Files
claude-mem/docs/architecture/overview.mdx
T
Alex Newman 12459eab3b docs: comprehensive v5.1.2 documentation update
This commit brings all documentation up to date with the current v5.1.2
codebase, addressing 12+ critical discrepancies and adding 2 major new
documentation files.

## Files Modified (18 documentation files):

### Root Documentation:
- README.md: Updated version badge (4.3.1 → 5.1.2), tool count (7 → 9),
  added viewer UI and theme toggle features, updated "What's New" section
- CHANGELOG.md: Added 8 missing releases (v4.3.2 through v5.1.2) with
  comprehensive release notes
- CLAUDE.md: Removed hardcoded personal paths, documented all 14 worker
  endpoints (was 8), added Chroma integration overview, updated v5.x releases

### Mintlify Documentation (docs/):
- introduction.mdx: Updated search tool count to 9, added viewer UI and
  theme toggle to features
- configuration.mdx: Added smart-install.js documentation, clarified data
  directory locations, added CLAUDE_CODE_PATH env var, explained observations
  vs sessions, updated hook configuration examples
- development.mdx: Added comprehensive viewer UI development section (103 lines),
  updated build output filenames (search-server.mjs)
- usage/search-tools.mdx: Added get_context_timeline and get_timeline_by_query
  documentation with examples, updated tool count to 9
- architecture/overview.mdx: Updated to 7 hook files, 9 search tools, added
  Chroma to tech stack, enhanced component details with viewer UI
- architecture/hooks.mdx: Added smart-install.js and user-message-hook.js
  documentation, updated hook count to 7
- architecture/worker-service.mdx: Documented all 14 endpoints organized by
  category (Viewer & Health, Data Retrieval, Settings, Session Management)
- architecture/mcp-search.mdx: Added timeline tools documentation, updated
  tool count to 9, fixed filename references (search-server.mjs)
- architecture-evolution.mdx: Added complete v5.x release history (v5.0.0
  through v5.1.2), updated title to "v3 to v5"
- hooks-architecture.mdx: Updated to "Seven Hook Scripts", added smart-install
  and user-message-hook documentation
- troubleshooting.mdx: Added v5.x specific issues section (viewer, theme toggle,
  SSE, Chroma, PM2 Windows fix)

### New Documentation Files:
- docs/VIEWER.md: Complete 400+ line guide to web viewer UI including architecture,
  features, usage, development, API integration, performance considerations
- docs/CHROMA.md: Complete 450+ line guide to vector database integration including
  hybrid search architecture, semantic search explanation, performance benchmarks,
  installation, configuration, troubleshooting

## Key Corrections Made:

1.  Updated version badges and references: 4.3.1 → 5.1.2
2.  Corrected search tool count: 7 → 9 (added get_context_timeline, get_timeline_by_query)
3.  Fixed MCP server filename: search-server.js → search-server.mjs
4.  Updated hook count: 5 → 7 (added smart-install.js, user-message-hook.js)
5.  Documented all 14 worker endpoints (was 8, incorrectly claimed 6 were missing)
6.  Removed hardcoded personal file paths
7.  Added Chroma vector database documentation
8.  Added viewer UI comprehensive documentation
9.  Updated CHANGELOG with all missing v4.3.2-v5.1.2 releases
10.  Clarified data directory locations (production vs development)
11.  Added smart-install.js caching system documentation
12.  Updated SessionStart hook configuration examples

## Documentation Statistics:

- Total files modified: 18
- New files created: 2
- Lines added: ~2,000+
- Version mismatches fixed: 2 critical
- Missing features documented: 5+ major
- Missing tools documented: 2 MCP tools
- Missing endpoints documented: 6 API endpoints

## Impact:

Documentation now accurately reflects the current v5.1.2 codebase with:
- Complete viewer UI documentation (v5.1.0)
- Theme toggle feature (v5.1.2)
- Hybrid search architecture with Chroma (v5.0.0)
- Smart install caching (v5.0.3)
- All 7 hook scripts documented
- All 9 MCP search tools documented
- All 14 worker service endpoints documented
- Comprehensive troubleshooting for v5.x issues

