frontmatter)
├── operations/
│   ├── observations.md (detailed instructions)
│   ├── sessions.md
│   ├── prompts.md
│   ├── by-type.md
│   ├── by-concept.md
│   ├── by-file.md
│   ├── recent-context.md
│   ├── timeline.md
│   ├── timeline-by-query.md
│   ├── help.md
│   ├── formatting.md
│   └── common-workflows.md
```

### Layer 3: API Response

**What's Returned**: Search results in requested format

**Format Options**:
- `index` - Titles, dates, IDs only (~50-100 tokens per result)
- `full` - Complete details (~500-1000 tokens per result)

**Progressive Usage**: Start with `index`, drill down with `full` as needed

## Implementation Details

### mem-search Skill Structure

```
plugin/skills/mem-search/
├── SKILL.md                           # Main frontmatter (~250 tokens)
├── operations/
│   ├── observations.md                # Search observations
│   ├── sessions.md                    # Search sessions
│   ├── prompts.md                     # Search prompts
│   ├── by-type.md                     # Filter by type
│   ├── by-concept.md                  # Filter by concept
│   ├── by-file.md                     # Filter by file
│   ├── recent-context.md              # Get recent context
│   ├── timeline.md                    # Timeline around point
│   ├── timeline-by-query.md           # Search + timeline
│   ├── help.md                        # API documentation
│   ├── formatting.md                  # Result formatting guide
│   └── common-workflows.md            # Usage patterns
```

### Worker Service Integration

**File**: `src/services/worker-service.ts`

**Search Routes**:
```typescript
// Full-text search
app.get('/api/search/observations', handleSearchObservations);
app.get('/api/search/sessions', handleSearchSessions);
app.get('/api/search/prompts', handleSearchPrompts);

// Filtered search
app.get('/api/search/by-type', handleSearchByType);
app.get('/api/search/by-concept', handleSearchByConcept);
app.get('/api/search/by-file', handleSearchByFile);

// Context retrieval
app.get('/api/context/recent', handleRecentContext);
app.get('/api/context/timeline', handleTimeline);
app.get('/api/timeline/by-query', handleTimelineByQuery);

// Documentation
app.get('/api/search/help', handleHelp);
```

**Database Access**:
- Uses `SessionSearch` service for FTS5 queries
- Uses `SessionStore` for structured queries
- Hybrid search with ChromaDB for semantic similarity

### Security

**FTS5 Injection Prevention** (v4.2.3):
```typescript
function escapeFTS5Query(query: string): string {
  return query.replace(/"/g, '""');
}
```

All user-provided search queries are properly escaped to prevent SQL injection.

**Comprehensive Testing**: 332 injection attack tests covering:
- Special characters
- SQL keywords
- Quote escaping
- Boolean operators

## Benefits

### 1. Token Efficiency

**Before (MCP)**:
- Session start: ~2,500 tokens for tool definitions
- Every session pays this cost
- No progressive disclosure

**After (Skill)**:
- Session start: ~250 tokens for skill frontmatter
- Full instructions: ~2,500 tokens (only when invoked)
- Net savings: ~2,250 tokens per session (~90% reduction)

### 2. Natural Language Interface

**Before**: Users needed to learn MCP tool syntax
```
search_observations with query="authentication" and type="decision"
```

**After**: Users ask naturally
```
"What decisions did we make about authentication?"
```

Claude translates to appropriate API call.

### 3. Flexibility

**HTTP API Benefits**:
- Can be called from skills, MCP tools, or other clients
- Easy to test with curl
- Standard REST conventions
- JSON responses

**Progressive Disclosure**:
- Loads only what's needed
- Can add more operations without increasing base cost
- Documentation co-located with operations

### 4. Performance

**Fast Queries**: FTS5 full-text search under 10ms for typical queries

**Caching**: HTTP layer allows response caching

**Pagination**: Efficient result pagination with offset/limit

## Migration Notes

### For Users

**No Action Required**: The migration from MCP to skill-based search is transparent.

**Same Questions Work**: Natural language queries work exactly the same way.

**Invisible Change**: Users won't notice any difference except better performance.

### For Developers

**Renamed**: MCP server (formerly `search-server.ts`, now `src/servers/mcp-server.ts`)
- Source file kept for reference
- No longer built or registered
- MCP configuration removed from `plugin/.mcp.json`

**New Implementation**: Skill-based search
- Skill files: `plugin/skills/mem-search/`
- HTTP endpoints: `src/services/worker-service.ts` (lines 200-400)
- Build script: `npm run build` includes skill files
- Sync script: `npm run sync-marketplace` copies to plugin directory

## Troubleshooting

### Worker Service Not Running

If searches fail, check worker service:

```bash
npm run worker:status       # Check status
npm run worker:restart      # Restart worker
npm run worker:logs         # View logs
```

### HTTP Endpoints Not Responding

Test endpoints directly:

```bash
# Health check
curl http://localhost:37777/health

# Search test
curl "http://localhost:37777/api/search/observations?query=test&limit=1"
```

### Skill Not Invoking

If Claude doesn't invoke the mem-search skill automatically:

1. Check skill files exist: `ls ~/.claude/plugins/marketplaces/thedotmack/plugin/skills/mem-search/`
2. Restart Claude Code session to reload skill definitions
3. Try more explicit phrasing: "Search past sessions for bug fixes" or "What did we do in yesterday's session?"
4. Ensure your question is about previous sessions (not current conversation context)

## Next Steps

- [Search Tools Usage](/usage/search-tools) - User guide with examples
- [Worker Service Architecture](/architecture/worker-service) - HTTP API details
- [Database Schema](/architecture/database) - FTS5 tables and indexes