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-06 13:59:10 -05:00

219 lines
11 KiB
Plaintext

---
title: "Architecture Overview"
description: "System components and data flow in Claude-Mem"
---
# Architecture Overview
## System Components
Claude-Mem operates as a Claude Code plugin with five core components:
1. **Plugin Hooks** - Capture lifecycle events (7 hook files)
2. **Worker Service** - Process observations via Claude Agent SDK
3. **Database Layer** - Store sessions and observations (SQLite + FTS5)
4. **MCP Search Server** - Query historical context (9 search tools)
5. **Viewer UI** - Web-based real-time memory stream visualization
## Technology Stack
| Layer | Technology |
|------------------------|-------------------------------------------|
| **Language** | TypeScript (ES2022, ESNext modules) |
| **Runtime** | Node.js 18+ |
| **Database** | SQLite 3 with better-sqlite3 driver |
| **Vector Store** | ChromaDB (optional, for semantic search) |
| **HTTP Server** | Express.js 4.18 |
| **Real-time** | Server-Sent Events (SSE) |
| **UI Framework** | React + TypeScript |
| **AI SDK** | @anthropic-ai/claude-agent-sdk |
| **Build Tool** | esbuild (bundles TypeScript) |
| **Process Manager** | PM2 |
| **Testing** | Node.js built-in test runner |
## Data Flow
### Memory Pipeline
```
Hook (stdin) → Database → Worker Service → SDK Processor → Database → Next Session Hook
```
1. **Input**: Claude Code sends tool execution data via stdin to hooks
2. **Storage**: Hooks write observations to SQLite database
3. **Processing**: Worker service reads observations, processes via SDK
4. **Output**: Processed summaries written back to database
5. **Retrieval**: Next session's context hook reads summaries from database
### Search Pipeline
```
Claude Request → MCP Server → SessionSearch Service → FTS5 Database → Search Results → Claude
```
1. **Query**: Claude uses MCP search tools (e.g., `search_observations`)
2. **Search**: MCP server calls SessionSearch service with query parameters
3. **FTS5**: Full-text search executes against FTS5 virtual tables
4. **Format**: Results formatted as `search_result` blocks with citations
5. **Return**: Claude receives citable search results for analysis
## Session Lifecycle
```
┌─────────────────────────────────────────────────────────────────┐
│ 0. Smart Install Hook Fires │
│ Checks dependencies (cached), only runs on version changes │
└─────────────────────────────────────────────────────────────────┘
┌─────────────────────────────────────────────────────────────────┐
│ 1. Session Starts → Context Hook Fires │
│ Starts PM2 worker if needed, injects context from previous │
│ sessions (configurable observation count) │
└─────────────────────────────────────────────────────────────────┘
┌─────────────────────────────────────────────────────────────────┐
│ 2. User Types Prompt → UserPromptSubmit Hook Fires │
│ Creates session in database, saves raw user prompt for FTS5 │
└─────────────────────────────────────────────────────────────────┘
┌─────────────────────────────────────────────────────────────────┐
│ 3. Claude Uses Tools → PostToolUse Hook Fires (100+ times) │
│ Captures tool executions, sends to worker for AI compression │
└─────────────────────────────────────────────────────────────────┘
┌─────────────────────────────────────────────────────────────────┐
│ 4. Worker Processes → Claude Agent SDK Analyzes │
│ Extracts structured learnings via iterative AI processing │
└─────────────────────────────────────────────────────────────────┘
┌─────────────────────────────────────────────────────────────────┐
│ 5. Claude Stops → Summary Hook Fires │
│ Generates final summary with request, completions, learnings │
└─────────────────────────────────────────────────────────────────┘
┌─────────────────────────────────────────────────────────────────┐
│ 6. Session Ends → Cleanup Hook Fires │
│ Marks session complete (graceful, not DELETE), ready for │
│ next session context. Skips on /clear to preserve ongoing │
└─────────────────────────────────────────────────────────────────┘
```
## Directory Structure
```
claude-mem/
├── src/
│ ├── hooks/ # Hook implementations (7 hooks)
│ │ ├── smart-install.ts # Dependency check (cached)
│ │ ├── context-hook.ts # SessionStart
│ │ ├── user-message-hook.ts # UserMessage (for debugging)
│ │ ├── new-hook.ts # UserPromptSubmit
│ │ ├── save-hook.ts # PostToolUse
│ │ ├── summary-hook.ts # Stop
│ │ └── cleanup-hook.ts # SessionEnd
│ │
│ ├── servers/ # MCP servers
│ │ └── search-server.ts # MCP search tools server (9 tools)
│ │
│ ├── sdk/ # Claude Agent SDK integration
│ │ ├── prompts.ts # XML prompt builders
│ │ ├── parser.ts # XML response parser
│ │ └── worker.ts # Main SDK agent loop
│ │
│ ├── services/
│ │ ├── worker-service.ts # Express HTTP + SSE service
│ │ └── sqlite/ # Database layer
│ │ ├── SessionStore.ts # CRUD operations
│ │ ├── SessionSearch.ts # FTS5 search service
│ │ ├── migrations.ts
│ │ └── types.ts
│ │
│ ├── ui/ # Viewer UI
│ │ └── viewer/ # React + TypeScript web interface
│ │ ├── components/ # UI components
│ │ ├── hooks/ # React hooks
│ │ ├── utils/ # Utilities
│ │ └── assets/ # Fonts, logos
│ │
│ ├── shared/ # Shared utilities
│ │ ├── config.ts
│ │ ├── paths.ts
│ │ └── storage.ts
│ │
│ └── utils/
│ ├── logger.ts
│ ├── platform.ts
│ └── port-allocator.ts
├── plugin/ # Plugin distribution
│ ├── .claude-plugin/
│ │ └── plugin.json
│ ├── .mcp.json # MCP server configuration
│ ├── hooks/
│ │ └── hooks.json
│ ├── scripts/ # Built executables
│ │ ├── smart-install.js
│ │ ├── context-hook.js
│ │ ├── user-message-hook.js
│ │ ├── new-hook.js
│ │ ├── save-hook.js
│ │ ├── summary-hook.js
│ │ ├── cleanup-hook.js
│ │ ├── worker-service.cjs # Background worker
│ │ └── search-server.mjs # MCP search server
│ │
│ └── ui/ # Built viewer UI
│ └── viewer.html # Self-contained bundle
├── tests/ # Test suite
├── docs/ # Documentation
└── ecosystem.config.cjs # PM2 configuration
```
## Component Details
### 1. Plugin Hooks (7 Hooks)
- **smart-install.js** - Cached dependency checker (only runs on version changes)
- **context-hook.js** - SessionStart: Starts PM2 worker, injects context
- **user-message-hook.js** - UserMessage: Debugging hook
- **new-hook.js** - UserPromptSubmit: Creates session, saves prompt
- **save-hook.js** - PostToolUse: Captures tool executions
- **summary-hook.js** - Stop: Generates session summary
- **cleanup-hook.js** - SessionEnd: Marks session complete
See [Plugin Hooks](/architecture/hooks) for detailed hook documentation.
### 2. Worker Service
Express.js HTTP server on port 37777 (configurable) with:
- 8 HTTP/SSE endpoints for viewer UI
- Async observation processing via Claude Agent SDK
- Real-time updates via Server-Sent Events
- Auto-managed by PM2 process manager
See [Worker Service](/architecture/worker-service) for HTTP API and endpoints.
### 3. Database Layer
SQLite3 with better-sqlite3 driver featuring:
- FTS5 virtual tables for full-text search
- SessionStore for CRUD operations
- SessionSearch for FTS5 queries
- Location: `~/.claude-mem/claude-mem.db`
See [Database Architecture](/architecture/database) for schema and FTS5 search.
### 4. MCP Search Server (9 Tools)
Provides 9 specialized search tools:
- search_observations, search_sessions, search_user_prompts
- find_by_concept, find_by_file, find_by_type
- get_recent_context, get_context_timeline, get_timeline_by_query
See [MCP Search Server](/architecture/mcp-search) for search tools and examples.
### 5. Viewer UI
React + TypeScript web interface at http://localhost:37777 featuring:
- Real-time memory stream via Server-Sent Events
- Infinite scroll pagination with automatic deduplication
- Project filtering and settings persistence
- GPU-accelerated animations
- Self-contained HTML bundle (viewer.html)
Built with esbuild into a single file deployment.